基于多模态超声成像数据的慢性肝病肝纤维化、炎症和脂肪变性的智能分级诊断

doi:10.3969/j.issn.1006-7795.2023.06.004

首都医科大学学报 ›› 2023, Vol. 44 ›› Issue (6): 928-935.doi: 10.3969/j.issn.1006-7795.2023.06.004

基于多模态超声成像数据的慢性肝病肝纤维化、炎症和脂肪变性的智能分级诊断

魏星月^1,2#，王连双^3#，王媛媛⁴，高孟泽5，何琼^1,2，张瑶^3*，罗建文^1,2*

1.清华大学医学院生物医学工程系，北京 100084; 2.清华大学精准医学研究院，北京 100084; 3.首都医科大学附属北京地坛医院超声科，北京 100015; 4.北京理工大学光电学院北京市混合现实与新型显示工程技术研究中心，北京 100081; 5.清华大学机械工程学院精密仪器系，北京 100084

收稿日期:2023-09-05 出版日期:2023-12-21 发布日期:2023-12-20
通讯作者: 张瑶，罗建文 E-mail:zgzsy007@163.com，luo_jianwen@mail.tsinghua.edu.cn
基金资助:
北京市自然科学基金项目(M22018), 首都健康专项研究与发展项目（2022-2G-2177)，清华精准医学基金会基金项目（2022TS012), 清华大学精准医学科研计划项目（2022ZLA005), 清华大学春风基金项目(2021Z99CFY025)。

Intelligent grading diagnosis of liver fibrosis, inflammation, and steatosis in chronic liver disease based on multimodal ultrasound imaging data

Wei Xingyue^1,2#, Wang Lianshuang^3#, Wang Yuanyuan⁴, Gao Mengze⁵, He Qiong^1,2, Zhang Yao^3*, Luo Jianwen^1,2*

1.Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing 100084, China; 2.Institute of Precision Medicine, Tsinghua University, Beijing 100084, China; 3.Department of Ultrasound, Beijing Ditan Hospital, Capital Medical University, Beijing 100015, China; 4.Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Electronics, Beijing Institute of Technology, Beijing 100081, China;5.Department of Precision Instrument, Tsinghua University, Beijing 100084, China

Received:2023-09-05 Online:2023-12-21 Published:2023-12-20
Supported by:
This study was supported by Beijing Natural Science Foundation(M22018), the Capital Health Research and Development of Special（2022-2G-2177), Tsinghua Precision Medicine Foundation（2022TS012), Tsinghua University Initiative Scientific Research Program of Precision Medicine（2022ZLA005), Tsinghua University Spring Breeze Fund(2021Z99CFY025).

摘要/Abstract

摘要： 目的开发一套能同时诊断肝纤维化、炎症及脂肪变性的智能系统。方法基于慢性肝病（chronic liver disease, CLD)患者的多模态超声成像数据，包括超声B模式图像、剪切波弹性成像、瞬时弹性成像数据及其原始射频数据，使用定量超声方法和影像组学方法提取这些数据的多模态特征，以超声引导的肝穿刺活检结果为金标准，使用支持向量机以二分类的方式搭建智能分级诊断系统，同时实现肝纤维化、炎症和脂肪变性的智能辅助诊断。结果本方法对于肝纤维化分级的四个二分类任务：≥F1、≥F2、≥F3、≥F4，受试者工作特征（receiver operating characteristic， ROC)曲线下面积（area under the curve, AUC)达到了0.81、0.80、0.89、0.87；对于炎症分级≥A2、≥A3、≥A4，AUC为0.80、0.93、0.93；对于脂肪变性分级≥S1、≥S2，AUC为0.75、0.92。结论本研究提出了基于多模态超声成像数据的CLD肝纤维化、炎症和脂肪变性的智能分级诊断系统，该系统在3种CLD的智能评估中取得了较好的结果，有望推广至临床应用。

关键词: 慢性肝病, 肝纤维化, 炎症, 脂肪变性, 多模态超声, 支持向量机

Abstract: Objective To develop a non-invasive, accurate, convenient, and widely applicable intelligent diagnostic system to diagnose simultaneously liver fibrosis, inflammation, and steatosis of chronic liver disease (CLD). Methods This study is based on multimodal ultrasound imaging data from CLD patients, including two-dimensional B-mode ultrasound images, two-dimensional shear wave elastography, transient elastography data, and the corresponding original radio-frequency data. Quantitative ultrasound methods were used to extract multimodal features from these multimodal data, and the results of ultrasound-guided liver biopsy were used as the gold standard. Support vector machine (SVM) was used to construct an intelligent grading diagnosis system for CLD in a binary-classification manner. Results The proposed method achieves high the receiver operating characteristic (ROC) area under the curve (AUC) of 0.81, 0.80, 0.89, 0.87 for the classification of fibrosis grade ≥F1, ≥F2, ≥F3 ≥F4, and 0.80, 0.93, 0.93 for inflammation ≥A2, ≥A3, ≥A4, and 0.75, 0.92 for steatosis ≥S1, ≥S2. Conclusion The results indicated that the proposed method showed potential expected to be promoted to clinical applications.

Key words: chronic liver disease, liver fibrosis, inflammation, steatosis, multimodal quantitative ultrasound, support vector machine

中图分类号:

R445

魏星月, 王连双, 王媛媛, 高孟泽, 何琼, 张瑶, 罗建文. 基于多模态超声成像数据的慢性肝病肝纤维化、炎症和脂肪变性的智能分级诊断[J]. 首都医科大学学报, 2023, 44(6): 928-935.

Wei Xingyue, Wang Lianshuang, Wang Yuanyuan, Gao Mengze, He Qiong, Zhang Yao, Luo Jianwen. Intelligent grading diagnosis of liver fibrosis, inflammation, and steatosis in chronic liver disease based on multimodal ultrasound imaging data[J]. Journal of Capital Medical University, 2023, 44(6): 928-935.

参考文献

［1］Wang F S, Fan J G, Zhang Z, et al. The global burden of liver disease: the major impact of China［J］. Hepatology, 2014, 60(6): 2099－2108.
［2］何迪, 陈鹏, 刘锋, 等. 肝纤维化病因与机制研究进展［J］. 昆明医科大学学报, 2022, 43(11): 165－171.
［3］王宇明, 于乐成. 肝脏炎症及其防治专家共识［J］. 中国实用内科杂志, 2014, 34(2): 152－162.
［4］范建高, 庄辉, 黄薏. 全球首部 “科普版”《脂肪肝防治指南》10大关键词(一)［J］. 肝博士, 2015(2): 13－19.
［5］Regev A, Berho M, Jeffers L J, et al. Sampling error and intraobserver variation in liver biopsy in patients with chronic HCV infection［J］. Am J Gastroenterol, 2002, 97(10): 2614－2618.
［6］Fujita K, Kuroda N, Morishita A, et al. Fibrosis staging using direct serum biomarkers is influenced by hepatitis activity grading in hepatitis C virus infection［J］. J Clin Med, 2018, 7(9): 267.
［7］Vieira Barbosa J, Milligan S, Frick A, et al. Fibrosis-4 index can independently predict major adverse cardiovascular events in nonalcoholic fatty liver disease［J］. Am J Gastroenterol, 2022, 117(3): 453－461.
［8］Sigrist R M S, Liau J, EL Kaffas A, et al. Ultrasound elastography: review of techniques and clinical applications［J］. Theranostics, 2017, 7(5): 1303－1329.
［9］Garra B S, Insana M F, Shawker T H, et al. Quantitative ultrasonic detection and classification of diffuse liver disease. Comparison with human observer performance［J］. Invest Radiol, 1989, 24(3): 196－203.
［10］Toyoda H, Kumada T, Kamiyama N, et al. B-mode ultrasound with algorithm based on statistical analysis of signals: evaluation of liver fibrosis in patients with chronic hepatitis C［J］. AJR Am J Roentgenol, 2009, 193(4): 1037－1043.
［11］Liao Y Y, Yang K C, Lee M J, et al. Multifeature analysis of an ultrasound quantitative diagnostic index for classifying nonalcoholic fatty liver disease［J］. Sci Rep, 2016, 6: 35083.
［12］Ho M C, Lin J J, Shu Y C, et al. Using ultrasound Nakagami imaging to assess liver fibrosis in rats［J］. Ultrasonics, 2012, 52(2): 215－222.
［13］Destrempes F, Gesnik M, Chayer B, et al. Quantitative ultrasound, elastography, and machine learning for assessment of steatosis, inflammation, and fibrosis in chronic liver disease［J］. PLoS One, 2022, 17(1): e0262291.
［14］Wen H Y, Zheng W, Li M, et al. Multiparametric quantitative US examination of liver fibrosis: a feature-engineering and machine-learning based analysis［J］. IEEE J Biomed Health Inform, 2022, 26(2): 715－726.
［15］尤红, 王福生, 李太生, 等. 慢性乙型肝炎防治指南 (2022年版)［J］. 传染病信息, 2023, 36(1): 1－17.
［16］Miranda D R, Nap R, de Rijk A, et al. Nursing activities score［J］. Crit Care Med, 2003, 31(2): 374－382.
［17］Xiao Y, Zeng J, Niu L L, et al. Computer-aided diagnosis based on quantitative elastographic features with supersonic shear wave imaging［J］. Ultrasound Med Biol, 2014, 40(2): 275－286.
［18］Li Y S, Liu Y, Zhang M K, et al. Radiomics with attribute bagging for breast tumor classification using multimodal ultrasound images［J］. J Ultrasound Med, 2020, 39(2): 361－371.
［19］Hanley J A, McNeil B J. The meaning and use of the area under a receiver operating characteristic (ROC) curve［J］. Radiology, 1982, 143(1): 29－36.

[1]	宋海曼, 何文, 康睿君, 王立淑, 于腾飞, 张巍. 卵巢－附件影像报告和数据系统在卵巢肿瘤良恶性鉴别诊断中的应用价值[J]. 首都医科大学学报, 2023, 44(6): 948-952.
[2]	于腾飞, 殷露, 田道然, 宋海曼, 尹子毅, 张巍, 何文. 超微血流成像和彩色多谱勒血流显像在乳腺BI-RADS 4类微小结节中的临床应用[J]. 首都医科大学学报, 2023, 44(6): 921-927.
[3]	庄佳绵, 曾宇然, 陈绍琦. 高帧率剪切波评价血液透析患者冈上肌腱的力学性能[J]. 首都医科大学学报, 2023, 44(6): 936-940.
[4]	贾筱夏, 常莹, 侯文颖, 符颖, 张会单, 杨敬春. 超声引导下射频消融治疗甲状腺微小乳头状癌术后吸收率的影响因素分析[J]. 首都医科大学学报, 2023, 44(6): 941-947.
[5]	宋倩, 周倩, 孙宏, 李硕, 梅雪, 郭瑞君, 葛辉玉. Lindegaard指数预测早期脓毒症相关性脑病的临床价值[J]. 首都医科大学学报, 2023, 44(6): 959-965.
[6]	孙哲, 马姣姣, 张波. 胸膜超声在呼吸系统疾病中的应用现状及展望[J]. 首都医科大学学报, 2023, 44(6): 966-972.
[7]	宋海曼, 何文, 康睿君, 王立淑, 于腾飞, 张巍. 卵巢－附件影像报告和数据系统在卵巢肿瘤良恶性鉴别诊断中的应用价值[J]. 首都医科大学学报, 0, (): 948-952.
[8]	张姝, 王凯, 杨子皓, 乔真, 李晓桐, 袁磊磊, 艾林. ¹¹C-MET PET/CT筛查幕上较低级别胶质瘤IDH和1p/19q分子分型的应用价值[J]. 首都医科大学学报, 2022, 43(6): 826-833.
[9]	耿义强, 刘家金, 吴世娜, 孙树伟, 赵东, 宋敬斌, 孙亚兵, 王瑞民. NEMA NU 2-2018标准在PET/CT系统性能测试中的作用评价[J]. 首都医科大学学报, 2022, 43(6): 840-844.
[10]	徐洋, 王凯, 陈嫱, 艾林. 核医学分子影像在胶质瘤诊疗中的研究进展[J]. 首都医科大学学报, 2022, 43(6): 880-885.
[11]	黄黎香, 王绍舟, 曹宸, 夏爽. 豆纹动脉对基底节区脑组织定量灌注的影响及预后预测效果评价[J]. 首都医科大学学报, 2022, 43(1): 53-60.
[12]	王莉, 施昭, 孔祥, 杨柳, 刘亚, 罗松, 张龙江. 大脑前动脉A1段发育不良和分叉角度与前交通动脉瘤形成的相关性[J]. 首都医科大学学报, 2022, 43(1): 61-66.
[13]	张慧博, 杨晓旭, 刘欣圆, 顾华, 王双坤, 杨旗. 磁共振影像对脑静脉窦血栓形成的诊断价值研究[J]. 首都医科大学学报, 2022, 43(1): 67-73.
[14]	孙鹏慧, 李莹莹, 刘鑫, 贾学佳, 贾秀琴, 杨旗. 卒中相关性肺炎患者神经功能恶化的影像指标及其预测价值分析[J]. 首都医科大学学报, 2022, 43(1): 74-81.
[15]	康丽, 李硕, 熊颖, 郭瑞君. 托拉塞米联合葡萄糖快速利尿后超声技术诊断在役飞行员肾微小结石的临床价值[J]. 首都医科大学学报, 2021, 42(6): 1076-1080.

基于多模态超声成像数据的慢性肝病肝纤维化、炎症和脂肪变性的智能分级诊断

Intelligent grading diagnosis of liver fibrosis, inflammation, and steatosis in chronic liver disease based on multimodal ultrasound imaging data

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价