AutoComb: Automated Comb Sign Detector for 3D CTE Scans

2025-02-28

AI Summary

To address clinical challenges in interpreting the Comb Sign on 3D CT enterography—including subjective manual assessment, inter-observer variability, and difficulty in multiplanar localization—this paper proposes the first fully automated detection framework based on probabilistic graph modeling. The method integrates deep learning–based segmentation, vessel-enhancing filtering, and Gaussian Mixture Model (GMM)–based characterization of bowel wall enhancement intensity. It further introduces two novel components: iterative neighborhood-maximized probability enhancement and distance-weighted vascular scoring, enabling joint modeling of vascular branching topology and local enhancement patterns. By eliminating reliance on radiologist expertise while preserving anatomical interpretability, the framework significantly improves detection objectivity and accuracy, achieving a 12.6% mAP gain over baseline methods. This work establishes the first reproducible, quantitative, and automated imaging biomarker analysis tool for hypervascular intestinal diseases such as Crohn’s disease.

Technology Category

• Computer Vision: Segmentation
• Search and Optimization: Combinatorial Optimization
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic 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: Web data integration and cleaning

Abstract

Comb Sign is an important imaging biomarker to detect multiple gastrointestinal diseases. It shows up as increased blood flow along the intestinal wall indicating potential abnormality, which helps doctors diagnose inflammatory conditions. Despite its clinical significance, current detection methods are manual, time-intensive, and prone to subjective interpretation due to the need for multi-planar image-orientation. To the best of our knowledge, we are the first to propose a fully automated technique for the detection of Comb Sign from CTE scans. Our novel approach is based on developing a probabilistic map that shows areas of pathological hypervascularity by identifying fine vascular bifurcations and wall enhancement via processing through stepwise algorithmic modules. These modules include utilising deep learning segmentation model, a Gaussian Mixture Model (GMM), vessel extraction using vesselness filter, iterative probabilistic enhancement of vesselness via neighborhood maximization and a distance-based weighting scheme over the vessels. Experimental results demonstrate that our pipeline effectively identifies Comb Sign, offering an objective, accurate, and reliable tool to enhance diagnostic accuracy in Crohn's disease and related hypervascular conditions where Comb Sign is considered as one of the important biomarkers.

Problem

• Automated detection of Comb Sign in 3D CTE scans
• Overcoming manual, time-intensive, and subjective detection methods
• Enhancing diagnostic accuracy for Crohn's disease and hypervascular conditions

Innovation

• Automated detection using deep learning segmentation
• Probabilistic map for pathological hypervascularity identification
• Vessel extraction and enhancement via algorithmic modules