Using transfer learning for automated microbleed segmentation
Mahsa Dadar1, Maryna Zhernovaia2, Sawsan Mahmoud2
1Department of Psychiatry, Faculty of Medicine, McGill University, Montreal, QC, Canada.
Introduction:
Cerebral microbleeds are small perivascular hemorrhages that can occur in both gray 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 interrater and intrarater variability. Automated techniques so far have shown high accuracy at a neighborhood ("patch") level at the expense of a high number of false positive voxel-wise lesions. We aimed to develop an automated, more precise microbleed segmentation tool that can use standardizable MRI contrasts.
Methods:
We first trained a ResNet50 network on another MRI segmentation task (cerebrospinal fluid vs. background segmentation) using T1-weighted, T2-weighted, and T2* MRIs. 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 segmentation of microbleeds from 78 participants was 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, and data augmentation on the performance of the Microbleed ResNet50 network.
Results:
The proposed method achieved 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.
Insights
This study introduces an automated method for detecting cerebral microbleeds using MRI. The new tool offers high sensitivity for identifying these small hemorrhages, improving diagnostic accuracy.
Area of Science:
- Neuroimaging
- Medical image analysis
- Neurology
Background:
- Cerebral microbleeds are small hemorrhages indicating cerebrovascular pathology and dementia risk.
- Current identification relies on manual segmentation of MRI, which is time-consuming and variable.
- Existing automated methods struggle with false positives, limiting their clinical utility.
Purpose of the Study:
- To develop an automated, precise microbleed segmentation tool.
- To utilize standardizable MRI contrasts for improved harmonization across scanners.
- To overcome limitations of manual segmentation and existing automated techniques.
Main Methods:
- A ResNet50 network was trained using transfer learning on T1-weighted, T2-weighted, and T2* MRIs.
- Morphological operators and rules were applied to reduce false positives.
- The system was trained and validated using manual microbleed segmentations from 78 participants.
Main Results:
- The automated method achieved high patch-level performance: 99.57% sensitivity, 99.16% specificity, and 99.93% accuracy.
- Per-lesion analysis showed high sensitivity (89.1-100%) across different brain regions (cortical GM, deep GM, WM).
- The system demonstrated excellent performance in deep gray matter (100% sensitivity, precision, and Dice index).
Conclusions:
- The developed automated method is highly sensitive for microbleed detection.
- This tool offers a more precise and efficient alternative to manual segmentation.
- The approach has the potential to improve the diagnosis and monitoring of cerebrovascular diseases.
