Abstract Introduction Cerebral microbleeds are small perivascular haemorrhages that can occur in both grey and white matter brain regions. Microbleeds are a marker of cerebrovascular pathology, and are associated with an increased risk of cognitive decline and dementia. Microbleeds can be identified and manually segmented by expert radiologists and neurologists, usually from susceptibility-contrast MRI. The latter is hard to harmonize across scanners, while manual segmentation is laborious, time-consuming, and subject to inter- and intra-rater variabiltiy. Automated techniques so far have shown high accuracy at a neighborhood (“patch”) level at the expense of a high number of false positives voxel-wise lesions. We aimed to develop an automated, more precise microbleeds segmentation tool able to use standardizable MRI contrasts. Methods We first trained a ResNet50 network on another MRI segmentations task (cerberospinal fluid versus background segmentation) using T1-weighted, T2-weighted, and T2* MRI. We then used transfer learning to train the network for the detection of microbleeds with the same contrasts. As a final step, we employed a combination of morphological operators and rules at the local lesion level to remove false positives. Manual segmentations of microbleeds from 78 participants were used to train and validate the system. We assessed the impact of patch size, freezing weights of the initial layers, mini-batch size, learning rate, as well as data augmentation on the performance of the Microbleed ResNet50 network. Results The proposed method achieved a high performance, with a patch-level sensitivity, specificity, and accuracy of 99.57%, 99.16%, and 99.93%, respectively. At a per lesion level, sensitivity, precision, and Dice similarity index values were 89.1%, 20.1%, and 0.28 for cortical GM; 100%, 100%, and 1.0 for deep GM; and 91.1%, 44.3%, and 0.58 for WM, respectively. Discussion The proposed microbleed segmentation method is more suitable for the automated detection of microbleeds with high sensitivity.

Using Transfer Learning for Automated Microbleed Segmentation