Towards precision medicine: from quantitative imaging to radiomics

Towards precision medicine: from quantitative imaging to radiomics 精准医学发展趋势:从定量成像到放射组学 1 2 3 first-author 1 1 4 4 corresp ‡Corresponding Author ‡Corresponding Author †E-mail:ngkh@ummc.edu.my †E-mail:ngkh@ummc.edu.my ngkh@ummc.edu.my Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore Department of Biomedical Engineering, School of Science and Technology, Singapore University of Social Sciences, Singapore 599494, Singapore Department of Biomedical Engineering, School of Science and Technology, Singapore University of Social Sciences, Singapore 599494, Singapore Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia Department of Biomedical Imaging, Faculty of Medicine, University of Malaya, Kuala Lumpur 50603, Malaysia Department of Biomedical Imaging, Faculty of Medicine, University of Malaya, Kuala Lumpur 50603, Malaysia Radiology (imaging) and imaging-guided interventions, which provide multi-parametric morphologic and functional information, are playing an increasingly significant role in precision medicine. Radiologists are trained to understand the imaging phenotypes, transcribe those observations (phenotypes) to correlate with underlying diseases and to characterize the images. However, in order to understand and characterize the molecular phenotype (to obtain genomic information) of solid heterogeneous tumours, the advanced sequencing of those tissues using biopsy is required. Thus, radiologists image the tissues from various views and angles in order to have the complete image phenotypes, thereby acquiring a huge amount of data. Deriving meaningful details from all these radiological data becomes challenging and raises the big data issues. Therefore, interest in the application of radiomics has been growing in recent years as it has the potential to provide significant interpretive and predictive information for decision support. Radiomics is a combination of conventional computer-aided diagnosis, deep learning methods, and human skills, and thus can be used for quantitative characterization of tumour phenotypes. This paper discusses the overview of radiomics workflow, the results of various radiomics-based studies conducted using various radiological images such as computed tomography (CT), magnetic resonance imaging (MRI), and positron-emission tomography (PET), the challenges we are facing, and the potential contribution of radiomics towards precision medicine. (感谢浙江大学医学院附属第二医院核医学科陈琳提供中文概要) Radiological imaging Personalised medicine Precision medicine Quantitative imaging Radiogenomics Radiomics 放射影像学 个体化医学 精准医学 定量成像 放射基因组学 放射组学 Introduction 1 Precision medicine is gaining popularity for providing customised or personalised healthcare (Chen and Snyder, 2013 2013 ). It employs diagnostic testing for the selection of appropriate and optimal therapies (treatments) based on the patient’s genetic context (Chen and Snyder, 2013 2013 ). Thus, by practising precision medicine in healthcare, medical decisions and treatments can be tailored to suit every individual patient’s need. Diagnostic radiology and image-guided intervention are playing an increasingly significant role in precision medicine. For decades, radiology has been dealing with diagnosis and has provided anatomical abnormality information. With the advent of digital technology, quantitative imaging has been contributing to improved diagnosis and in addition, radiological imaging has become a recognised technology in the clinical assessment and confirmation of a disease (Cook et al., 2014 2014 ; WHO, 2017 2017 ). One of the significant contributions of radiology is in oncology, as cancer has become the number one source of mortality in recent years and there is an increasing proliferation of cancer cases in developing countries (Hawkins et al., 2014 2014 ). Different radiological imaging modalities have the capability to detect different information that is present on the various types of tissue. However, extracting informative data from all radiological images is difficult in this era of ‘big data’. The latest progress in computational power and the exploitation of genomics have given rise to a recently developed field of research coined ‘Radiomics’. Radiomics is a promising field of medical research that employs state-of-the-art machine learning techniques to extract imaging features from various modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and positron-emission tomography (PET) to objectively and computably characterise tumour phenotypes. Radiomics was first formally introduced by Lambin et al. in 2012 (Lambin et al., 2012 2012 ; Scrivener et al., 2016 2016 ). It is the extraction and study of huge quantities of features from radiological images and these data are used to predict or decode concealed genetic and molecular traits for decision support (Kumar et al., 2012 2012 ; Cook et al., 2014 2014 ; Court et al., 2016 2016 ; Gillies et al., 2016 2016 ; Narang et al., 2016 2016 ; Yip and Aerts, 2016 2016 ; Sala et al., 2017 2017 ). Radiomics features contain useful spatial and textural information on the greyscale patterns and the correlation between image pixels. Further, these features can be modelled into computer-aided systems that can supplement as an adjunct instrument for individualised diagnosis and treatment guidance (Parekh and Jacobs, 2016 2016 ). Hence, information obtained from these radiological images can also be combined with additional ‘omics’ (genomics, proteomics, metabolomics, and transcriptomics) data for further analysis. Radiomics has been extensively studied in oncology with a substantial contribution from the Quantitative Imaging Network (QIN) and National Cancer Institute (NCI) (Gillies et al., 2016 2016 ). It has been researched and reported, notably in, breast cancer (Wu et al., 2016 2016 ), glioblastoma (Narang et al., 2016 2016 ), head and neck cancer (Wong et al., 2016 2016 ), lung cancer (Scrivener et al., 2016 2016 ), oesophageal cancer (van Rossum et al., 2016 2016 ), prostate cancer (Stoyanova et al., 2016 2016 ), and rectal cancer (Dinapoli et al., 2016 2016 ). Furthermore, radiomics has been adopted in dermatology (Cho et al., 2015 2015 ). Workflow of radiomics 1 Fig. 1 1 shows a typical workflow of radiomics that consists of four main stages. Images 2 The radiological images are acquired from different non-invasive imaging modalities such as CT, MRI, and PET (Castellino, 2005 2005 ; Lambin et al., 2012 2012 ; Aerts, 2016 2016 ; Court et al., 2016 2016 ; Yip and Aerts, 2016 2016 ). These images are pre-processed to ensure that they are consistent and uniformity is maintained. Then, all images are progressively pooled together to form a large database. In addition, the image contrast is enhanced using a technique known as Contrast Limited Adaptive Histogram Equalization (CLAHE) and the noise and artefacts are removed in this pre-processing step (Pizer et al., 1987 1987 ; Wang et al., 2005 2005 ). Segmentation 2 Segmentation is an essential step as highly distinctive features are obtained from the segmented area of the images and these features are used in the development of a model for automated screening of radiological images. The aim of segmentation is to simplify or to modify the image for more meaningful analyses (Aerts, 2016 2016 ). Once the images are pre-processed, segmentation of a region of interest (ROI) is performed. Initially, an ROI is selected as a part of an image that is of interest and where some machine learning algorithms have to be applied (https:// www.mathworks www.mathworks . com/help/images/roi-processing-in-image-processing-toolbox.html). Segmentation of an ROI can be carried out manually, semi-automated, or fully automated. Comparative studies have been reported to increase the performance of fully automated, manual, or semi-automated segmentation of these images (Egger et al., 2013 2013 ; Velazquez et al., 2013 2013 , 2015 2015 ; Kumar et al., 2016 2016 ; Narang et al., 2016 2016 ). The 3D-Slicer is a free open source segmentation software for biomedical research that is widely adopted in the medical field (Velazquez et al., 2013 2013 ). Manual segmentation of the tumour volume is a normal clinical procedure in the planning process before patients receive radiotherapy (Eminowicz and McCormack, 2015 2015 ). Manual delineation is easy but it is highly subjective and labour-intensive. In addition, manual segmentation is not recommended for radiomics evaluation as it requires a large amount of data and would be very time-consuming. Semi-automated segmentation and fully automated segmentation can be performed on radiological images with the help of software and segmentation algorithms. Furthermore, the present consensus is to implement computer-aided edge detection followed by manual adjustment (Gillies et al., 2016 2016 ). The various segmentation techniques namely active contour, level-set, region-based and graph-based methods have been used. The active contour model relies on knowledge of size, position, and structure of the ROI. Based on prior knowledge, the active contour can outline the ROI for segmentation (Kass et al., 1988 1988 ). The level-set model retrieves the shapes and contours from medical images to two or three dimensions (Malladi et al., 1995 1995 ). It is also a sort of active contour modelling (Malladi et al., 1995 1995 ). The region-based technique, on the other hand, is a method based on grey level features. This technique relies on the principle of homogeneity where the ROI is determined by examining its neighbouring pixels relative to the initial seed point (Sonka et al., 2007 2007 ). The graph-based approach is based on the selection of edges from the graph where every single pixel in the image corresponds to a node in the graph (Felzenszwalb and Huttenlocher, 2004 2004 ). The segmentation criterion is then adjusted according to the variability of the pixels in the neighbourhood (Felzenszwalb and Huttenlocher, 2004 2004 ). These segmentation techniques are commonly used in a computer-aided detection system. Recently, deep learning-based approaches such as the convolutional neural network (CNN) have been used for medical image segmentation and demonstrated promising results (Ma et al., 2017a 2017a , 2017b 2017b ). Feature extraction 2 Feature extraction is the next step after an ROI is identified and segmented. Feature extraction is the selection of useful information to assist in the characterization of normal and abnormal radiological images. These features are comprised of intensity, shape, size, and texture of an ROI identified on the images. The shape and size of the tumours are regularly used to define lesions which can be easily identified without computer assistance. On the other hand, the texture of a radiological image is defined by the way the grey levels are apportioned over the pixels in an image (van Rossum et al., 2016 2016 ). These texture features are mathematically extracted using first-order, or second-order, and/or higher-order statistical methods (Davnall et al., 2012 2012 ; Mitra and Shankar, 2015 2015 ; van Rossum et al., 2016 2016 ). First-order statistics are characterised based on the distribution of values of individual voxels without concern for spatial relationships. They are generally histogram-based techniques which reduce an ROI to single value representation for entropy, kurtosis, maximum, mean, median, minimum, skewness, and uniformity of the intensities on the radiological image (Gillies et al., 2016 2016 ). Second-order statistics are universally defined as textural features. They define statistical correlations between voxels with alike or unlike contrast value (Gillies et al., 2016 2016 ). Grey level co-occurrence matrix (GLCM), grey level run-length matrix, and size-zone matrix are typically extracted from the images. Higher-order statistics set filter grids to obtain patterns on these images. Fractal analysis, Gabor transform, Laplacian transforms of Gaussian bandpass filters, laws kernel, and wavelets are commonly performed to extract textural information from the images (Yip and Aerts, 2016 2016 ). Various textural features extracted from radiological images are summarised in Table 1 1 . CCC: concordance correlation coefficient; ROC: receiver operating characteristic; ANOVA: analysis of variance; SVM: support vector machine; GLCM: grey level co-occurrence matrix; CT: computed tomography; BI-RADS: breast imaging reporting and data system; CART: classification and regression tree; PCA: principal component analysis; CBCT: cone beam computed tomography; K-NN: K-nearest neighbour; ROI: region of interest; MRI: magnetic resonance imaging; FLAIR: fluid-attenuated inversion recovery; EGFR: epidermal growth factor receptor; LASSO: least absolute shrinkage and selection operator; VASARI: Visually Accessible Rembrandt Images; DCT: discrete cosine transform; SUV: standardised uptake value; ICC: intraclass correlation; PET: positron-emission tomography; ADASYN: adaptive synthetic; HSD: honest significant difference; FDG: fludeoxyglucose; FLT: fluorothymidine Author (year) Objective of study Radiomics features Techniques used Performance 5 Computed tomography Hunter et al. ( 2013 2013 ) Identify radiomics features that are consistent across multiple diagnostic tools Geometry, intensity histogram, absolute gradient image, textural features Hierarchical clustering, dice similaritycoefficient, Jaccard index, CCC Feature reproducibility is depended on the machine and images Velazquez et al. ( 2013 2013 ) Evaluate the clinical applicability of a semiautomatic segmentation method 3D-Slicer algorithm It is noted that 3D-Slicer illustrated high agreement, smaller uncertainty areas, and lower volume differences as compared to manual slice delineation Aerts et al. ( 2014 2014 ) Assess the correlation of radiomics features with clinical data and the predictive capability of radiomics features Intensity histogram, shape, textural features, wavelet features Friedman test, Wilcoxon test, Kaplan-Meier analysis It is concluded that radiomics features possess prognostic capability Balagurunathan et al. ( 2014b 2014b ) Assess the reproducibility of quantitative imaging features Intensity histogram, textural features, Laws’ kernels features Test-retest CCC, Kaplan-Meier plot Texture features are statistically significant Balagurunathan et al. ( 2014a 2014a ) Assess the reproducibility of image features Morphological features, first-order features, wavelets feature CCC, dynamic range, redundancy reduction, weighted Kappa index, optical threshold linear discriminant analysis, ROC curve It is concluded that most features show high reproducibility with semi-automated segmentation Fried et al. ( 2014 2014 ) Investigate if pre-treatment textural features can enhance the predictive capability in stage III non-small cell lung cancer Intensity histogram, textural features Kaplan-Meier curves, leave-one-out cross-validation, CCC Pre-treatment textural features have better predictive values Parmar et al. ( 2014 2014 ) Evaluate the performance of using 3D-Slicer Intra-class correlation coefficient Radiomics features obtained from 3D-Slicer had notably higher reproducibility than those from manual delineation Hawkins et al. ( 2014 2014 ) Propose an automated prognostic model Intensity histogram, textural features, geometric features Decision tree, leave-one-out cross-validation Accuracy=77.50% Coroller et al. ( 2015 2015 ) Prognostic capability to identify distant metastasis for lung adenocarcinoma patients Intensity histogram, shape and texture Laplacian of Gaussian filter, wavelet filter, minimum relevance feature selection Radiomics features possess strong prognostic capability Parmar et al. ( 2015a 2015a ) Compare radiomics features across different cancer types Intensity histogram, shape, textural and wavelet features Consensus clustering, ROC analysis, concordance index, logistic regression, Jaccard index Radiomics features possess clustering and prognostic characteristics Parmar et al. ( 2015b 2015b ) Assess the different feature selection and classification methods in terms of their performance and prognostic capability Intensity histogram, textural features Various feature selection and classification techniques implemented It is concluded that conditional infomax feature extraction, minimum redundancy maximum relevance, and mutual information feature selection produced the highest stability and predictive capability Cunliffe et al. ( 2015 2015 ) Investigate the correlation of radiation dose and radiomics features and the capability of radiomics features in the analysis of radiation pneumonitis Textural features, fractal features Laws’ filters, linear regression model, ANOVA, ROC curve Radiomics is a promising methodology that can diagnose patients with radiation pneumonitis Mackin et al. ( 2015 2015 ) Study the variability between different CT scanners Textural features General Electric, Philips, Siemens, and Toshiba scanners, feature noise introduced It is verified that the variability in features corresponded in the variability seen in the radiomics features obtained from the images Mattonen et al. ( 2016 2016 ) Physician assessment versus radiomic assessment in the detection of local cancer recurrence for lung cancer First-order statistics features, textural features PRTools 5.0 (Delft Pattern Recognition Research, Delft) was utilised for feature selection and classification, leave-one-out cross-validation, SVM classifier Radiomics can detect early changes associated with local recurrence Mattonen et al. ( 2015 2015 ) Analysis of features for prognostic capability of lung cancer recurrence Textural features PRTools 5.0 (Delft Pattern Recognition Research, Delft) was utilised for classification, Wilcoxon signed rank test High prognostic accuracy using GLCM Wang et al. ( 2016 2016 ) Initiate and evaluate a normalised set of features obtained from CT images and their correlations with overall survival Lexicon of BI-RADS, Fleischner Society as a guide to establish features Weighted Kappa index, Kaplan-Meier analysis, CART classifier, PCA It was reported that textural features are important in the characterisation of lung adenocarcinomas Fave et al. ( 2015 2015 ) Validate the usefulness of predictive models using radiomics features extracted from CT images Textural features CCC analysis Certain radiomics features are resistant to poor-quality CBCT images and noises Huynh et al. ( 2016 2016 ) Analyse stereotactic body radiation therapy with lung cancer Textural, shape, and statistical features PCA, factor analysis, Wilcoxon rank-sum test Radiomics features possess the potential to be predictive Szigeti et al. ( 2016 2016 ) Propose an innovative technique to diagnose lung diseases Nonlinear features Radiomics-based fractal dimension analysis, Kruskal-Wallis test, Mann-Whitney post hoc test, Gaussian curves It is reported that the proposed method is promising and can be implemented in clinical practices Coroller et al. ( 2016 2016 ) Investigate if pre-treatment radiomics features have the prognostic capability in non-small cell lung cancer Textural features Wilcoxon-test, Kaplan-Meier analysis, logistic regression, ROC curve Radiomics features are predictive Zhao et al. ( 2016 2016 ) Investigate the reproducibility of radiomics features Intensity histogram, morphological features, textural features Gabor energy, wavelets, Laplacian of Gaussian, model-based feature of fractal dimension, CCC analysis It is noted that radiomics features are reproducible over different algorithms Yang et al. ( 2016 2016 ) Analyse quantitative imaging features in lung tumours Intensity histogram, textural features, geometric shape CCC analysis, Spearman’s correlation, PCA, edge-preserving smoothing filter Texture features could be utilised for predictive analysis in the future Song et al. ( 2016 2016 ) Investigate if tumour heterogeneity of non-small cell lung cancer can be predicted with radiomics Textural features Statistical analysis Radiomics has prognostic capability for clinical aided diagnosis Wu et al. ( 2016 2016 ) Identify the classifiers for radiomics in lung cancer histology Intensity histogram, shape features, textural features Twenty-four feature selection methods, random forest classifier, naïve Bayes classifier, K-NN classifier, ROC curve Naïve Bayes classifier performed the best; the area under ROC curve: accuracy=0.72 Fave et al. ( 2016 2016 ) Evaluate how different image pre-processing techniques may impact the predictive outcome in univariate analysis Intensity histogram, textural features Harrell’s concordance index (c-index), Benjamini-Hochberg procedure Pre-processing of CT images has an impact on the volume dependence of a feature He et al. ( 2016 2016 ) Examine the effects of contrast-enhancement, reconstruction slice thickness, and convolution kernel on the diagnosis performance of radiomics Textural features Laplacian of Gaussian spatial band-pass filter, statistical analysis, Mann-Whitney U -test It is noted that contrast-enhancement, reconstruction slice thickness, and convolution kernel affect the performance of radiomics Emaminejad Develop a new quantitative image feature analysis scheme and Textural features Naïve Bayesian network-based classifier, leave-one-case-out cross-validation, synthetic minority oversampling technique Accuracy=80.00% Liang et al. ( 2016 2016 ) Review the prognostic ability of radiomics features for the staging of colorectal cancer Textural features Logistic regression model, Mann-Whitney U -test, ROC curve The area under ROC curve: accuracy=0.792; sensitivity=0.611; specificity=0.680 Huang et al. ( 2016 2016 ) Justify the prognostic ability of lymph node metastasis in patients using radiomics nomogram Textural features Statistical analysis, multivariable logistic regression analysis Radiomics nomogram is proved to be useful in clinical settings Kumar et al. ( 2016 2016 ) Analyse an automatic liver segmentation Statistical parameter-based approach It is proven that the proposed method has prognostic capability 5 Magnetic resonance imaging Egger et al. ( 2013 2013 ) Assess the advantages of 3D-Slicer over manual segmentation Dice similarity coefficient, Hausdorff distance It is reported that 3D-Slicer is more time-efficient and is statistically comparable to manual segmentation Zhou et al. ( 2014 2014 ) Determine the differentiating ROIs within the tumour for clinical practices Textural features K-NN classifier K-NN classifier: accuracy=93.75% Coquery et al. ( 2014 2014 ) Assess the possibility if histologic properties can be extracted based on an automated analysis Gaussian mixture modelling, t -tests, linear discriminant analysis It is reported that the integration of spatial selection and cluster analysis can be implemented to form information obtained from the multiparametric MRI Chaddad et al. ( 2015 2015 ) Validate the effectiveness of features extracted from GLCM in glioblastoma phenotypes Textural features Nearest neighbour classifier Accuracy=75.58%; sensitivity=63.95%; specificity=90.69% Chaudhury Validate a new method in the study of heterogeneity in breast cancer Textural kinetic features CCC-based random subspace method, naïve Bayes classifier, decision tree classifier, SVM classifier, Kappa statistic It was concluded that textural kinetic features were more prognostic than features obtained from the whole tumour Upadhaya et al. ( 2015a 2015a ) Study on multimodal MRI in glioblastoma multiforme Intensity histogram, textural features SVM classifier Accuracy=90.00%; sensitivity=85.00%; specificity=95.00% Upadhaya et al. (2015b) Propose a workflow for a predictive model based on textural features Intensity histogram, textural features SVM classifier T1 pre-contrast: accuracy=60.00%; T1 post-contrast: accuracy=82.50%;T2: accuracy=72.50%;FLAIR: accuracy=75.00%; T1 pre-contrast/T1 post-contrast: accuracy=90.00% Lee et al. ( 2015 2015 ) Identify the correlation of radiomics features with EGFR-driven tumours Spatial diversity features Spatial diversity analysis, ROC curve, Characterising EGFR-driven tumours, the area under ROC curve: accuracy=0.790 Depeursinge et al. ( 2015 2015 ) Assess the significance of intensity and textural features Nonlinear features, textural features Riesz wavelet, concordance index, SVM classifier, Cox-LASSO predictive model C-index=0.81±0.02. It is concluded that accuracy is better when features are extracted based on solid components of a tumour instead of the entire tumour Khalvati et al. ( 2015 2015 ) The automatic detection system of prostate cancer using texture features Statistical features, textural features, Gabor features Gabor filter, SVM classifier Proposed technique surpasses conventional model Velazquez et al. ( 2015 2015 ) Assess the predictive value of glioblastoma automatically segmented and compare it with manual segmentation VASARI features The brain tumour image analysis software was utilised, statistical analysis, Spearman rank correlation, CCC analysis, decision tree classifier It is reported that the automatically segmented datasets have potential in medical imaging research Guo et al. ( 2015 2015 ) Determine the efficiency of the prognostic outcome when combining genomic and radiomics features Morphological texture, kinetic curve assessment, enhancement-variance kinetic features Quantitative radiomics analysis, logistic regression, Benjamini-Hochberg procedure, cross-validation with ROC curve Radiomics features have prognostic capability in determining pathological stage Chung et al. ( 2015 2015 ) Present an innovative automated prostate detection algorithm Intensity histogram, textural features Radiomics-driven conditional random field framework, Kirsch edge detection, Gabor filters, SVM classifier Accuracy=91.17%; sensitivity=71.47%; specificity=91.93% van den Burg et al. ( 2016 2016 ) Analysis of labyrinth Intensity histogram Fourier DCT filter, edge detection, gradient orientation filter, entropy filter, Laplacian filter, ridge filter, discrete wavelet transform, image saliency filter, clustering components, morphological components, and binarize colour tone mapping There was significant statistical difference between normal and patients Grossmann et al. ( 2016 2016 ) Investigate the correlation of radiomics features and molecular pathways Volumetric features Gene expression, pathway analysis It is noted that radiomics features contain highly significant features 5 Positron emission tomography Nair et al. ( 2012 2012 ) Investigate radiogenomics with PET Textural features Student’s t -test, chi-squared test, Fisher’s exact test, PCA, SUV, Kaplan-Meier curves It is noted that there is a correlation between gene signatures and features extracted with ʏ18һF-FDG Leijenaar et al. ( 2013 2013 ) Carry out a stability analysis of radiomics features in non-small cell lung carcinoma Intensity histogram, textural features SUV discretisation, ICC, non-parametric ANOVA Radiomics features possess prognostic capability Leijenaar et al. ( 2015 2015 ) Determine the importance of a standardised procedure in tumour texture analysis Textural features SUV discretisation, Kruskal-Wallis one-way ANOVA Experiments showed the importance of standardised procedure in tumour texture analysis Ypsilantis et al. ( 2015 2015 ) Determine if machine learning techniques can predict cancer’s metabolic profile and compare the performance of machine learning algorithms with 3S-convolutional neural network Textural features Convolutional neural networks, SUV, PCA, SVM classifier, logistic regression Sensitivity=80.70%; specificity=81.60%. Convolutional neural networks possess better prognostic capability of response to therapy Tixier et al. ( 2015 2015 ) Compare the results of the visual and prognostic assessment in non-small cell lung cancer Textural features SUV, t -test, Spearman rank coefficient, Kaplan-Meier method, Cox regression model The assessments of both visual and prognostic using textural features are not contradictory to each other Nyflot et al. ( 2015 2015 ) Study the influence of stochastic outcome on textural features Intensity histogram, textural features Power analysis It is concluded that protocols should be implemented to ensure that textural features extracted are standardised Grootjans et al. ( 2016 2016 ) Investigate the effect of respiratory gating and noises in PET images Textural features Fuzzy locally adaptive Bayesian segmentation algorithm, ranking tests It is reported that textural features in this work are resilient in the existence of respiratory motion Lian et al. ( 2016 2016 ) Propose a novel methodology for the prognostic tool in PET imaging Textural features, SUV-based features SUV, Dempster-Shafer theory for feature selection, ADASYN, K-NN classifier Proposed methodology showed promising results 5 Positron emission tomography/computed tomography Cheebsumon et al. ( 2012 2012 ) Comparing PET-and CT-based methods to pathology SUV, statistical analysis Diameter from PET-based delineation has reported a more similar result with pathology as compared to CT-based delineation Yoon et al. ( 2015 2015 ) Discover the predictors of tumours for lung adenocarcinoma Morphological features, histogram-based, regional, and local features Chi-squared test, Student’s t -test, SUV, ten-fold cross-validation method This methodology has potential to be utilised in clinical practice Oliver et al. ( 2015 2015 ) Investigate the difference of image features between RG and 3D images Sphericity, spherical disproportion, entropy, sum entropy, textural features SUV, long axis calculation and rotation analysis It is reported that features obtained from 3D and RG images are different van Velden et al. ( 2016 2016 ) Evaluate the impact of reconstruction techniques and the delineation of radiomics features in non-small cell lung cancer Fractal features, textural features SUV, statistical analysis, Wilcoxon signed-rank test It is noted that the performance of radiomics features is better in delineation than that of applied reconstruction technique Bailly et al. ( 2016 2016 ) Assess the robustness of textural features Textural features SUV, coefficient of variation, one-way ANOVA, Tukey HSD test SUV-based metrics (energy, entropy, RP, and ZP) are found to be robust features Desseroit et al. ( 2016 2016 ) Initiate a nomogram by blending clinical and imaging features Textural features SUV, Kaplan-Meier method, log-rank test Textural features can be used to create a nomogram but need to be further validated 5 Positron emission tomography/magnetic resonance imaging Vallières et al. ( 2015 2015 ) Develop a joint FDG-PET/CT and MRI texture-based model for early diagnosis of lung metastasis risk Textural features SUV, discrete wavelet transform, wavelet band-pass filtering, logistic regression, multivariable analysis, ROC curve The area under ROC curve: accuracy=98.4%; sensitivity=95.5%; specificity=92.6% Antunes et al. ( 2016 2016 ) Investigate the capability of radiomics features in FLT-PET and MRI Filtered-based, entropy and textural features from PET images Sobel and Kirsch edge filters, Gaussian low-pass filter, SUV, Bhattacharyya distance Radiomics has potential to be an effective tool for categorising treatment response in PET/MRI 5 Ultrasonography Acharya et al. ( 2016b 2016b ) Propose a novel algorithm to accurately classify non-alcoholic fatty liver disease DCT Radon transform, fuzzy sugeno, fatty liver disease index Accuracy=100.00%; sensitivity=100.00%; specificity=100.00% Acharya et al. ( 2016c 2016c ) Develop an automated thyroid screening system Entropies Gabor transform, statistical analysis, C4.5 decision tree Accuracy=94.30% Acharya et al. ( 2016a 2016a ) Assess the reliability and robustness of an automated fatty liver disease and cirrhosis diagnosis system Higher-order spectra and entropies Probabilistic neural network, liver disease index Accuracy=97.33%;sensitivity=96.00%;specificity=100.00% Acharya et al. ( 2017 2017 ) Evaluate the performance of a new ultrasonography procedure Second-order statistics Quadratic discriminant analysis, shear wave breast cancer risk index Accuracy=93.59%; sensitivity=90.41%; specificity=96.39% Raghavendra et al. ( 2017 2017 ) Develop a computer-aided diagnosis system to automatically differentiate the different stages of thyroid cancer Textural features SVM, thyroid clinical risk index Accuracy=97.52%; sensitivity=90.32%; specificity=98.57% Ma et al. ( 2017a 2017a ) Initiate and assess an automated thyroid nodules detection system Convolutional neural network The area under ROC curve: accuracy=98.51% Ma et al. ( 2017b 2017b ) Propose a hybrid approach to automatically classify benign and malignant thyroid nodules Convolutional neural network Accuracy=83.02%; sensitivity=82.41%; specificity=84.96% From Table 1 1 , it is observed that textural features are persistently used in the study of radiomics regardless of the radiological modalities (CT, MRI, or PET). Furthermore, Fig. 2 2 shows a summary of the various feature extraction techniques implemented based on the literature review (Table 1 1 ) and it can be noted that textural-based methods are commonly used. Generally, the feature extraction process produces a huge number of features; among them few features are redundant. Therefore, feature reduction or selection is performed to identify useful features from the pool of features extracted. This step significantly boosts the performance of the classifier by selecting only the highly significant features and eliminating redundant features. In addition, statistical tests, namely analysis of variance (ANOVA), Benjamini-Hochberg procedure, chi-squared test, Cox regression model, Friedman test, Kaplan-Meier analysis, Kruskal-Wallis test, Mann-Whitney test, Student’s t -test, Tukey honest significant difference (HSD) test, and Wilcoxon test, are performed to select highly significant features for optimal performance. These statistical tests are used based on different conditions (SPSS Tutorials 2017; https:// www.spss-tutorials.com www.spss-tutorials.com ). Hence, there are different types of statistical tests to implement based on the conditions of the dataset. ANOVA is used for a three-class or more problem with the assumption that the input data are normally distributed. Benjamini-Hochberg procedure is used in a three-class or more problem and when the data are independent of each other. Chi-squared test is a distribution-free test and can be used only when the two-class problem data are independent of each other. Cox regression model works on a normally distributed two-class problem data. Friedman test can be used in a three-class or more problem that does not assume that the data are normally distributed. Also, the Kaplan-Meier analysis can be used in a three-class or more problem in abnormally distributed data. Kruskal-Wallis test is used when there is a three-class or more problem and the data are assumed to be skewed; Mann-Whitney test, also known as the Wilcoxon rank sum test, is used when the data are independent and assumed to be non-normally distributed. Wilcoxon signed rank test, on the other hand, is used when the two-class problem data are dependent and assumed to be non-normally distributed. Student’s t -test is used only when the two-class problem data are assumed to be normally distributed. The Tukey HSD test is used when the three-class or more problem dataset is assumed to be normally distributed. Analysis 2 In the final stage, the selected highly significant features are fed into classifiers for further analysis and assessment. These extracted radiomics features are then examined together with clinical data obtained from other ‘omics’ studies in order to analyse the mutuality of clinical features (information) and radiomics features (Narang et al., 2016 2016 ). The combination of data is known as multilevel data. Classifier models are machine learning algorithms for making accurate predictions based on the training dataset and on the features extracted from radiological images. Machine learning uses algorithms to analyse data, learn the data, and make a prediction with the data. The machine is ‘trained’ with a huge amount of data using algorithms to extract information from the data and to analyse them. Moreover, with the advancement and improvement of machine learning, a subset of machine learning known as deep learning is established. Deep learning is inspired by the anatomy and function of the brain and it involves neural networks with at least three or more hidden layers (Chen et al., 2014 2014 ). The difference between deep learning and conventional machine learning is in the segmentation and feature extraction processes. Deep learning does not require any algorithm to select ROI or to extract significant features for classification. This technique can learn to focus on the right features with least guidance; hence, the potential of deep learning in high-throughput medicine is straightforward (Angermueller et al., 2016 2016 ). However, deep learning is relatively new and has tremendous potential waiting to be explored. Nevertheless, Ma et al. ( 2017a 2017a , 2017b 2017b ) reported the potential by implementing deep learning (CNN) in their work. From the literature review (Table 1 1 ), it can be seen that the different classifiers, namely bagging (Parmar et al., 2015b 2015b ), Bayesian (Parmar et al., 2015b 2015b ), boosting (Parmar et al., 2015b 2015b ), classification and regression tree (CART) (Wang et al., 2015 2015 ), decision tree (Hawkins et al., 2014 2014 ; Chaudhury, 2015 2015 ; Parmar et al., 2015b 2015b ; Velazquez et al., 2015 2015 ), discriminant analysis (Balagurunathan et al., 2014b 2014b ; Coquery et al., 2014 2014 ; Parmar et al., 2015b 2015b ), generalised linear (Parmar et al., 2015b 2015b ), K-nearest neighbour (K-NN) (Zhou et al., 2014 2014 ; Chaddad et al., 2015 2015 ; Parmar et al., 2015b 2015b ; Lian et al., 2016 2016 ; Wu et al., 2016 2016 ), logistic regression (Guo et al., 2015 2015 ; Parmar et al., 2015a 2015a ; Vallières et al., 2015 2015 ; Ypsilantis et al., 2015 2015 ; Coroller et al., 2016 2016 ; Huang et al., 2016 2016 ; Liang et al., 2016 2016 ), naïve Bayes (Chaudhury, 2015 2015 ; Emaminejad et al., 2016 2016 ; Wu et al., 2016 2016 ), neural network (Parmar et al., 2015b 2015b ), random forest (Parmar et al., 2015b 2015b ; Wu et al., 2016 2016 ), and support vector machine (SVM) (Zhou et al., 2014 2014 ; Chaudhury, 2015 2015 ; Chung et al., 2015 2015 ; Depeursinge et al., 2015 2015 ; Khalvati et al., 2015 2015 ; Parmar et al., 2015b 2015b ; Upadhaya et al., 2015a 2015a , 2015b 2015b ; Ypsilantis et al., 2015 2015 ; Mattonen et al., 2016 2016 ), are used. Fig. 3 3 depicts a summary of the types and times of the classifiers used in various studies. SVM: support vector machine; K-NN: K-nearest neighbour; CART: classification and regression tree Discussion 1 In this review, the results of radiomics and various radiomics-based studies conducted using various radiological images such as CT, MRI, PET, and ultrasonography are discussed. The findings of those studies are summarised in Table 1 1 . Cho et al. ( 2015 2015 ) experimented on an automated screening of melanoma and noted that radiomics improved the overall efficacy of characterising benign from malignant melanoma. They achieved an accuracy of 82.4% using 367 dermal radiomics features with the random forest classifier. In the oesophageal cancer review paper by van Rossum et al. ( 2016 2016 ), they reported that textural radiomics features proved to be correlated to the underlying physiologic processes as textural features are valuable characteristics used to extract subtle information from ROIs (Haralick et al., 1973 1973 ). Some researchers have studied the reproducibility and resilience of radiomics features in CT images and concluded that radiomics features can be reproducible (Hunter et al., 2013 2013 ; Balagurunathan et al., 2014a 2014a , 2014b 2014b ; Fried et al., 2014 2014 ; Zhao et al., 2016 2016 ). Hunter et al. ( 2013 2013 ) utilised two different CT scanners obtained from 59 non-small cell lung cancer patients in their experiment to single out radiomics features that are highly significant, non-redundant, and reproducible across the scanners. They found that average derived image features showed superior inter-machine reproducibility as compared to end-exhale and breath-hold images, as well as cine 4D-CT compared to helical 3D-CT. Mackin et al. ( 2015 2015 ) also evaluated the repeatability of radiomics features in images acquired from different scanners and found that there was inter-scanner variability in the mean CT numbers and noise for the 17 CT scanners. In addition, Oliver et al. ( 2015 2015 ) reported a difference between the radiomics features extracted from a static CT image and a respiratory-gated CT image, thus exhibiting the effect of respiratory motion on radiomics features. Hence, we can comment that radiomics features reproducibility and redundancy are dependent on the CT scanners and the type of CT image, as well as the standardisation of image acquisition and reconstruction. To date, there is still limited study on radiomics features using MRI and its reliability. One of the diseases that have been studied is glioblastoma multiforme (GBM), a highly malignant neurologic tumour in the brain exhibiting complex intra-tumoural and inter-patient heterogeneity. Hence, because of the difficulty in obtaining representative biopsies, the underlying radiomics features extracted by processing radiological imaging data are hypothesized to provide detailed phenotypic information (Lambin et al., 2012 2012 ). Narang et al. ( 2016 2016 ) found two main approaches used to develop radiomics features in GBM. Firstly, the standardised semantic features scored by radiologists are used. The features include tumour location, lesion size, proportion enhancing, proportion necrosis, proportion oedema, and definition of enhancing margin. Secondly, fully computational derived features using imaging and statistical techniques are extracted from the images. Semantic features are known to be highly correlated with clinical outcomes, as shown in a study by Lacroix et al. ( 2001 2001 ) on 416 patients with GBM. They found that necrosis and tumour enhancement were a strong prognostic indicator. A Visually Accessible Rembrandt Images (VASARI) feature set comprising 30 semantic features was used to standardise radiological assessment of GBM (https://wiki. cancerimagingarchive.net/display/Public/VASARI+Research+Project). The neuroradiology domain experts agreed that these distinct VASARI features could quantify the phenotype comprehensively and robustly, and these measurements and assessments can be reproducible to provide clinically meaningful and biologically relevant information (Gutman et al., 2013 2013 ). These VASARI features can be extracted using automated phenotype quantification, i.e. radiomics. PET is progressively being used for analysis, cancer staging, and therapy response assessments in tumours (Boellaard, 2009 2009 ; Kato and Nakajima, 2012 2012 ; Rahim et al., 2014 2014 ). In addition, radiomics features extracted from PET images have been used to broaden clinical parameters such as the standardised uptake value (SUV) used to aid visual interpretation (Thie, 2004 2004 ) in clinical practices (Chicklore et al., 2013 2013 ; Tixier et al., 2015 2015 ). Most PET studies included SUVs in their work (Cheebsumon et al., 2012 2012 ; Nair et al., 2012 2012 ; Leijenaar et al., 2013 2013 , 2015 2015 ; Oliver et al., 2015 2015 ; Tixier et al., 2015 2015 ; Vallières et al., 2015 2015 ; Yoon et al., 2015 2015 ; Ypsilantis et al., 2015 2015 ; Antunes et al., 2016 2016 ; Bailly et al., 2016 2016 ; Desseroit et al., 2016 2016 ; Grootjans et al., 2016 2016 ; Lian et al., 2016 2016 ; van Velden et al., 2016 2016 ). Leijenaar et al. ( 2013 2013 ) reported a high test-retest stability of approximately 71% using radiomics features in the analysis of non-small cell lung carcinoma (NSCLC) from PET scans. Moreover, the performance of analysis using radiomics features outperformed inter-observer’s diagnosis. Furthermore, Tixier et al. ( 2015 2015 ) compared inter-observer’s analysis with the analysis made with radiomics for NSCLC, and concluded that a computer-aided diagnosis system using radiomics has a higher prognostic capability and can reduce subjective diagnosis. Tixier et al. ( 2012 2012 ) in another study on oesophageal cancer found that for some textural features such as entropy, dissimilarity, homogeneity, size variability, and intensity of homogenous tumour areas (regional characterization) had reproducibility similar to or better than that of simple SUV measurements. However, several studies found that PET radiomics features are susceptible to reconstruction parameters and the type of image acquisition. Galavis et al. ( 2010 2010 ) in their cohort study of 20 patients with various solid tumours found that 40 out of 50 features tested demonstrated large variations ( > 30%) when the number of iterations, grid size, reconstruction algorithm, and/or post-reconstruction filter were changed. Their findings were further supported by van Velden et al. ( 2016 2016 ) and Yan et al. ( 2015 2015 ). Respiratory motion artefact is also a well-known concern in any imaging modality. Grootjans et al. ( 2016 2016 ) and Oliver et al. ( 2015 2015 ) studied lung cancer with PET and reported that respiratory motion has a considerable effect on the quantification of tumour heterogeneity. From these recent studies, we can conclude that PET radiomics features can be reproducible; however, interpretation of the images and results must be done carefully bearing in mind that there are limitations. The combination of CT and PET imaging is an established diagnostic imaging tool in oncology (Tixier et al., 2015 2015 ; Lu and Chen, 2016 2016 ). PET-CT has an advantage over just PET or CT scan only as PET-CT provides additional information on a tumour (Lu et al., 2015 2015 ). Also, a combination of MRI and PET-CT has been reported (Vallières et al., 2015 2015 ; Antunes et al., 2016 2016 ). Vallières et al. ( 2015 2015 ) proposed a collaborative study with PET and MRI to analyse lung metastasis risk in soft-tissue sarcomas. It was concluded that the radiomics features extracted from the fusion of PET-MRI possess additional prognostic characteristics and could reveal the underlying details from the ROI. It is also noted that there are very few radiomics-based studies using ultrasound modality mainly due to the subjectivity and operator-dependent nature of this modality. As mentioned here, there are very few studies using ultrasound modality mainly due to the subjective and operator-dependent nature of this modality. However, there have been several attempts with very good results (Acharya et al., 2016a 2016a , 2016b 2016b , 2016c 2016c , 2017 2017 ). It is anticipated that more studies will be embarked on this area. Acharya et al. ( 2016b 2016b ) proposed a novel technique to distinguish fatty liver disease using discrete cosine transform and radon transform. They have achieved 100% accuracy, sensitivity, and specificity with the fuzzy sugeno classifier. Also, they developed a fatty liver disease index using a single number to differentiate normal from the fatty liver disease class. Moreover, they extended their work to a three-class problem to differentiate normal, fatty liver disease, and cirrhosis (Acharya et al., 2016a 2016a ). They also formulated a fatty liver disease index to mathematically distinguish the three classes. Further, Acharya et al. ( 2016c 2016c ) explored the possibility of thyroid lesion classification obtained from ultrasound images. They implemented Gabor transform on the images and then extracted entropy features. They attained a performance rate of 94.30% with C4.5 decision tree classifier. In their later work (Acharya et al., 2017 2017 ), they also studied the classification of breast lesion in shear wave ultrasound. In their work, they devised a shear wave breast cancer risk index to distinguish benign and malignant breast lesions. They reported a performance of 93.59% accuracy using a quadratic discriminant analysis classifier. Raghavendra et al. ( 2017 2017 ) explored the fusion of different texture features and extracted various entropies for the discrimination of benign and malignant thyroid lesions. Similarly, they constructed a thyroid clinical risk index to distinguish the two classes using numerical values. Also, Ma et al. ( 2017a 2017a , 2017b 2017b ) proposed CNN-based automatic thyroid nodule detection system. These high performances confirm the application of CNN in developing robust computer-aided diagnosis systems using medical images. Radiogenomics 1 However, utilising radiomics alone is insufficient to qualify as or achieve the goal for precision medicine. More information is needed to consider individual variability in genes for more accurate diagnosis and treatment. Nevertheless, studies have demonstrated that there is a correlation between genomics, proteomics, and radiomics (Segal et al., 2007 2007 ; Zinn et al., 2011 2011 ; Aerts et al., 2014 2014 ; Sala et al., 2017 2017 ). Furthermore, genomics and proteomics have brought overwhelming progress in medicine (Wanichthanarak et al., 2015 2015 ; Aerts, 2016 2016 ). They belong to the ‘omics’ data which have facilitated the state-of-the-art analysis of diverse organismal and molecular processes (Horgan and Kenny, 2011 2011 ; Wanichthanarak et al., 2015 2015 ). Thus, the term radiogenomics was coined as it highlights the synergistic combination of genomics and radiomics. Radiogenomics signifies the broadening of clinical imaging into genomic and molecular imaging (Kuo and Jamshidi, 2014 2014 ) as it focuses on the relationship between features obtained from radiological images and biomolecular markers. Yamamoto et al. ( 2014 2014 ) performed a radiogenomic analysis in non-small cell lung cancer and achieved an accuracy of 78.8%, a sensitivity of 83.3%, and specificity of 77.9%. They concluded that the molecular phenotype and CT imaging, when combined, can distinguish tumours from non-tumours. Moreover, Yamamoto et al. ( 2015 2015 ) conducted another radiogenomic study on breast cancer to investigate the correlations between MRI phenotype, quantitative imaging, and RNA expression. Their experiment showed the potential of radiogenomics in identifying early metastasis. Although radiogenomics is still in its infancy, radiogenomic analysis does possess the potential to reveal a predictive radiomic signature and underlying gene expression patterns. Therefore, for radiogenomics to be formally introduced to clinical settings, radiomics must be firmly established first. Challenges 1 Radiomics is a new multi-disciplinary field and hence, new challenges are inevitable (Kumar et al., 2012 2012 ). Firstly, there is no standardised procedure in image acquisition (Leijenaar et al., 2015 2015 ; Scrivener et al., 2016 2016 ). Different protocols have been implemented by different centres for acquisition and analysis of radiological images. The variation of protocol parameters includes, among others, resolution, field of view, and slice thickness of the images. Thus, studies using these heterogeneous radiological images will not produce accurate comparisons across different sets of radiological images. Secondly, it can be seen from Table 1 1 that there are numerous techniques and algorithms being used. However, there is no standard methodology being developed and therefore, it is unclear which is the best way forward (Dinapoli et al., 2016 2016 ). Furthermore, there is a lack of international protocols and standards for validating results (Sala et al., 2017 2017 ). It is important to validate the re-usability and suitability of a radiomic model to establish rules in this new discipline for a reliable and consistent prognostic tool to be implemented in a clinical setting (Coquery et al., 2014 2014 ; van Rossum et al., 2016 2016 ). Thirdly, sharing of radiological images publicly has always been a problem in clinical research (Nelson, 2009 2009 ; Gillies et al., 2016 2016 ). It is beneficial to have shared databases for maximum information to be extracted from radiological images (Gillies et al., 2016 2016 ). Having an integrated shared database with radiological images and the extracted features will ensure standardisation in radiomic algorithms (Nyflot et al., 2015 2015 ; Gillies et al., 2016 2016 ; Wong et al., 2016 2016 ). Moreover, using the same set of data across various radiomic algorithms will ensure consistency when it comes to inter-comparison and validation of results. Future directions 1 An important achievement is to correlate ‘omics’ data with radiomics features extracted from radiological images and integrate them to create a more efficient and robust prognostic model to aid clinicians in practising personalised medicine. The next step is to implement radiomics as an adjunct tool in clinical settings. However, the challenges discussed here must be addressed first before radiomics could be employed in routine clinical settings. Currently, radiomics is at best fragmented with multiple players. Thus, it is imperative to form an international consortium to bring all researchers together for collaboration. Another focus will be to incorporate deep learning to radiomics as deep learning is currently not being extensively deployed. The deep learning technique reduces the need for feature engineering and thus, it is much more time-efficient and boosts accuracy. 7 Conclusions 2 The increasing use of biomarkers in cancer diagnosis has paved the way for personalised medicine; however, the accuracy and predictive diagnosis and treatment alternatives are further improved by using imaging biomarkers derived from radiomics. In this review, the potentials of radiomics, the current workflow of radiomics, and employment of radiomics are highlighted. Thus, by introducing radiomics in the clinical setting, significant features can be extracted from the radiological images for subsequent analysis of image phenotypes in order to aid clinical decision-making. However, we need to overcome the challenges before radiomics can be successfully introduced into clinical settings. Further development in radiogenomics will bring us closer towards precision medicine. References UR Acharya , U Raghavendra , H Fujita , 等 . Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images . Comput Biol Med , 2016 . 79 250 - 258 . 27825038 DOI: 10.1016/j.compbiomed.2016.10.022 http://doi.org/10.1016/j.compbiomed.2016.10.022 . Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images UR Acharya , H Fujita , VK Sudarshan , 等 . An integrated index for identification of fatty liver disease using radon transform and discrete cosine transform features in ultrasound images . Inform Fusion , 2016 . 31 43 - 53 . DOI: 10.1016/j.inffus.2015.12.007 http://doi.org/10.1016/j.inffus.2015.12.007 . An integrated index for identification of fatty liver disease using radon transform and discrete cosine transform features in ultrasound images UR Acharya , P Chowriappa , H Fujita , 等 . Thyroid lesion classification in 242 patient population using Gabor transform features from high resolution ultrasound images . Knowl-Based Syst , 2016 . 107 235 - 245 . DOI: 10.1016/j.knosys.2016.06.010 http://doi.org/10.1016/j.knosys.2016.06.010 . Thyroid lesion classification in 242 patient population using Gabor transform features from high resolution ultrasound images UR Acharya , WL Ng , K Rahmat , 等 . Data mining framework for breast lesion classification in shear wave ultrasound: a hybrid feature paradigm . Biomed Signal Proces , 2017 . 33 400 - 410 . DOI: 10.1016/j.bspc.2016.11.004 http://doi.org/10.1016/j.bspc.2016.11.004 . Data mining framework for breast lesion classification in shear wave ultrasound: a hybrid feature paradigm HJWL Aerts . The potential of radiomic-based phenotyping in precision medicine: a review . JAMA Oncol , 2016 . 2 1636 - 1642 . 27541161 DOI: 10.1001/jamaoncol.2016.2631 http://doi.org/10.1001/jamaoncol.2016.2631 . The potential of radiomic-based phenotyping in precision medicine: a review HJWL Aerts , ER Velazquez , RTH Leijenaar , 等 . Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach . Nat Commun, 5:4006 , 2014 . DOI: 10.1038/ncomms5006 http://doi.org/10.1038/ncomms5006 . Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach C Angermueller , T Pärnamaa , L Parts , 等 . Deep learning for computational biology . Mol Syst Biol, 12: 878 , 2016 . DOI: 10.15252/msb.20156651 http://doi.org/10.15252/msb.20156651 . Deep learning for computational biology J Antunes , S Viswanath , M Rusu , 等 . Radiomics analysis on FLT-PET/MRI for characterisation of early treatment response in renal cell carcinoma: a proof of concept study . Transl Oncol , 2016 . 9 ( 2 ): 155 - 162 . 27084432 DOI: 10.1016/j.tranon.2016.01.008 http://doi.org/10.1016/j.tranon.2016.01.008 . Radiomics analysis on FLT-PET/MRI for characterisation of early treatment response in renal cell carcinoma: a proof of concept study C Bailly , C Bodet-Milin , S Couespel , 等 . Revisiting the robustness of PET-based textural features in the context of multi-centric trials . PLoS ONE, 11:7 , 2016 . DOI: 10.1371/journal.pone.0159984 http://doi.org/10.1371/journal.pone.0159984 . Revisiting the robustness of PET-based textural features in the context of multi-centric trials Y Balagurunathan , YH Gu , H Wang , 等 . Reproducibility and prognosis of quantitative features extracted from CT images . Transl Oncol , 2014 . 7 ( 1 ): 72 - 87 . 24772210 DOI: 10.1593/tlo.13844 http://doi.org/10.1593/tlo.13844 . Reproducibility and prognosis of quantitative features extracted from CT images Y Balagurunathan , V Kumar , YH Gu , 等 . Test-retest reproducibility analysis of lung CT image features . J Digit Imaging , 2014 . 27 ( 6 ): 805 - 823 . 24990346 DOI: 10.1007/s10278-014-9716-x http://doi.org/10.1007/s10278-014-9716-x . Test-retest reproducibility analysis of lung CT image features R Boellaard . Standards for PET image acquisition and quantitative data analysis . J Nuclear Med, 50:11S-20S , 2009 . DOI: 10.2967/jnumed.108.057182 http://doi.org/10.2967/jnumed.108.057182 . Standards for PET image acquisition and quantitative data analysis RA Castellino . Computer-aided detection (CAD): an overview . Cancer Imaging , 2005 . 5 17 - 19 . 16154813 DOI: 10.1102/1470-7330.2005.0018 http://doi.org/10.1102/1470-7330.2005.0018 . Computer-aided detection (CAD): an overview A Chaddad , PO Zinn , RR Colen . Radiomics texture feature extraction for characterising GBM phenotypes using GLCM . 2015 . IEEE 12th International Symposium on Biomedical Imaging (ISBI). New York, USA . . Radiomics texture feature extraction for characterising GBM phenotypes using GLCM B Chaudhury . The Use of Textural Kinetic Habitats to Mine Diagnostic Information from DCE MR Images of Breast Tumours , 2015 . : Fowler Avenue, Tampa, USA University of South Florida, , PhD Theses . The Use of Textural Kinetic Habitats to Mine Diagnostic Information from DCE MR Images of Breast Tumours P Cheebsumon , R Boelaard , D de Ruysscher , 等 . Assessment of tumour size in PET/CT lung cancer studies: PET-and CT-based methods compared to pathology . EJNMMI Res , 2012 . 2 ( 1 ): 56 23034289 DOI: 10.1186/2191-219X-2-56 http://doi.org/10.1186/2191-219X-2-56 . Assessment of tumour size in PET/CT lung cancer studies: PET-and CT-based methods compared to pathology R Chen , M Snyder . Promise of personalized omics to precision medicine . Wiley Interdiscip Rev Syst Biol Med , 2013 . 5 ( 1 ): 73 - 82 . 23184638 DOI: 10.1002/wsbm.1198 http://doi.org/10.1002/wsbm.1198 . Promise of personalized omics to precision medicine YS Chen , ZH Lin , X Zhao , 等 . Deep learning-based classification of hyperspectral data . IEEE J-STARS , 2014 . 7 ( 6 ): 2094 - 2107 . DOI: 10.1109/JSTARS.2014.2329330 http://doi.org/10.1109/JSTARS.2014.2329330 . Deep learning-based classification of hyperspectral data S Chicklore , V Goh , M Siddique , 等 . Quantifying tumour heterogeneity in 18F-FDG PET/CT imaging by texture analysis . Eur J Nucl Med Mol Imaging , 2013 . 40 ( 1 ): 133 - 140 . 23064544 DOI: 10.1007/s00259-012-2247-0 http://doi.org/10.1007/s00259-012-2247-0 . Quantifying tumour heterogeneity in 18F-FDG PET/CT imaging by texture analysis DS Cho , DA Clausi , A Wong . Dermal radiomics for melanoma screening . Vision Lett , 2015 . 1 ( 1 ): 23 DOI: 10.15353/vsnl.v1i1.58 http://doi.org/10.15353/vsnl.v1i1.58 . Dermal radiomics for melanoma screening AG Chung , F Khalvati , MJ Shafiee , 等 . Prostate cancer detection via a quantitative radiomics-driven conditional random field framework . IEEE Access , 2015 . 3 2531 - 2541 . DOI: 10.1109/ACCESS.2015.2502220 http://doi.org/10.1109/ACCESS.2015.2502220 . Prostate cancer detection via a quantitative radiomics-driven conditional random field framework GJR Cook , M Siddique , BP Taylor , 等 . Radiomics in PET: principles and applications . Clin Transl Imaging , 2014 . 2 ( 3 ): 269 - 276 . DOI: 10.1007/s40336-014-0064-0 http://doi.org/10.1007/s40336-014-0064-0 . Radiomics in PET: principles and applications N Coquery , O Francois , B Lemasson , 等 . Microvascular MRI and unsupervised clustering yields histology-resembling images in two rat models of glioma . J Cerebr Blood Met , 2014 . 34 ( 8 ): 1354 - 1362 . DOI: 10.1038/jcbfm.2014.90 http://doi.org/10.1038/jcbfm.2014.90 . Microvascular MRI and unsupervised clustering yields histology-resembling images in two rat models of glioma TP Coroller , P Grossmann , Y Hou , 等 . CT-based radiomic signature predicts metastasis in lung adenocarcinoma . J Eur Soc Therapeut Radiol Oncol , 2015 . 114 ( 3 ): 345 - 350 . DOI: 10.1016/j.radonc.2015.02.015 http://doi.org/10.1016/j.radonc.2015.02.015 . CT-based radiomic signature predicts metastasis in lung adenocarcinoma TP Coroller , V Agrawal , V Narayan , 等 . Radiomic phenotype features predict pathological response in non-small cell lung cancer . Radiother Oncol , 2016 . 119 ( 3 ): 480 - 486 . 27085484 DOI: 10.1016/j.radonc.2016.04.004 http://doi.org/10.1016/j.radonc.2016.04.004 . Radiomic phenotype features predict pathological response in non-small cell lung cancer LE Court , X Fave , D Mackin , 等 . Computational resources for radiomics . Transl Cancer Res , 2016 . 5 ( 4 ): 340 - 348 . DOI: 10.21037/tcr.2016.06.17 http://doi.org/10.21037/tcr.2016.06.17 . Computational resources for radiomics A Cunliffe , SG Armato III , R Castillo , 等 . Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development . Int J Radiat Oncol , 2015 . 91 ( 5 ): 1048 - 1056 . DOI: 10.1016/j.ijrobp.2014.11.030 http://doi.org/10.1016/j.ijrobp.2014.11.030 . Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development F Davnall , CSP Yip , G Ljungqvist , 等 . Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? . Insights Imaging , 2012 . 3 ( 6 ): 573 - 589 . DOI: 10.1007/s13244-012-0196-6 http://doi.org/10.1007/s13244-012-0196-6 . Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? A Depeursinge , M Yanagawa , AN Leung , 等 . Predicting adenocarcinoma recurrence using computational texture models of nodule components in lung CT . Med Phys , 2015 . 42 ( 4 ): 2054 - 2063 . DOI: 10.1118/1.4916088 http://doi.org/10.1118/1.4916088 . Predicting adenocarcinoma recurrence using computational texture models of nodule components in lung CT MC Desseroit , D Visvikis , F Tixier , 等 . Development of a nomogram combining clinical staging with 18F-FDG PET/CT image features in non-small-cell lung cancer stage I‒III . Eur J Nucl Med Mol Imaging , 2016 . 43 ( 8 ): 1477 - 1485 . DOI: 10.1007/s00259-016-3325-5 http://doi.org/10.1007/s00259-016-3325-5 . Development of a nomogram combining clinical staging with 18F-FDG PET/CT image features in non-small-cell lung cancer stage I‒III N Dinapoli , C Casa , B Barbaro , 等 . Radiomics for rectal cancer . Transl Cancer Res , 2016 . 5 ( 4 ): 424 - 431 . DOI: 10.21037/tlcr.2016.08.01 http://doi.org/10.21037/tlcr.2016.08.01 . Radiomics for rectal cancer J Egger , T Kapur , A Fedorov , 等 . GBM volumetry using the 3D Slicer medical image computing platform . Sci Rep , 2013 . 3 1364 DOI: 10.1038/srep01364 http://doi.org/10.1038/srep01364 . GBM volumetry using the 3D Slicer medical image computing platform N Emaminejad , W Qian , YB Guan , 等 . Fusion of quantitative image and genomic biomarkers to improve prognosis assessment of early stage lung cancer patients . IEEE Trans Biomed Eng , 2016 . 63 ( 5 ): 1034 - 1043 . DOI: 10.1109/TBME.2015.2477688 http://doi.org/10.1109/TBME.2015.2477688 . Fusion of quantitative image and genomic biomarkers to improve prognosis assessment of early stage lung cancer patients G Eminowicz , M McCormack . Variability of clinical target volume delineation for definitive radiotherapy in cervix cancer . Radiother Oncol , 2015 . 117 ( 3 ): 542 - 547 . DOI: 10.1016/j.radonc.2015.10.007 http://doi.org/10.1016/j.radonc.2015.10.007 . Variability of clinical target volume delineation for definitive radiotherapy in cervix cancer X Fave , D Mackin , JZ Yang , 等 . Can radiomics features be reproducibly measured from CBCT images for patients with non-small cell lung cancer? . Med Phys , 2015 . 42 ( 12 ): 6784 - 6797 . DOI: 10.1118/1.4934826 http://doi.org/10.1118/1.4934826 . Can radiomics features be reproducibly measured from CBCT images for patients with non-small cell lung cancer? X Fave , LF Zhang , JZ Yang , 等 . Impact of image preprocessing on the volume dependence and prognostic potential of radiomics features in non-small cell lung cancer . Transl Cancer Res , 2016 . 5 ( 4 ): 349 - 363 . DOI: 10.21037/tcr.2016.07.11 http://doi.org/10.21037/tcr.2016.07.11 . Impact of image preprocessing on the volume dependence and prognostic potential of radiomics features in non-small cell lung cancer PF Felzenszwalb , DP Huttenlocher . Efficient graph-based image segmentation . Int J Comput Vision , 2004 . 59 ( 2 ): 167 - 181 . DOI: 10.1023/B:VISI.0000022288.19776.77 http://doi.org/10.1023/B:VISI.0000022288.19776.77 . Efficient graph-based image segmentation DV Fried , SL Tucker , SH Zhou , 等 . Prognostic value and reproducibility of pretreatment CT texture features in stage III non-small cell lung cancer . Int J Radiat Oncol Biol Phys , 2014 . 90 ( 4 ): 834 - 842 . DOI: 10.1016/j.ijrobp.2014.07.020 http://doi.org/10.1016/j.ijrobp.2014.07.020 . Prognostic value and reproducibility of pretreatment CT texture features in stage III non-small cell lung cancer PE Galavis , C Hollensen , N Jallow , 等 . Variability of textural features in FDG PET images due to different acquisition modes and reconstruction parameters . Acta Oncol , 2010 . 49 ( 7 ): 1012 - 1016 . DOI: 10.3109/0284186X.2010.498437 http://doi.org/10.3109/0284186X.2010.498437 . Variability of textural features in FDG PET images due to different acquisition modes and reconstruction parameters RJ Gillies , PE Kinahan , H Hricak . Radiomics: images are more than pictures, they are data . Radiology , 2016 . 278 ( 2 ): 563 - 577 . DOI: 10.1148/radiol.2015151169 http://doi.org/10.1148/radiol.2015151169 . Radiomics: images are more than pictures, they are data W Grootjans , F Tixier , CS van der Vos , 等 . The impact of optimal respiratory gating and image noise on evaluation of intratumor heterogeneity on 18F-FDG PET imaging of lung cancer . J Nucl Med , 2016 . 57 ( 11 ): 1692 - 1698 . DOI: 10.2967/jnumed.116.173112 http://doi.org/10.2967/jnumed.116.173112 . The impact of optimal respiratory gating and image noise on evaluation of intratumor heterogeneity on 18F-FDG PET imaging of lung cancer P Grossmann , DA Gutman , WD Dunn Jr , 等 . Imaging-genomics reveals driving pathways of MRI derived volumetric tumor phenotype features in glioblastoma . 2016 . BMC Cancer, 16:611 . . Imaging-genomics reveals driving pathways of MRI derived volumetric tumor phenotype features in glioblastoma WT Guo , H Li , YT Zhu , 等 . Prediction of clinical phenotypes in invasive breast carcinomas from the integration of radiomics and genomics data . J Med Imaging , 2015 . 2 ( 4 ): 041007 DOI: 10.1117/1.JMI.2.4.041007 http://doi.org/10.1117/1.JMI.2.4.041007 . Prediction of clinical phenotypes in invasive breast carcinomas from the integration of radiomics and genomics data DA Gutman , LAD Cooper , SN Hwang , 等 . MR imaging predictors of molecular profile and survival: multi-institutional study of the TCGA glioblastoma data set . Radiology , 2013 . 267 ( 2 ): 560 - 569 . DOI: 10.1148/radiol.13120118 http://doi.org/10.1148/radiol.13120118 . MR imaging predictors of molecular profile and survival: multi-institutional study of the TCGA glioblastoma data set RM Haralick , K Shanmugam , I Dinstein . Textural features for image classification . IEEE Trans Syst Man Cybernetics , 1973 . SMC-3 ( 6 ): 610 - 621 . DOI: 10.1109/TSMC.1973.4309314 http://doi.org/10.1109/TSMC.1973.4309314 . Textural features for image classification SH Hawkins , JN Korecki , Y Balagurunathan , 等 . Predicting outcomes of non-small cell lung cancer using CT image features . IEEE Access , 2014 . 2 1418 - 1426 . DOI: 10.1109/ACCESS.2014.2373335 http://doi.org/10.1109/ACCESS.2014.2373335 . Predicting outcomes of non-small cell lung cancer using CT image features L He , YQ Huang , ZL Ma , 等 . Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule . Sci Rep, 6:34921 , 2016 . DOI: 10.1038/srep34921 http://doi.org/10.1038/srep34921 . Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule RP Horgan , LC Kenny . SAC review ‘Omic’ technologies: genomics, transcriptomics, proteomics and metabolomics . Obstet Gynaecol , 2011 . 13 ( 3 ): 189 - 195 . . SAC review ‘Omic’ technologies: genomics, transcriptomics, proteomics and metabolomics YQ Huang , CH Liang , L He , 等 . Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer . J Clin Oncol , 2016 . 34 ( 18 ): 2157 - 2164 . 27138577 DOI: 10.1200/JCO.2015.65.9128 http://doi.org/10.1200/JCO.2015.65.9128 . Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer LA Hunter , S Krafft , F Stingo , 等 . High-quality machine-robust image features: identification in non-small cell lung cancer computed tomography images . Med Phys , 2013 . 40 ( 12 ): 121916 24320527 DOI: 10.1118/1.4829514 http://doi.org/10.1118/1.4829514 . High-quality machine-robust image features: identification in non-small cell lung cancer computed tomography images E Huynh , TP Coroller , V Narayan , 等 . CT-based radiomic analysis of stereotactic body radiation therapy patients with lung cancer . Radiother Oncol , 2016 . 120 ( 2 ): 258 - 266 . 27296412 DOI: 10.1016/j.radonc.2016.05.024 http://doi.org/10.1016/j.radonc.2016.05.024 . CT-based radiomic analysis of stereotactic body radiation therapy patients with lung cancer M Kass , A Witkin , D Terzopoulos . Snakes: active contour models . Int J Comput Vision , 1988 . 1 ( 4 ): 321 - 331 . DOI: 10.1007/BF00133570 http://doi.org/10.1007/BF00133570 . Snakes: active contour models H Kato , M Nakajima . The efficacy of FDG-PET for the management of esophageal cancer: review article . Ann Thorac Cardiovasc Surg , 2012 . 18 ( 5 ): 412 - 419 . 22785452 DOI: 10.5761/atcs.ra.12.01954 http://doi.org/10.5761/atcs.ra.12.01954 . The efficacy of FDG-PET for the management of esophageal cancer: review article F Khalvati , A Wong , MA Haider . Automated prostate cancer detection via comprehensive multi-parametric magnetic resonance imaging texture feature models . BMC Med Imaging, 15:27 , 2015 . DOI: 10.1186/s12880-015-0069-9 http://doi.org/10.1186/s12880-015-0069-9 . Automated prostate cancer detection via comprehensive multi-parametric magnetic resonance imaging texture feature models V Kumar , Y Gu , S Basu , 等 . Radiomics: the process and the challenges . Magn Reson Imaging , 2012 . 30 ( 9 ): 1234 - 1248 . 22898692 DOI: 10.1016/j.mri.2012.06.010 http://doi.org/10.1016/j.mri.2012.06.010 . Radiomics: the process and the challenges YR Kumar , NM Muthukrishnan , A Mahajan , 等 . Statistical parameter-based automatic liver tumor segmentation from abdominal CT scans: a potiential radiomic signature . Proced Comput Sci , 2016 . 93 446 - 452 . DOI: 10.1016/j.procs.2016.07.232 http://doi.org/10.1016/j.procs.2016.07.232 . Statistical parameter-based automatic liver tumor segmentation from abdominal CT scans: a potiential radiomic signature MD Kuo , N Jamshidi . Behind the numbers: decoding molecular phenotypes with radiogenomics–guiding principles and technical considerations . Radiology , 2014 . 270 ( 2 ): 320 - 325 . 24471381 DOI: 10.1148/radiol.13132195 http://doi.org/10.1148/radiol.13132195 . Behind the numbers: decoding molecular phenotypes with radiogenomics–guiding principles and technical considerations M Lacroix , D Abi-Said , DR Fourney , 等 . A multivariate analysis of 416 patients with glioblastoma multiforme: prognosis, extent of resection, and survival . J Neurosur , 2001 . 95 ( 2 ): 190 - 198 . DOI: 10.3171/jns.2001.95.2.0190 http://doi.org/10.3171/jns.2001.95.2.0190 . A multivariate analysis of 416 patients with glioblastoma multiforme: prognosis, extent of resection, and survival P Lambin , E Rios-Velazquez , R Leijenaar , 等 . Radiomics: extracting more information from medical images using advanced feature analysis . Eur J Cancer , 2012 . 48 ( 4 ): 441 - 446 . 22257792 DOI: 10.1016/j.ejca.2011.11.036 http://doi.org/10.1016/j.ejca.2011.11.036 . Radiomics: extracting more information from medical images using advanced feature analysis JS Lee , S Narang , JJ Martinez , 等 . Associating spatial diversity features of radiologically defined tumor habitats with epidermal growth factor receptor driver status and 12-month survival in glioblastoma: methods and preliminary investigation . J Med Imaging , 2015 . 2 ( 4 ): 041006 DOI: 10.1117/1.JMI.2.4.041006 http://doi.org/10.1117/1.JMI.2.4.041006 . Associating spatial diversity features of radiologically defined tumor habitats with epidermal growth factor receptor driver status and 12-month survival in glioblastoma: methods and preliminary investigation RTH Leijenaar , S Carvalho , ER Velazquez , 等 . Stability of FDG-PET radiomics features: an integrated analysis of test-retest and inter-observer variability . Acta Oncol , 2013 . 52 ( 7 ): 1391 - 1397 . 24047337 DOI: 10.3109/0284186X.2013.812798 http://doi.org/10.3109/0284186X.2013.812798 . Stability of FDG-PET radiomics features: an integrated analysis of test-retest and inter-observer variability RTH Leijenaar , G Nalbantov , S Carvalho , 等 . The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis . Sci Rep, 5:11075 , 2015 . DOI: 10.1038/srep11075 http://doi.org/10.1038/srep11075 . The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis CF Lian , S Ruan , T Denoeux , 等 . Selecting radiomic features from FDG-PET images for cancer treatment outcome prediction . Med Image Anal , 2016 . 32 257 - 268 . 27236221 DOI: 10.1016/j.media.2016.05.007 http://doi.org/10.1016/j.media.2016.05.007 . Selecting radiomic features from FDG-PET images for cancer treatment outcome prediction CS Liang , YQ Huang , L He , 等 . The development and validation of a CT-based radiomics signature for the preoperative discrimination of stage I‒II and stage III‒IV colorectal cancer . Oncotarget , 2016 . 7 ( 21 ): 31401 - 31412 . 27120787 DOI: 10.18632/oncotarget.8919 http://doi.org/10.18632/oncotarget.8919 . The development and validation of a CT-based radiomics signature for the preoperative discrimination of stage I‒II and stage III‒IV colorectal cancer W Lu , W Chen . Positron emission tomography/computerized tomography for tumor response assessment–a review of clinical practices and radiomics studies . Transl Cancer Res , 2016 . 5 ( 4 ): 364 - 370 . 27904837 DOI: 10.21037/tcr.2016.07.12 http://doi.org/10.21037/tcr.2016.07.12 . Positron emission tomography/computerized tomography for tumor response assessment–a review of clinical practices and radiomics studies W Lu , J Wang , HH Zhang . Computerized PET/CT image analysis in the evaluation of tumour response to therapy . Brit J Radiol , 2015 . 88 ( 1048 ): 20140625 25723599 DOI: 10.1259/bjr.20140625 http://doi.org/10.1259/bjr.20140625 . Computerized PET/CT image analysis in the evaluation of tumour response to therapy J Ma , F Wu , T Jiang , 等 . Cascade convolutional neural networks for automatic detection of thyroid nodules in ultrasound images . Med Phys , 2017 . 44 ( 5 ): 1678 - 1691 . 28186630 DOI: 10.1002/mp.12134 http://doi.org/10.1002/mp.12134 . Cascade convolutional neural networks for automatic detection of thyroid nodules in ultrasound images J Ma , F Wu , J Zhu , 等 . A pre-trained convolutional neural network based method for thyroid nodule diagnosis . Ultrasonics , 2017 . 73 221 - 230 . 27668999 DOI: 10.1016/j.ultras.2016.09.011 http://doi.org/10.1016/j.ultras.2016.09.011 . A pre-trained convolutional neural network based method for thyroid nodule diagnosis D Mackin , X Fave , LF Zhang , 等 . Measuring computed tomography scanner variability of radiomics features . Invest Radiol , 2015 . 50 ( 11 ): 757 - 765 . 26115366 DOI: 10.1097/RLI.0000000000000180 http://doi.org/10.1097/RLI.0000000000000180 . Measuring computed tomography scanner variability of radiomics features R Malladi , JA Sethian , BC Vemuri . Shape modeling with front propagation: a level set approach . IEEE Trans Pattern Anal Machine Intell , 1995 . 17 ( 2 ): 158 - 175 . DOI: 10.1109/34.368173 http://doi.org/10.1109/34.368173 . Shape modeling with front propagation: a level set approach SA Mattonen , S Tetar , DA Palma , 等 . Imaging texture analysis for automated prediction of lung cancer recurrence after stereotactic radiotherapy . J Med Imaging , 2015 . 2 ( 4 ): 041010 DOI: 10.1117/1.JMI.2.4.041010 http://doi.org/10.1117/1.JMI.2.4.041010 . Imaging texture analysis for automated prediction of lung cancer recurrence after stereotactic radiotherapy SA Mattonen , DA Palma , C Johnson , 等 . Detection of local cancer recurrence after stereotactic ablative radiation therapy for lung cancer: physician performance versus radiomic assessment . Int J Radiat Oncol Biol Phys , 2016 . 94 ( 5 ): 1121 - 1128 . 26907916 DOI: 10.1016/j.ijrobp.2015.12.369 http://doi.org/10.1016/j.ijrobp.2015.12.369 . Detection of local cancer recurrence after stereotactic ablative radiation therapy for lung cancer: physician performance versus radiomic assessment S Mitra , BU Shankar . Medical image analysis for cancer management in natural computing framework . Inform Sci , 2015 . 306 111 - 131 . DOI: 10.1016/j.ins.2015.02.015 http://doi.org/10.1016/j.ins.2015.02.015 . Medical image analysis for cancer management in natural computing framework VS Nair , O Gevaert , G Davidzon , 等 . Prognostic PET 18 F-FDG uptake imaging features are associated with major oncogenomic alterations in patients with resected non-small cell lung cancer . Cancer Res , 2012 . 72 ( 15 ): 3725 - 3734 . 22710433 DOI: 10.1158/0008-5472.CAN-11-3943 http://doi.org/10.1158/0008-5472.CAN-11-3943 . Prognostic PET 18F-FDG uptake imaging features are associated with major oncogenomic alterations in patients with resected non-small cell lung cancer S Narang , M Lehrer , D Yang , 等 . Radiomics in glioblastoma: current status, challenges and potential opportunities . Transl Cancer Res , 2016 . 5 ( 4 ): 383 - 397 . DOI: 10.21037/tcr.2016.06.31 http://doi.org/10.21037/tcr.2016.06.31 . Radiomics in glioblastoma: current status, challenges and potential opportunities B Nelson . Data sharing: empty archives . Nature , 2009 . 461 160 - 163 . 19741679 DOI: 10.1038/461160a http://doi.org/10.1038/461160a . Data sharing: empty archives MJ Nyflot , F Yang , D Byrd , 等 . Quantitative radiomics: impact of stochastic effects on textural feature analysis implies the need for standards . J Med Imaging , 2015 . 2 ( 4 ): 041002 DOI: 10.1117/1.JMI.2.4.041002 http://doi.org/10.1117/1.JMI.2.4.041002 . Quantitative radiomics: impact of stochastic effects on textural feature analysis implies the need for standards JA Oliver , M Budzevich , GG Zhang , 等 . Variability of image features computed from conventional and respiratory-gated PET/CT images of lung cancer . Transl Oncol , 2015 . 8 ( 6 ): 524 - 534 . 26692535 DOI: 10.1016/j.tranon.2015.11.013 http://doi.org/10.1016/j.tranon.2015.11.013 . Variability of image features computed from conventional and respiratory-gated PET/CT images of lung cancer V Parekh , MA Jacobs . Radiomics: a new application from established techniques . Expert Rev Precis Med Drug Dev , 2016 . 1 ( 2 ): 207 - 226 . 28042608 DOI: 10.1080/23808993.2016.1164013 http://doi.org/10.1080/23808993.2016.1164013 . Radiomics: a new application from established techniques C Parmar , ER Velazquez , R Leijenaar , 等 . Robust radiomics feature quantification using semiautomatic volumetric segmentation . PLoS ONE , 2014 . 9 ( 7 ): e102107 25025374 DOI: 10.1371/journal.pone.0102107 http://doi.org/10.1371/journal.pone.0102107 . Robust radiomics feature quantification using semiautomatic volumetric segmentation C Parmar , RTH Leijenaar , P Grossmann , 等 . Radiomic feature clusters and prognostic signatures specific for lung and head & neck cancer . Sci Rep, 5:11044 , 2015 . DOI: 10.1038/srep11044 http://doi.org/10.1038/srep11044 . Radiomic feature clusters and prognostic signatures specific for lung and head & neck cancer C Parmar , P Grossmann , D Rietveld , 等 . Radiomic machine-learning classifiers for prognostic biomarkers of head and neck cancer . Front Oncol, 5:272 , 2015 . DOI: 10.3389/fonc.2015.00272 http://doi.org/10.3389/fonc.2015.00272 . Radiomic machine-learning classifiers for prognostic biomarkers of head and neck cancer SM Pizer , EP Amburn , JD Austin , 等 . Adaptive histogram equalization and its variations . Comput Vision Graph Image Proc , 1987 . 39 ( 3 ): 355 - 368 . DOI: 10.1016/S0734-189X(87)80186-X http://doi.org/10.1016/S0734-189X(87)80186-X . Adaptive histogram equalization and its variations U Raghavendra , UR Acharya , A Gudigar , 等 . Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions . Ultrasonics , 2017 . 77 110 - 120 . 28219805 DOI: 10.1016/j.ultras.2017.02.003 http://doi.org/10.1016/j.ultras.2017.02.003 . Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions MK Rahim , SE Kim , H So , 等 . Recent trends in PET image interpretations using volumetric and texture-based quantification methods in nuclear oncology . Nucl Med Mol Imaging , 2014 . 48 ( 1 ): 1 - 15 . 24900133 DOI: 10.1007/s13139-013-0260-2 http://doi.org/10.1007/s13139-013-0260-2 . Recent trends in PET image interpretations using volumetric and texture-based quantification methods in nuclear oncology E Sala , E Mema , Y Himoto , 等 . Unravelling tumour heterogeneity using next-generation imaging: radiomics, radiogenomics, and habitat imaging . Clin Radiol , 2017 . 72 ( 1 ): 3 - 10 . 27742105 DOI: 10.1016/j.crad.2016.09.013 http://doi.org/10.1016/j.crad.2016.09.013 . Unravelling tumour heterogeneity using next-generation imaging: radiomics, radiogenomics, and habitat imaging M Scrivener , EEC de Jong , JE van Timmeren , 等 . Radiomics applied to lung cancer: a review . Transl Cancer Res , 2016 . 5 ( 4 ): 398 - 409 . DOI: 10.21037/tcr.2016.06.18 http://doi.org/10.21037/tcr.2016.06.18 . Radiomics applied to lung cancer: a review E Segal , CB Sirlin , C Ooi , 等 . Decoding global gene expression programs in liver cancer by noninvasive imaging . Nat Biotechnol , 2007 . 25 675 - 680 . 17515910 DOI: 10.1038/nbt1306 http://doi.org/10.1038/nbt1306 . Decoding global gene expression programs in liver cancer by noninvasive imaging JD Song , D Dong , YQ Huang , 等 . Association between tumour heterogeneity and overall survival in patients with non-small cell lung cancer . 2016 . 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). Prague, Czech Republic . 1249 - 1252 . DOI: 10.1109/ISBI.2016.7493493 http://doi.org/10.1109/ISBI.2016.7493493 . Association between tumour heterogeneity and overall survival in patients with non-small cell lung cancer M Sonka , V Hlavac , R Boyle , 等 . Image processing, analysis, and machine vision . Cengage Learning , 2007 . Image processing, analysis, and machine vision R Stoyanova , M Takhar , Y Tschudi , 等 . Prostate cancer radiomics and the promise of radiogenomics . Transl Cancer Res , 2016 . 5 ( 4 ): 432 - 447 . 29188191 DOI: 10.21037/tcr.2016.06.20 http://doi.org/10.21037/tcr.2016.06.20 . Prostate cancer radiomics and the promise of radiogenomics K Szigeti , T Szabó , C Korom , 等 . Radiomics-based differentiation of lung disease models generated by polluted air based on X-ray computed tomography data . BMC Med Imaging, 16:14 , 2016 . DOI: 10.1186/s12880-016-0118-z http://doi.org/10.1186/s12880-016-0118-z . Radiomics-based differentiation of lung disease models generated by polluted air based on X-ray computed tomography data JA Thie . Understanding the standardized uptake value, its methods, and implications for usage . J Nucl Med , 2004 . 45 ( 9 ): 1431 - 1434 . 15347707 . Understanding the standardized uptake value, its methods, and implications for usage F Tixier , M Hatt , C Cheze Le Rest , 等 . Reproducibility of tumor uptake heterogeneity characterization through textural feature analysis in 18 F-FDG PET . J Nucl Med , 2012 . 53 ( 5 ): 693 - 700 . 22454484 DOI: 10.2967/jnumed.111.099127 http://doi.org/10.2967/jnumed.111.099127 . Reproducibility of tumor uptake heterogeneity characterization through textural feature analysis in 18F-FDG PET F Tixier , M Hatt , C Valla , 等 . Visual versus quantitative assessment of intratumor 18 F-FDG PET uptake heterogeneity: prognostic value in non-small cell lung cancer . J Nucl Med , 2015 . 55 ( 8 ): 1235 - 1241 . DOI: 10.2967/jnumed.113.133389 http://doi.org/10.2967/jnumed.113.133389 . Visual versus quantitative assessment of intratumor 18F-FDG PET uptake heterogeneity: prognostic value in non-small cell lung cancer T Upadhaya , Y Morvan , E Stindel , 等 . A framework for multimodal imaging-based prognostic model building: preliminary study on multimodal MRI in glioblastoma multiforme . IRBM , 2015 . 36 ( 6 ): 345 - 350 . DOI: 10.1016/j.irbm.2015.08.001 http://doi.org/10.1016/j.irbm.2015.08.001 . A framework for multimodal imaging-based prognostic model building: preliminary study on multimodal MRI in glioblastoma multiforme T Upadhaya , Y Morvan , E Stindel , 等 . Prognostic value of multimodal MRI tumor features in glioblastoma multiforme using textural features analysis . 2015 . 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), New York, NY, USA. IEEE . DOI: 10.1109/ISBI.2015.7163814 http://doi.org/10.1109/ISBI.2015.7163814 . Prognostic value of multimodal MRI tumor features in glioblastoma multiforme using textural features analysis X Vallières , CR Freeman , SR Skamene , 等 . A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities . Phys Med Biol , 2015 . 60 5471 - 5496 . 26119045 DOI: 10.1088/0031-9155/60/14/5471 http://doi.org/10.1088/0031-9155/60/14/5471 . A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities EL van den Burg , M van Hoof , AA Postma , 等 . An exploratory study to detect Ménière’s disease in conventional MRI scans using radiomics . Front Neurol, 7:190 , 2016 . DOI: 10.3389/fneur.2016.00190 http://doi.org/10.3389/fneur.2016.00190 . An exploratory study to detect Ménière’s disease in conventional MRI scans using radiomics PSN van Rossum , C Xu , DV Fried , 等 . The emerging field of radiomics in esophageal cancer: current evidence and future potential . Transl Cancer Res , 2016 . 5 ( 4 ): 410 - 423 . DOI: 10.21037/tcr.2016.06.19 http://doi.org/10.21037/tcr.2016.06.19 . The emerging field of radiomics in esophageal cancer: current evidence and future potential FHP van Velden , GM Kramer , V Frings , 等 . Repeatability of radiomic features in non-small-cell lung cancer [ 18 F]FDG-PET/CT studies: impact of reconstruction and delineation . Mol Imaging Biol , 2016 . 18 ( 5 ): 788 - 795 . 26920355 DOI: 10.1007/s11307-016-0940-2 http://doi.org/10.1007/s11307-016-0940-2 . Repeatability of radiomic features in non-small-cell lung cancer [18F]FDG-PET/CT studies: impact of reconstruction and delineation ER Velazquez , C Parmar , M Jermoumi , 等 . Volumetric CT-based segmentation of NSCLC using 3D-Slicer . Sci Rep, 3:3529 , 2013 . DOI: 10.1038/srep03529 http://doi.org/10.1038/srep03529 . Volumetric CT-based segmentation of NSCLC using 3D-Slicer ER Velazquez , R Meier , WD Dunn Jr , 等 . Fully automatic GBM segmentation in the TCGA-GBM dataset: prognosis and correlation with VASARI features . Sci Rep, 5:16822 , 2015 . DOI: 10.1038/srep16822 http://doi.org/10.1038/srep16822 . Fully automatic GBM segmentation in the TCGA-GBM dataset: prognosis and correlation with VASARI features H Wang , MB Schabath , Y Liu , 等 . Semiquantitative computed tomography characteristics for lung adenocarcinoma and their association with lung cancer survival . Clin Lung Cancer , 2015 . 16 ( 6 ): e141 - e163 . 26077095 DOI: 10.1016/j.cllc.2015.05.007 http://doi.org/10.1016/j.cllc.2015.05.007 . Semiquantitative computed tomography characteristics for lung adenocarcinoma and their association with lung cancer survival H Wang , ZS Xu , H Fujita , 等 . Towards felicitous decision making: an overview on challenges and trends of Big Data . Inform Sci , 2016 . 367-368 747 - 765 . DOI: 10.1016/j.ins.2016.07.007 http://doi.org/10.1016/j.ins.2016.07.007 . Towards felicitous decision making: an overview on challenges and trends of Big Data X Wang , BS Wong , TC Guan . Image enhancement for radiography inspection . 2005 . Proceedings Volume 5852, Third International Conference on Experimental Mechanics and Third Conference of the Asian Committee on Experimental Mechanics, Singapore . DOI: 10.1117/12.621707 http://doi.org/10.1117/12.621707 . Image enhancement for radiography inspection K Wanichthanarak , JF Fahrmann , D Grapov . Genomic, proteomic, and metabolomic data integration strategies . Biomark Insights , 2015 . 10 ( Suppl 4 ): 1 - 6 . 26396492 DOI: 10.4137/BMI.S29511 http://doi.org/10.4137/BMI.S29511 . Genomic, proteomic, and metabolomic data integration strategies Diagnostic imaging . WHO (World Health Organization) , 2017 . https://www.who.int/diagnostic_imaging/en [accessed on May 13, 2017] . . Diagnostic imaging AJ Wong , A Kanwar , AS Mohamed , 等 . Radiomics in head and neck cancer: from exploration to application . Transl Cancer Res , 2016 . 5 ( 4 ): 371 - 382 . DOI: 10.21037/tcr.2016.07.18 http://doi.org/10.21037/tcr.2016.07.18 . Radiomics in head and neck cancer: from exploration to application WM Wu , C Parmar , P Grossmann , 等 . Exploratory study to identify radiomics classifiers for lung cancer histology . Front Oncol, 6:71 , 2016 . DOI: 10.3389/fonc.2016.00071 http://doi.org/10.3389/fonc.2016.00071 . Exploratory study to identify radiomics classifiers for lung cancer histology S Yamamoto , RL Korn , R Oklu , 等 . ALK molecular phenotype in non-small cell lung cancer: CT radiogenomic characterization . Radiology , 2014 . 272 ( 2 ): 568 - 576 . 24885982 DOI: 10.1148/radiol.14140789 http://doi.org/10.1148/radiol.14140789 . ALK molecular phenotype in non-small cell lung cancer: CT radiogenomic characterization S Yamamoto , W Han , Y Kim , 等 . Breast cancer: radiogenomic biomarker reveals associations among dynamic contrast-enhanced MR imaging, long noncoding RNA, and metastasis . Radiology , 2015 . 275 ( 2 ): 384 - 392 . 25734557 DOI: 10.1148/radiol.15142698 http://doi.org/10.1148/radiol.15142698 . Breast cancer: radiogenomic biomarker reveals associations among dynamic contrast-enhanced MR imaging, long noncoding RNA, and metastasis J Yan , JL Chu-Shern , HY Loi , 等 . Impact of image reconstruction settings on texture features in 18 F-FDG PET . J Nucl Med , 2015 . 56 ( 11 ): 1667 - 1673 . 26229145 DOI: 10.2967/jnumed.115.156927 http://doi.org/10.2967/jnumed.115.156927 . Impact of image reconstruction settings on texture features in 18F-FDG PET JZ Yang , LF Zhang , XJ Fave , 等 . Uncertainty analysis of quantitative imaging features extracted from contrast-enhanced CT in lung tumors . Comput Med Imaging Graph , 2016 . 48 1 - 8 . 26745258 DOI: 10.1016/j.compmedimag.2015.12.001 http://doi.org/10.1016/j.compmedimag.2015.12.001 . Uncertainty analysis of quantitative imaging features extracted from contrast-enhanced CT in lung tumors SSF Yip , HJWL Aerts . Applications and limitations of radiomics . Phys Med Biol , 2016 . 61 ( 13 ): R150 - R166 . 27269645 DOI: 10.1088/0031-9155/61/13/R150 http://doi.org/10.1088/0031-9155/61/13/R150 . Applications and limitations of radiomics HJ Yoon , I Sohn , JH Cho , 等 . Decoding tumor phenotypes for ALK, ROS1, and RET fusions in lung adenocarcinoma using a radiomics approach . Medicine , 2015 . 94 ( 41 ): e1753 26469915 DOI: 10.1097/MD.0000000000001753 http://doi.org/10.1097/MD.0000000000001753 . Decoding tumor phenotypes for ALK, ROS1, and RET fusions in lung adenocarcinoma using a radiomics approach PP Ypsilantis , M Siddique , H Sohn , 等 . Predicting response to neoadjuvant chemotherapy with PET imaging using convolutional neural networks . PLoS ONE , 2015 . 10 ( 9 ): e0137036 26355298 DOI: 10.1371/journal.pone.0137036 http://doi.org/10.1371/journal.pone.0137036 . Predicting response to neoadjuvant chemotherapy with PET imaging using convolutional neural networks BS Zhao , YQ Tan , WY Tsai , 等 . Reproducibility of radiomics for deciphering tumor phenotype with imaging . Sci Rep, 6:23428 , 2016 . DOI: 10.1038/srep23428 http://doi.org/10.1038/srep23428 . Reproducibility of radiomics for deciphering tumor phenotype with imaging M Zhou , LO Hall , DB Goldgof . Exploring brain tumor heterogeneity for survival time prediction . 2014 . 2014 22nd International Conference on Pattern Recognition (ICPR), Stockholm, Sweden. IEEE . 580 - 585 . DOI: 10.1109/ICPR.2014.110 http://doi.org/10.1109/ICPR.2014.110 . Exploring brain tumor heterogeneity for survival time prediction PO Zinn , B Majadan , P Sathyan , 等 . Radiogenomic mapping of edema/cellular invasion MRI-phenotypes in glioblastoma multiforme . PLoS ONE , 2011 . 6 ( 10 ): e25451 21998659 DOI: 10.1371/journal.pone.0025451 http://doi.org/10.1371/journal.pone.0025451 . Radiogenomic mapping of edema/cellular invasion MRI-phenotypes in glioblastoma multiforme Compliance with ethics guidelines U. Rajendra ACHARYA, Yuki HAGIWARA, Vidya K. SUDARSHAN, Wai Yee CHAN, and Kwan Hoong NG declare that they have no conflict of interest. This article does not contain any studies with human or animal subjects performed by any of the authors. 10.1631/jzus.B1700260 2017-05-24 2017-08-16 2022-01-05 Copyright © Zhejiang University and Springer-Verlag GmbH Germany, part of Springer Nature 2018 2018 Journal of Zhejiang University-SCIENCE B (Biomedicine and Biotechnology) 01 19