Computed tomography-based transformer model for non-invasive prediction of portal venous pressure in chronic liver diseases

doi:10.3748/wjg.121435

Advanced Search

BPG is committed to discovery and dissemination of knowledge

Home / Archive / Volume 32, Issue 47

This Article

(6)

(7)

(0)

(141)

Peer-Review Report of This Article

CrossCheck and Google Search of This Article

Academic Rules and Norms of This Article

Supplementary Materials of This Article

Citation of this article

Corresponding Author of This Article

Research Domain of This Article

Article-Type of This Article

Open-Access Policy of This Article

Times Cited Counts in Google of This Article

Journal Information of This Article

Publication Name

World Journal of Gastroenterology

ISSN

1007-9327

Publisher of This Article

Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA

Retrospective Study

Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.

World J Gastroenterol. Dec 21, 2026; 32(47): 121435
Published online Dec 21, 2026. doi: 10.3748/wjg.121435

Computed tomography-based transformer model for non-invasive prediction of portal venous pressure in chronic liver diseases

Xu Guo, Huan Tong, Wu-Que Cai, Jia-Yi He, Ting-Rui Han, Shuai-Jie Qian, Xin Quan, Ying Li, Bo Wei, Zhi-Dong Wang, Yang Tai, Da-Qing Guo, Hao Wu

Xu Guo, Huan Tong, Ting-Rui Han, Shuai-Jie Qian, Xin Quan, Ying Li, Bo Wei, Zhi-Dong Wang, Yang Tai, Hao Wu, Department of Gastroenterology and Hepatology, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China

Wu-Que Cai, Jia-Yi He, Da-Qing Guo, School of Life Science and Technology, University of Electronic Science and Technology, Chengdu 611731, Sichuan Province, China

Co-first authors: Xu Guo and Huan Tong.

Co-corresponding authors: Da-Qing Guo and Hao Wu.

Author contributions: Guo X and Tong H contributed to formal analysis and writing-original draft as co-first authors; Guo X, Tong H, Cai WQ, He JY, Han TR, Tai Y, Qian SJ, Quan X, and Li Y contributed to data curation; Guo X, Tong H, Cai WQ, He JY, Han TR, and Tai Y contributed to software; Guo X, Tong H, Cai WQ, He JY, Wei B, and Wang ZD contributed to methodology; Wei B and Wang ZD contributed to hepatic venous pressure gradient measurement; Guo DQ and Wu H contributed to conceptualization, supervision, and writing-review and editing as co-corresponding authors. All authors critically reviewed and provided final approval of the manuscript, and were responsible for the decision to submit the manuscript for publication.

AI contribution statement: Portions of this manuscript were edited using AI tools (Google Gemini 3.1 pro) solely for language refinement. The authors carefully reviewed and verified all AI-assisted outputs and take full responsibility for the scientific content of the manuscript.

Supported by National Natural Science Foundation of China, No. 82270649; and Chengdu Science and Technology Program, No. 2024-YF05-00564-SN.

Institutional review board statement: This study was reviewed and approved by the Biomedical Ethics Committee of West China Hospital, Sichuan University, China, No. 20211488.

Informed consent statement: Given the retrospective design of this study, informed consent of patients was waived.

Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.

Data sharing statement: The data that support the findings of this study are available on request from the corresponding author.

Corresponding author: Hao Wu, PhD, Professor, Department of Gastroenterology and Hepatology, West China Hospital, Sichuan University, No. 37 Guo Xue Xiang, Chengdu 610041, Sichuan Province, China. hxxhwh@163.com

Received: March 26, 2026
Revised: June 16, 2026
Accepted: July 6, 2026
Published online: December 21, 2026
Processing time: 216 Days and 3.8 Hours

Core Tip

Core Tip: This retrospective study developed and validated a non-invasive regression machine learning model to predict the hepatic venous pressure gradient values in chronic liver diseases. Utilizing the transformer network combined with transfer learning based on contrast-enhanced computed tomography images from four pivotal sections, our model efficiently predicted the entire spectrum of portal venous pressure (from 1 to 37 mmHg) and showed good diagnostic performance for clinically significant hepatic venous pressure gradient thresholds including 5, 10, 12, 16 and 20 mmHg, outperforming conventional non-invasive methods. Moreover, the time-saving approach in this study minimized region of interest delineation workload, demonstrating potential for routine clinical application.