Early prediction of adverse outcomes in liver cirrhosis using a CT-based multimodal deep learning model.

Gastroenterology Transplantation Product Alert Pain Management Primary Care
Journal: Abdominal radiology (New York)
Published Date: Jun 27, 2025

Abstract

PURPOSE: Early-stage cirrhosis frequently presents without symptoms, making timely identification of high-risk patients challenging. We aimed to develop a deep learning-based triple-modal fusion liver cirrhosis network (TMF-LCNet) for the prediction of adverse outcomes, offering a promising tool to enhance early risk assessment and improve clinical management strategies.

Authors

  • Nanai Xie
    Department of Radiology, The Second Affiliated Hospital, School of Medicine, The Chinese University of Hong Kong, Shenzhen & Longgang District People's Hospital of Shenzhen, Shenzhen, China.
  • Yiwen Liang
    Department of Urology, The Second Affiliated Hospital of The Chinese University of HongKong/Longgang District People's Hospital of Shenzhen, Shenzhen, Guangdong, 518172, China.
  • Zixin Luo
  • Jing Hu
    College of Chemistry, Sichuan University Chengdu 610064 People's Republic of China [email protected] +86 028 8541 2290.
  • Ruiquan Ge
  • Xiang Wan
    Institute of Computational and Theoretical Study and Department of Computer Science, Hong Kong Baptist University, Hong Kong, P.R. China.
  • Changmiao Wang
    Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Boulevard, Shenzhen 518055, China; University of Chinese Academy of Sciences, 52 Sanlihe Road, Beijing 100864, China.
  • Guannan Zou
    Department of Radiology, The Second Affiliated Hospital, School of Medicine, The Chinese University of Hong Kong, Shenzhen & Longgang District People's Hospital of Shenzhen, Shenzhen, China.
  • Feng Guo
  • Yi Jiang
    Institute of Genomic Medicine, Wenzhou Medical University, Wenzhou 325035, China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals