MixMicrobleed: Multi-stage detection and segmentation of cerebral microbleeds
This work addresses the detection and segmentation of cerebral microbleeds for medical imaging analysis, but it appears incremental as it combines existing methods without major innovations.
The authors tackled the problem of detecting and segmenting cerebral microbleeds in MRI images by proposing a multi-stage approach using Mask R-CNN for detection and U-Net for segmentation, achieving results on a dataset of 72 subjects from the MICCAI 2021 challenge.
Cerebral microbleeds are small, dark, round lesions that can be visualised on T2*-weighted MRI or other sequences sensitive to susceptibility effects. In this work, we propose a multi-stage approach to both microbleed detection and segmentation. First, possible microbleed locations are detected with a Mask R-CNN technique. Second, at each possible microbleed location, a simple U-Net performs the final segmentation. This work used the 72 subjects as training data provided by the "Where is VALDO?" challenge of MICCAI 2021.