ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Prediction of microvascular invasion in hepatocellular carcinoma with expert-inspiration and skeleton sharing deep learning

Xiao, Han; Guo, Yuchen; Zhou, Qian; Chen, Qiaofeng; Du, Qiang; Chen, Shuling; Fu, Shunjun; Lin, Jie; Li, Dexuan; Song, Xinming; Peng, Sui; Huang, Yuhua*; Shen, Jingxian*; Kuang, Ming*南方医科大学; 清华大学; 中山大学; 1
Liver International2022-6DOI: 10.1111/liv.15254
7被引23阅读
引用收藏
分享

摘要

Background and Aims Radiological prediction of microvascular invasion (MVI) of hepatocellular carcinoma (HCC) is essential but few models were clinically implemented because of limited interpretability and generalizability. Methods Based on 2096 patients in three independent HCC cohorts, we established and validated an MVI predicting model. First, we used data from the primary cohort to train a 3D-ResNet network for MVI prediction and then optimised the model with "expert-inspired training" for model construction. Second, we implemented the model to the other two cohorts using three implementation strategies, the original model implementation, data sharing model implementation and skeleton sharing model implementation, the latter two of which used part of the cohorts' data for fine-tuning. The areas under the receiver operating characteristic curve (AUCs) were calculated to compare the performances of different models. Results For the MVI predicting model, the AUC of the expert-inspired model was 0.83 (95% CI: 0.77-0.88) compared to 0.54 (95% CI: 0.46-0.62) of model before expert-inspiring. Taking this model as an original model, AUC on the second cohort was 0.76 (95% CI: 0.67-0.84). The AUC was improved to 0.83 (95% CI: 0.77-0.90) with the data-sharing model, and further improved to 0.85 (95% CI: 0.79-0.92) with the skeleton sharing model. The trend that the skeleton sharing model had an advantage in performance was similar in the third cohort. Conclusions We established an expert-inspired model with better predictive performance and interpretability than the traditional constructed model. Skeleton sharing process is superior to data sharing and direct model implementation in model implementation.

学科与关键词

关键词
carcinomacomputer-assisteddeep learninghepatocellularimage processing
相关
加载中…
  • Deep learning for evaluation of microvascular invasion in hepatocellular carcinoma from tumor areas of histology images
    Chen, Qiaofeng; Xiao, Han; Gu, Yunquan; Weng, Zongpeng; Wei, Lihong; Li, Bin; Liao, Bing; Li, Jiali; Lin, Jie; Hei, Mengying; Peng, Sui; Wang, Wei*; Kuang, Ming*; Chen, Shuling*Hepatology International, 2022, 16(3): 590-602.被引 7
  • Deep convolutional neural network for preoperative prediction of microvascular invasion and clinical outcomes in patients with HCCs
    Li, Xinming; Qi, Zhendong; Du, Haiyan; Geng, Zhijun; Li, Zhipeng; Qin, Shuping; Zhang, Xuhui; Liang, Jianye; Zhang, Xiao; Liang, Wen; Yang, Wei; Xie, Chuanmiao*; Quan, Xianyue*European Radiology, 2022, 32(2): 771-782.被引 12
  • Deep-learning-based analysis of preoperative MRI predicts microvascular invasion and outcome in hepatocellular carcinoma
    Sun, Bao-Ye; Gu, Pei-Yi; Guan, Ruo-Yu; Zhou, Cheng; Lu, Jian-Wei; Yang, Zhang-Fu; Pan, Chao; Zhou, Pei-Yun; Zhu, Ya-Ping; Li, Jia-Rui; Wang, Zhu-Tao; Gao, Shan-Shan; Gan, Wei*; Yi, Yong*; Luo, Ye*; Qiu, Shuang-Jian*World Journal of Surgical Oncology, 2022, 20(1): 189.被引 13
查看全部 →

发表信息

论文状态
公开发表
期刊
Liver International
发表日期
2022-06
卷期
第 42 卷, 第 6 期
页码
1423-1431
DOI
10.1111/liv.15254
语言
ENGLISH
期刊等级
2区
成果收录
SCIE
资助标注
National Key Research and Development Program of China [2020AAA0109504]; National Science Fund for Distinguished Young Scholars [81825013]; Guangdong Basic and Applied Basic Research Foundation [2019A1515111168]; Natural Science Foundation of Guangdong Province [2021A1515010450]

作者

  • X

    Xiao, Han (第一作者)

    1 · sun yat sen univ

  • G

    Guo, Yuchen

    tsinghua univ

查看全部 14 位作者收起作者
  • Z

    Zhou, Qian

    1 · sun yat sen univ

  • C

    Chen, Qiaofeng

    1 · sun yat sen univ

  • D

    Du, Qiang

  • C

    Chen, Shuling

    1 · sun yat sen univ

  • F

    Fu, Shunjun

    southern med univ

  • L

    Lin, Jie

    southern med univ

  • L

    Li, Dexuan

  • S

    Song, Xinming

    1 · sun yat sen univ

  • P

    Peng, Sui

    1 · sun yat sen univ

  • H

    Huang, Yuhua (通讯)

    sun yat sen univ

  • S

    Shen, Jingxian (通讯)

    sun yat sen univ

  • K

    Kuang, Ming (通讯)

    1 · 2 · sun yat sen univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417