Predicting prognosis of patients with hepatitis B virus-related acute-on-chronic liver failure from longitudinal ultrasound images using a multi-task deep learning approach.

Journal: Annals of medicine
Published Date:

Abstract

BACKGROUND: Individualized risk stratification in hepatitis B virus-related acute-on-chronic liver failure (HBV-ACLF) remains challenging. This study aimed to develop and validate a multi-task deep learning model using longitudinal liver ultrasound images for prognosis prediction.

Authors

  • Xingzhi Huang
    Department of Ultrasonography, The First Affiliated Hospital of Nanchang University, Nanchang, China.
  • Songsong Yuan
    Department of Infectious Disease, The First Affiliated Hospital of Nanchang University, Nanchang, China.
  • Aiyun Zhou
    Department of Ultrasonography, The First Affiliated Hospital of Nanchang University, Nanchang, China.
  • Xinchun Yuan
    Department of Ultrasound, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China.
  • Yaohui Li
    Department of Ultrasonography, The First Affiliated Hospital of Nanchang University, Nanchang, China.
  • Yufan Kuang
    Department of Ultrasound, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China.
  • Pan Xu
    Institute of Analytical Science, Shaanxi Provincial Key Laboratory of Electroanalytical Chemistry, Northwest University, Xi'an, Shaanxi 710069, China.