Unsupervised Detection of Post-Stroke Brain Abnormalities

TL;DR

This paper presents REFLECT, an unsupervised flow-based generative model that detects both focal and non-lesional brain abnormalities in post-stroke MRI, outperforming supervised methods in identifying structural changes.

Contribution

It introduces REFLECT, a novel unsupervised model trained on healthy and stroke data, improving detection of brain abnormalities without requiring annotated lesions.

Findings

Training on healthy controls enhances abnormality detection.

The model achieves higher lesion segmentation accuracy.

Unsupervised detection captures secondary structural changes.

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.