EXACT-CT: EXplainable Analysis for Crohn's and Tuberculosis using CT

2025-02-28

AI Summary

Crohn’s disease (CD) and intestinal tuberculosis (ITB) exhibit highly overlapping clinical and imaging features, with histological similarities—such as granulomas—further complicating differential diagnosis and risking harmful mismanagement (e.g., anti-tubercular therapy in CD or immunosuppressants in ITB). To address this, we propose an interpretable 3D contrast-enhanced CT (CECT)-based machine learning framework. Our method systematically integrates radiologist-defined imaging biomarkers—including the vasa recta-to-submucosal fat (VF/SF) ratio, necrosis, calcification, comb sign, and pulmonary TB findings—within an XGBoost classifier augmented by SHAP for quantitative interpretability. We benchmark against ResNet and the CTFoundation pretrained model. Evaluated on multicenter data, our approach significantly outperforms current state-of-the-art methods. SHAP analysis confirms strong, clinically meaningful contributions from key biomarkers. This work delivers a high-accuracy, clinically trustworthy decision-support tool for CD/ITB differentiation.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Interpretability, Explainability, and Transparency
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Crohn's disease and intestinal tuberculosis share many overlapping features such as clinical, radiological, endoscopic, and histological features - particularly granulomas, making it challenging to clinically differentiate them. Our research leverages 3D CTE scans, computer vision, and machine learning to improve this differentiation to avoid harmful treatment mismanagement such as unnecessary anti-tuberculosis therapy for Crohn's disease or exacerbation of tuberculosis with immunosuppressants. Our study proposes a novel method to identify radiologist - identified biomarkers such as VF to SF ratio, necrosis, calcifications, comb sign and pulmonary TB to enhance accuracy. We demonstrate the effectiveness by using different ML techniques on the features extracted from these biomarkers, computing SHAP on XGBoost for understanding feature importance towards predictions, and comparing against SOTA methods such as pretrained ResNet and CTFoundation.

Problem

• Differentiating Crohn's disease and intestinal tuberculosis using CT scans.
• Avoiding harmful treatment mismanagement through accurate diagnosis.
• Identifying biomarkers and using ML to enhance diagnostic accuracy.

Innovation

• Uses 3D CTE scans for disease differentiation
• Applies machine learning to identify biomarkers
• Computes SHAP on XGBoost for feature importance