Graph Classification and Radiomics Signature for Identification of Tuberculous Meningitis

2025-04-01

AI Summary

This study addresses the challenge of non-invasive imaging diagnosis of tuberculous meningitis (TBM) by proposing a region-specific classification framework based on T1-weighted, contrast-free MRI. We introduce the Pixel Array Graph Classifier (PAG-Classifier), which models the 3D neighborhood of pixels in the pre-pontine cistern as a graph structure; spatial-topological representations are extracted via graph Laplacian spectral decomposition and fused with radiomic features from GLCM and GLRLM. Crucially, we provide the first empirical evidence that the pre-pontine cistern exhibits dominant discriminative value for TBM identification. Evaluated on an internal cohort of 52 cases, the pre-pontine cistern PAG-Classifier achieves a mean F1-score of 85.71%, while the radiomics-only classifier attains 92.85%—surpassing state-of-the-art methods by 15% and 22%, respectively. In contrast, F1-scores for bone and corpus callosum regions fall below 50%, rigorously validating regional specificity.

Technology Category

Machine Learning: Graph-based Machine LearningData Mining & Knowledge Management: Graph Mining, Social Network Analysis & CommunityReasoning under Uncertainty: Graphical Models

Application Category

Web Mining and Content Analysis: Content-based information diffusionGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsUser Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Introduction: Tuberculous meningitis (TBM) is a serious brain infection caused by Mycobacterium tuberculosis, characterized by inflammation of the meninges covering the brain and spinal cord. Diagnosis often requires invasive lumbar puncture (LP) and cerebrospinal fluid (CSF) analysis. Objectives: This study aims to classify TBM patients using T1-weighted (T1w) non-contrast Magnetic Resonance Imaging (MRI) scans. We hypothesize that specific brain regions, such as the interpeduncular cisterns, bone, and corpus callosum, contain visual markers that can non-invasively distinguish TBM patients from healthy controls. We propose a novel Pixel-array Graphs Classifier (PAG-Classifier) that leverages spatial relationships between neighbouring 3D pixels in a graph-based framework to extract significant features through eigen decomposition. These features are then used to train machine learning classifiers for effective patient classification. We validate our approach using a radiomics-based methodology, classifying TBM patients based on relevant radiomics features. Results: We utilized an internal dataset consisting of 52 scans, 32 from confirmed TBM patients based on mycobacteria detection in CSF, and 20 from healthy individuals. We achieved a 5-fold cross-validated average F1 score of 85.71% for cistern regions with our PAG-Classifier and 92.85% with the radiomics features classifier, surpassing current state-of-the-art benchmarks by 15% and 22%, respectively. However, bone and corpus callosum regions showed poor classification effectiveness, with average F1 scores below 50%. Conclusion: Our study suggests that algorithms like the PAG-Classifier serve as effective tools for non-invasive TBM analysis, particularly by targeting the interpeduncular cistern. Findings indicate that the bone and corpus callosum regions lack distinctive patterns for differentiation.

Problem

• Non-invasive TBM diagnosis using MRI scans
• Graph-based classifier for brain region analysis
• Radiomics features for TBM patient classification

Innovation

• Pixel-array Graphs Classifier for TBM
• Graph-based feature extraction via eigen decomposition
• Radiomics features for non-invasive classification