深度学习剪切波弹性成像的Radiomics显着提高了评估慢性乙型

StephenW

PDF
Hepatology
Original article
Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study

    Kun Wang1,2, Xue Lu1, Hui Zhou2,3, Yongyan Gao4, Jian Zheng1,5, Minghui Tong6, Changjun Wu7, Changzhu Liu8, Liping Huang9, Tian’an Jiang10, Fankun Meng11, Yongping Lu12, Hong Ai13, Xiao-Yan Xie14, Li-ping Yin15, Ping Liang3, Jie Tian2,3, Rongqin Zheng1

Author affiliations

    Guangdong Key Laboratory of Liver Disease Research, Department of Medical Ultrasound, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China
    CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
    Department of the Artificial Intelligence Technology, University of Chinese Academy of Sciences, Beijing, China
    Department of Interventional Ultrasound, Chinese PLA General Hospital, Beijing, China
    Department of Medical Ultrasonics, Third Hospital of Longgang, Shenzhen, China
    Functional Examination Department of Children’s Hospital, Lanzhou University Second Hospital, Lanzhou, China
    Ultrasound Department, The First Affiliated Hospital of Harbin Medical University, Harbin, China
    Ultrasound Department, Guangzhou Eighth People’s Hospital, Guangzhou, China
    Department of Ultrasound, Shengjing Hospital of China Medical University, Shenyang, China
    Department of Ultrasonography, The First Affiliated Hospital, Medical College of Zhejiang University, Hangzhou, China
    Function Diagnosis Center, Beijing Youan Hospital, Affiliated to Capital Medical University, Beijing, China
    Ultrasound Department, The Second People’s Hospital of Yunnan Province, Kunming, China
    Ultrasound Department, The First Affiliated Hospital of Xi’an Jiaotong University, Xi’an, China
    Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China
    Department of Ultrasound, Jiangsu Province Hospital of TCM, Affiliated Hospital of Nanjing University of TCM, Nanjing, China

    Correspondence to Proffesor Ping Liang, Department of Interventional Ultrasound, Chinese PLA General Hospital, Beijing 100853, China; [email protected], Proffessor Jie Tian, CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; [email protected] and Proffessor Rongqin Zheng, Guangdong Key Laboratory of Liver Disease Research, Department of Medical Ultrasound, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, China; [email protected]

Abstract

Objective We aimed to evaluate the performance of the newly developed deep learning Radiomics of elastography (DLRE) for assessing liver fibrosis stages. DLRE adopts the radiomic strategy for quantitative analysis of the heterogeneity in two-dimensional shear wave elastography (2D-SWE) images.

Design A prospective multicentre study was conducted to assess its accuracy in patients with chronic hepatitis B, in comparison with 2D-SWE, aspartate transaminase-to-platelet ratio index and fibrosis index based on four factors, by using liver biopsy as the reference standard. Its accuracy and robustness were also investigated by applying different number of acquisitions and different training cohorts, respectively. Data of 654 potentially eligible patients were prospectively enrolled from 12 hospitals, and finally 398 patients with 1990 images were included. Analysis of receiver operating characteristic (ROC) curves was performed to calculate the optimal area under the ROC curve (AUC) for cirrhosis (F4), advanced fibrosis (≥F3) and significance fibrosis (≥F2).

Results AUCs of DLRE were 0.97 for F4 (95% CI 0.94 to 0.99), 0.98 for ≥F3 (95% CI 0.96 to 1.00) and 0.85 (95% CI 0.81 to 0.89) for ≥F2, which were significantly better than other methods except 2D-SWE in ≥F2. Its diagnostic accuracy improved as more images (especially ≥3 images) were acquired from each individual. No significant variation of the performance was found if different training cohorts were applied.

Conclusion DLRE shows the best overall performance in predicting liver fibrosis stages compared with 2D-SWE and biomarkers. It is valuable and practical for the non-invasive accurate diagnosis of liver fibrosis stages in HBV-infected patients.

Trial registration number NCT02313649; Post-results.

This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/

http://dx.doi.org/10.1136/gutjnl-2018-316204

StephenW

PDF
肝病
来源文章
深度学习剪切波弹性成像的Radiomics显着提高了评估慢性乙型肝炎肝纤维化的诊断性能：一项前瞻性多中心研究

    王坤1,2，薛璐1，周慧2,3，高永炎4，简正5，明慧彤6，吴长军7，刘长柱8，黄丽萍9，田安江10，范坤梦11，陆永平12，洪爱13，萧炎谢14，李丽萍15，平良3，解天2,3，郑荣勤1

作者隶属关系

    中山大学附属第三医院广东省肝病研究重点实验室，医学超声科，广州
    中国科学院自动化研究所，中国科学院分子影像重点实验室，北京
    中国科学院大学人工智能技术系，北京，中国
    中国人民解放军总医院介入超声科，北京，中国
    深圳市龙岗区第三医院医学超声科
    兰州大学第二医院儿童医院功能检查科，兰州
    哈尔滨医科大学附属第一医院超声科，哈尔滨
    广州市第八人民医院超声科，广州
    中国医科大学附属盛京医院超声科，沉阳
    浙江大学医学院附属第一医院超声科，杭州
    首都医科大学附属北京佑安医院功能诊断中心，北京
    云南省第二人民医院超声科，昆明
    西安交通大学第一附属医院超声科，西安
    中山大学附属第一医院诊断与介入超声研究所医学超声科，广州
    江苏省中医院超声科，南京中医药大学附属医院，南京

    中国人民解放军总医院介入超声科Proffesor Ping Liang，北京100853; [email protected]，中国科学院自动化研究所，中国科学院分子影像重点实验室，田杰，北京100190; [email protected]和教授郑荣勤，中山大学附属第三医院医学超声科广东省肝病研究重点实验室，广州510630; [email protected]

抽象

目的我们旨在评估新开发的弹性成像深度学（DLRE）在评估肝纤维化阶段的表现。 DLRE采用放射性原理策略定量分析二维剪切波弹性成像（2D-SWE）图像的异质性。

设计通过肝活检作为参考标准，进行前瞻性多中心研究以评估其在慢性乙型肝炎患者中的准确性，与基于四个因素的2D-SWE，天冬氨酸转氨酶与血小板比率指数和纤维化指数进行比较。通过分别应用不同数量的采集和不同的训练群组，还研究了其准确性和稳健性。来自12家医院的654名潜在合格患者的数据被前瞻性地纳入，最终包括了398名1990年图像的患者。对接受者操作特征（ROC）曲线进行分析以计算肝硬化（F4），晚期纤维化（≥F3）和显着纤维化（≥F2）的ROC曲线下的最佳面积（AUC）。

结果FRE的DLU为0.97（95％CI为0.94~0.99），≥F3为0.98（95％CI为0.96~1.00），≥F2为0.85（95％CI为0.81~0.89），明显优于其他方法除了≥F2的2D-SWE。随着从每个人获得更多图像（特别是≥3个图像），其诊断准确性得到改善。如果应用不同的训练队列，则没有发现性能的显着变化。

结论与2D-SWE和生物标志物相比，DLRE在预测肝纤维化阶段方面表现出最佳的整体表现。对于HBV感染患者的肝纤维化阶段的非侵入性准确诊断是有价值和实用的。

试用注册号NCT02313649;后的结果。

这是根据知识共享署名非商业（CC BY-NC 4.0）许可分发的开放获取文章，该许可允许其他人以非商业方式分发，重新混合，改编，构建此作品，并将其衍生作品许可给不同条款，条件是原始作品被正确引用且使用是非商业性的。请参阅：http：//creativecommons.org/licenses/by-nc/4.0/

http://dx.doi.org/10.1136/gutjnl-2018-316204

StephenW

https://gut.bmj.com/content/gutjnl/68/4/729.full.pdf