基于影像组学的深度学习评估肌少症对肝癌切除和移植患者预后的影响

刘治坤; 吴逸超; Abid Ali KHAN; 陆伦; 王建国; 陈峻; 贾宁阳; 郑树森; 徐骁

doi:10.1631/jzus.B2300363

Your Location：

Home >

Browse articles >

基于影像组学的深度学习评估肌少症对肝癌切除和移植患者预后的影响

Scan for full text

文章被引用时，请邮件提醒。

Submit

Correspondence | Updated：2023-12-27

基于影像组学的深度学习评估肌少症对肝癌切除和移植患者预后的影响
Deep learning-based radiomics allows for a more accurate assessment of sarcopenia as a prognostic factor in hepatocellular carcinoma
浙江大学学报（英文版）（B辑：生物医学和生物技术） 2024年25卷第1期页码：83-90
Affiliations：

1.Key Laboratory of Integrated Oncology and Intelligent Medicine of Zhejiang Province, Department of Hepatobiliary and Pancreatic Surgery, Affiliated Hangzhou First People’s Hospital, Zhejiang University School of Medicine, Hangzhou 310006, China
2.Zhejiang University School of Medicine, Hangzhou 310058, China
3.Department of Radiology, Easter Hepatobiliary Surgery Hospital, Naval Medical University, Shanghai 200438, China
4.Department of Hepatobiliary and Pancreatic Surgery, the First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China
5.NHC Key Laboratory of Combined Multi-organ Transplantation, Hangzhou 310003, China
6.Department of Hepatobiliary and Pancreatic Surgery, Shulan (Hangzhou) Hospital, Hangzhou 310022, China
Funds：

the Key Program of Provincial Natural Foundation of Zhejiang Province(LZ22H180003);the National Natural Science Foundation of China(92159202;81802889);the Key Research & Development Program of Zhejiang Province(2022C03108);We are grateful to Wiley Editing Services for assisting in language editing assistance(Order TNIPJ_1)
DOI：10.1631/jzus.B2300363
中图分类号：
CSTR：

刘治坤,吴逸超,Abid Ali KHAN等.基于影像组学的深度学习评估肌少症对肝癌切除和移植患者预后的影响[J].浙江大学学报（英文版）（B辑：生物医学和生物技术）,2024,25(01):83-90.

Zhikun LIU, Yichao WU, Abid Ali KHAN, et al. Deep learning-based radiomics allows for a more accurate assessment of sarcopenia as a prognostic factor in hepatocellular carcinoma[J]. Journal of Zhejiang University-SCIENCE B (Biomedicine & Biotechnology), 2024,25(1):83-90.
刘治坤,吴逸超,Abid Ali KHAN等.基于影像组学的深度学习评估肌少症对肝癌切除和移植患者预后的影响[J].浙江大学学报（英文版）（B辑：生物医学和生物技术）,2024,25(01):83-90. DOI： 10.1631/jzus.B2300363.

Zhikun LIU, Yichao WU, Abid Ali KHAN, et al. Deep learning-based radiomics allows for a more accurate assessment of sarcopenia as a prognostic factor in hepatocellular carcinoma[J]. Journal of Zhejiang University-SCIENCE B (Biomedicine & Biotechnology), 2024,25(1):83-90. DOI： 10.1631/jzus.B2300363.

摘要

肌少症是指因持续骨骼肌含量流失、强度和功能下降引起的综合征，且与包括肝细胞癌（HCC）在内的肿瘤患者预后密切相关。目前该病的检测手段局限且无统一标准。本文旨在利用基于影像组学的深度学习（DL）技术评估肌少症，用于肝癌患者行肝脏部分切除术或肝移植术的预后预测。本研究回顾性纳入浙大一院肝癌手术切除492例（训练集+内部验证集）与肝癌肝移植173例患者（外部LT验证集），东方肝胆医院肝癌切除患者161例（外部验证集），并收集患者术前一个月内的腹部计算机断层扫描（CT）平扫期影像与临床资料；单中心肝切除术组入组患者按7：3随机分为训练集和内部验证集（训练集345例，验证集147例），肝移植组及第二中心肝癌切除组作为外部验证集，经训练集建立预测模型，并利用内部和外部验证集验证预测模型的预测性能；对训练集患者CT图像中第3腰椎骨（L3）层面的骨骼肌（SM）及腰大肌（PM）轮廓进行人工勾画；抽提SM与PM影像组学特征，随后利用自编码器（AutoEncoder）压缩特征，TFDeepSurv生存分析网络构建DL预后预测模型，预测HCC术后无瘤生存率（RFS）与总体生存时间（OS）；最后计算时间依赖性受试者工作特征曲线（ROC）的曲线下面积（AUC）和一致性指数（C-index），采用应用净重新分类改善指数（NRI）和临床决策曲线（DCA）评价模型预测性能。最终从勾画的CT图像L3层面的SM及PM中采集相应肌肉中1343个影像组学特征。经AutoEncoder将此高阶影像组学特征降维至100个特征。运用TFDeepSurv生存分析网络完成DL预测模型的构建，将HCC患者根据预后的差异分为高危组和低危组，高危组HCC患者行肝部分切除手术后预后显著低于低危组患者。此外，通过Kaplan-Meier生存曲线分析等方法证实DL模型在内部及外部验证集、外部LT验证集中均可对肝癌患者术后的预后进行准确预测，一致性指数分别达0.775和0.613。NRI和DCA同样显示DL模型具有较高的预测性能。本研究创新性地提出了基于影像组学的DL技术构建的预后预测模型；该模型可在术前对肝癌手术切除和肝移植术后的生存风险进行个体化预测，从而实现对肝癌患者OS的早期预判，有助于制定合理的临床决策和指导临床实践。

Abstract

关键词

影像组学深度学习肌少症肝细胞肝癌肝部分切除术肝移植

Keywords

references

Bi WL, Hosny A, Schabath MB, et al., 2019. Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin, 69(2):127-157. https://doi.org/10.3322/caac.21552https://doi.org/10.3322/caac.21552

Carey EJ, Lai JC, Wang CW, et al., 2017. A multicenter study to define sarcopenia in patients with end-stage liver disease. Liver Transpl, 23(5):625-633. https://doi.org/10.1002/lt.24750https://doi.org/10.1002/lt.24750

Carey EJ, Lai JC, Sonnenday C, et al., 2019. A North American expert opinion statement on sarcopenia in liver transplantation. Hepatology, 70(5):1816-1829. https://doi.org/10.1002/hep.30828https://doi.org/10.1002/hep.30828

Chen XD, Chen WJ, Huang ZX, et al., 2022. Establish a new diagnosis of sarcopenia based on extracted radiomic features to predict prognosis of patients with gastric cancer. Front Nutr, 9:850929. https://doi.org/10.3389/fnut.2022.850929https://doi.org/10.3389/fnut.2022.850929

Cruz-Jentoft AJ, Sayer AA, 2019. Sarcopenia. Lancet, 393(10191):2636-2646. https://doi.org/10.1016/s0140-6736(19)31138-9https://doi.org/10.1016/s0140-6736(19)31138-9

Cruz-Jentoft AJ, Bahat G, Bauer J, et al., 2019. Sarcopenia: revised European consensus on definition and diagnosis. Age Ageing, 48(4):601. https://doi.org/10.1093/ageing/afz046https://doi.org/10.1093/ageing/afz046

Esser H, Resch T, Pamminger M, et al., 2019. Preoperative assessment of muscle mass using computerized tomography scans to predict outcomes following orthotopic liver transplantation. Transplantation, 103(12):2506-2514. https://doi.org/10.1097/tp.0000000000002759https://doi.org/10.1097/tp.0000000000002759

Forner A, Reig M, Bruix J, 2018. Hepatocellular carcinoma. Lancet, 391(10127):1301-1314. https://doi.org/10.1016/s0140-6736(18)30010-2https://doi.org/10.1016/s0140-6736(18)30010-2

Fujiwara N, Nakagawa H, Kudo Y, et al., 2015. Sarcopenia, intramuscular fat deposition, and visceral adiposity independently predict the outcomes of hepatocellular carcinoma. J Hepatol, 63(1):131-140. https://doi.org/10.1016/j.jhep.2015.02.031https://doi.org/10.1016/j.jhep.2015.02.031

Golse N, Bucur PO, Ciacio O, et al., 2017. A new definition of sarcopenia in patients with cirrhosis undergoing liver transplantation. Liver Transpl, 23(2):143-154. https://doi.org/10.1002/lt.24671https://doi.org/10.1002/lt.24671

Hamaguchi Y, Kaido T, Okumura S, et al., 2016. Proposal for new diagnostic criteria for low skeletal muscle mass based on computed tomography imaging in Asian adults. Nutrition, 32(11-12):1200-1205. https://doi.org/10.1016/j.nut.2016.04.003https://doi.org/10.1016/j.nut.2016.04.003

He ZQ, She XM, Liu ZY, et al., 2023. Advances in post-operative prognostic models for hepatocellular carcinoma. J Zhejiang Univ-Sci B (Biomed & Biotechnol), 24(3):191-206. https://doi.org/10.1631/jzus.B2200067https://doi.org/10.1631/jzus.B2200067

Jin JY, Yao Z, Zhang T, et al., 2021. Deep learning radiomics model accurately predicts hepatocellular carcinoma occurrence in chronic hepatitis b patients: a five-year follow-up. Am J Cancer Res, 11(2):576-589.

Kim YJ, 2021. Machine learning models for sarcopenia identification based on radiomic features of muscles in computed tomography. Int J Environ Res Public Health, 18(16):8710. https://doi.org/10.3390/ijerph18168710https://doi.org/10.3390/ijerph18168710

van Vugt JLA, Levolger S, de Bruin RWF, et al., 2016. Systematic review and meta-analysis of the impact of computed tomography-assessed skeletal muscle mass on outcome in patients awaiting or undergoing liver transplantation. Am J Transpl, 16(8):2277-2292. https://doi.org/10.1111/ajt.13732https://doi.org/10.1111/ajt.13732

Voron T, Tselikas L, Pietrasz D, et al., 2015. Sarcopenia impacts on short- and long-term results of hepatectomy for hepatocellular carcinoma. Ann Surg, 261(6):1173-1183. https://doi.org/10.1097/sla.0000000000000743https://doi.org/10.1097/sla.0000000000000743

Yoo T, Lo WD, Evans DC, 2017. Computed tomography measured psoas density predicts outcomes in trauma. Surgery, 162(2):377-384. https://doi.org/10.1016/j.surg.2017.03.014https://doi.org/10.1016/j.surg.2017.03.014

浏览量

Downloads

CSCD

工具集

关联资源

暂无数据