CenSynCMB: Centre Maps and Physics-Guided Synthesis for Microbleed Detection
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new computer method called CenSynCMB to find very small brain bleeds in MRI scans. These bleeds are hard to spot because they look like normal vessels or other small spots. Their method uses special techniques including 3D attention and synthetic training data to better recognize true bleeds and ignore look-alikes. Tests showed their method outperformed others in detecting these microbleeds in different data sets. They also note that adjusting the method for specific groups of scans is important for accurate results.
Cerebral microbleedsMRISmall vessel diseaseAmyloid related imaging abnormalities (ARIA-H)3D Attention U-NetSynthetic dataLesion detectionFalse-negative reweightingF1 scoreRecall
Authors
Lucas He, Hanyuan Zhang, Krinos Li, Adama Fatima Saccoh, Silvia Ingala, Rafael Rehwald, Marleen de Bruijne, Frederik Barkhof, Rhodri Davies, Carole H. Sudre
Abstract
Cerebral microbleeds (CMBs) are MRI markers of small vessel disease and the microbleed component of amyloid related imaging abnormalities (ARIA-H), but their small size, sparsity, and similarity to vessels, calcification-like foci, and artefacts make automated detection difficult. We propose CenSynCMB, a centre-guided and mimic-aware framework combining a 3D Attention U-Net, auxiliary centre-map supervision, false-negative-driven reweighting, and fold-wise physics-guided synthesis of positive CMBs and labelled hard negatives. Synthetic data expose the detector to compact lesions and common mimics without validation or test leakage. On VALDO Task 2, CenSynCMB achieved the best local-comparison lesion-level F1 (74.3%, p = 0.020); on external AIBL SWI, it achieved the highest local-comparison recall (88.5%, p = 0.0058) and F1 (65.0%, p = 0.0016). Together, these results support scalable CMB candidate extraction in large, unlabelled MRI cohorts, while highlighting cohort-specific calibration as the next step toward reliable burden estimation.