Deep Learning‐Enhanced CTA for Noninvasive Prediction of First Variceal Haemorrhage in Cirrhosis: A Multi‐Centre Study
Authors:
- 8 August 2025
- journal article
- research article
- Published by Wiley in Liver International
- Vol. 45 (9) , e70274
Abstract
Background and Aims: The first variceal haemorrhage (FVH) is a life‐threatening complication of liver cirrhosis that requires timely intervention; however, noninvasive tools for accurately predicting FVH remain limited. This study aimed to develop noninvasive, deep learning‐enhanced computed tomographic angiography (CTA) models for early and accurate FVH prediction. Methods: This multi‐centre retrospective study included 184 cirrhotic patients (FVH: n = 107, non‐FVH: n = 77) enrolled from December 2014 to May 2022. Patients were randomly divided (7:3) into training and validation cohorts. CTA and clinical data were collected and analysed. A novel Vision‐Transformer (ViT) network, combined with reinforcement learning (RL), was applied to CTA images to predict FVH and was compared with convolutional neural networks (CNNs). Models were evaluated using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA), and feature importance was determined from model coefficients and gradients. Results: The ViT + RL* model demonstrated superior diagnostic performance, achieving an AUC of 0.985 (95% CI, 0.955–1.0) in the validation cohort and 0.956 (95% CI, 0.919–0.988) in the training cohort, outperforming traditional CNNs. DCA and the area under the curve confirmed the enhanced clinical utility of the ViT + RL* model compared to CNNs; the ViT + RL* model highlighted critical regions in the liver, spleen, oesophageal lumen, and abdominal vessels. Meanwhile, clinical data identified creatinine and prothrombin time as potential predictive factors, with moderate predictive performance. Conclusions: The novel deep learning‐enhanced CTA models offer a robust, non‐invasive method for predicting FVH, with the ViT + RL* model demonstrating excellent efficacy; thus providing a valuable tool for early risk stratification in cirrhotic patients.Keywords
Funding Information
- China Postdoctoral Science Foundation
This publication has 19 references indexed in Scilit:
- Baveno VII algorithm outperformed other models in ruling out high-risk varices in individuals with HBV-related cirrhosisJournal of Hepatology, 2022
- A non-invasive model based on the virtual portal pressure gradient to predict the first variceal hemorrhage in cirrhotic patientsHepatology International, 2022
- Baveno VII – Renewing consensus in portal hypertensionJournal of Hepatology, 2022
- CT-derived quantitative liver volumetric parameters for prediction of severe esophageal varices and the risk of first variceal hemorrhageEuropean Journal of Radiology, 2021
- Automated and real-time validation of gastroesophageal varices under esophagogastroduodenoscopy using a deep convolutional neural network: a multicenter retrospective study (with video)Gastrointestinal Endoscopy, 2021
- Pharmacologic prevention of variceal bleeding and rebleedingHepatology International, 2017
- Portal hypertensive bleeding in cirrhosisHepatology, 2017
- Expanding consensus in portal hypertensionJournal of Hepatology, 2015
- Revising consensus in portal hypertension: Report of the Baveno V consensus workshop on methodology of diagnosis and therapy in portal hypertensionJournal of Hepatology, 2010
- Prevention and management of gastroesophageal varices and variceal hemorrhage in cirrhosisHepatology, 2007