Unsupervised Detection of Post-Stroke Brain Abnormalities

2025-10-28

AI Summary

This study addresses the unsupervised detection of both focal (e.g., infarcts) and non-focal (e.g., atrophy, ventricular enlargement) structural abnormalities in post-stroke brain MRI—challenging due to the absence of lesion annotations. We propose REFLECT, a flow-based generative model trained exclusively on healthy control data, enabling precise modeling of normal anatomical variation without requiring labeled pathology. To ensure interpretability and rigorous evaluation, we introduce a dual-expert central-slice annotation protocol and a free-response ROC (FROC) framework for quantitative assessment of anomaly maps. Evaluated on the ATLAS test set using an IXI-trained model, REFLECT achieves a Dice score of 0.37 for lesion segmentation (+21% over baseline) and an FROC score of 0.62 for non-lesional abnormality detection—marking the first unsupervised method to robustly detect both abnormality types simultaneously. This advances stroke imaging biomarker discovery by enabling annotation-free, anatomy-aware anomaly detection.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Segmentation
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Post-stroke MRI not only delineates focal lesions but also reveals secondary structural changes, such as atrophy and ventricular enlargement. These abnormalities, increasingly recognised as imaging biomarkers of recovery and outcome, remain poorly captured by supervised segmentation methods. We evaluate REFLECT, a flow-based generative model, for unsupervised detection of both focal and non-lesional abnormalities in post-stroke patients. Using dual-expert central-slice annotations on ATLAS data, performance was assessed at the object level with Free-Response ROC analysis for anomaly maps. Two models were trained on lesion-free slices from stroke patients (ATLAS) and on healthy controls (IXI) to test the effect of training data. On ATLAS test subjects, the IXI-trained model achieved higher lesion segmentation (Dice = 0.37 vs 0.27) and improved sensitivity to non-lesional abnormalities (FROC = 0.62 vs 0.43). Training on fully healthy anatomy improves the modelling of normal variability, enabling broader and more reliable detection of structural abnormalities.

Problem

• Detecting post-stroke brain abnormalities unsupervisedly using generative models
• Evaluating REFLECT model for focal and non-lesional anomaly detection
• Assessing training data impact on abnormality segmentation performance

Innovation

• Flow-based generative model detects brain abnormalities
• Unsupervised learning identifies structural changes post-stroke
• Training on healthy data improves abnormality detection accuracy