Non-Contrast CT Esophageal Varices Grading through Clinical Prior-Enhanced Multi-Organ Analysis

2025-12-22

AI Summary

This study addresses the clinical challenge of noninvasively assessing esophageal varices (EV) severity using non-contrast CT (NCCT). We propose MOON++, a multi-organ collaborative analysis framework that—uniquely—integrates morphological features of the esophagus, liver, and spleen with clinical prior knowledge (e.g., inter-organ volumetric correlations) into deep learning modeling, thereby overcoming the limitations of single-organ analysis. Our method jointly performs organ segmentation, relational modeling, and clinical-knowledge-guided feature fusion to enable end-to-end EV grading. On an independent test set of 289 cases, MOON++ achieves AUCs of 0.894 (+9.1% over single-organ baselines) for G3 vs. <G3 classification and 0.921 (+12.8%) for ≥G2 vs. <G2 classification. Radiologist validation confirms its clinical reliability, establishing the first multi-organ collaborative diagnostic paradigm specifically designed for EV grading.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Esophageal varices (EV) represent a critical complication of portal hypertension, affecting approximately 60% of cirrhosis patients with a significant bleeding risk of ~30%. While traditionally diagnosed through invasive endoscopy, non-contrast computed tomography (NCCT) presents a potential non-invasive alternative that has yet to be fully utilized in clinical practice. We present Multi-Organ-COhesion Network++ (MOON++), a novel multimodal framework that enhances EV assessment through comprehensive analysis of NCCT scans. Inspired by clinical evidence correlating organ volumetric relationships with liver disease severity, MOON++ synthesizes imaging characteristics of the esophagus, liver, and spleen through multimodal learning. We evaluated our approach using 1,631 patients, those with endoscopically confirmed EV were classified into four severity grades. Validation in 239 patient cases and independent testing in 289 cases demonstrate superior performance compared to conventional single organ methods, achieving an AUC of 0.894 versus 0.803 for the severe grade EV classification (G3 versus <G3) and 0.921 versus 0.793 for the differentiation of moderate to severe grades (>=G2 versus <G2). We conducted a reader study involving experienced radiologists to further validate the performance of MOON++. To our knowledge, MOON++ represents the first comprehensive multi-organ NCCT analysis framework incorporating clinical knowledge priors for EV assessment, potentially offering a promising non-invasive diagnostic alternative.

Problem

• Develops a non-invasive CT method for grading esophageal varices severity
• Integrates multi-organ analysis to enhance diagnostic accuracy over single-organ approaches
• Provides a clinical prior-enhanced framework to reduce reliance on invasive endoscopy

Innovation

• Multi-organ multimodal learning for esophageal varices grading
• Clinical prior-enhanced analysis of NCCT scans
• Non-invasive framework outperforming single-organ methods