CenSynCMB: Centre Maps and Physics-Guided Synthesis for Microbleed Detection
For radiologists and researchers studying small vessel disease, CenSynCMB improves automated detection of small, sparse lesions that are easily confused with mimics, though cohort-specific calibration remains a limitation.
CenSynCMB is a framework for detecting cerebral microbleeds in MRI that uses centre-map supervision and physics-guided synthesis of synthetic lesions and mimics. It achieved state-of-the-art lesion-level F1 of 74.3% on VALDO Task 2 and 65.0% on external AIBL SWI data.
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.