The Value of Ultra-High-Resolution Susceptibility-Weighted Imaging Minimum Intensity Projection in Deep Learning-Based Detection of Cerebral Microbleeds

Inhalt:
Cerebral microbleeds (CMBs), detected through susceptibility-weighted imaging (SWI) in magnetic resonance images, are important diagnostic indicators for various cerebrovascular diseases. The detection rate of CMBs generally increases with higher field strengths. This study explored the efficacy of detecting CMBs using the minimum intensity projection (MinIP) technique with 7T ultra-high field MRI. MinIP, a post-processing technique applied to SWI, maintains key characteristics of CMBs on each slice while preserving the continuous structure of blood vessels, offering potential advantages for automated detection. We compared the performance of CMB detection using the YOLO-v7 model with SWI and MinIP as inputs. In tests using the original images (size: 1456x1792 pixels and 1344x1792 pixels), the detection performance of SWI and MinIP was comparable. However, when a sliding window approach (patch size: 640x640 pixels) was employed, MinIP achieved a significant improvement in sensitivity (91.05%) while maintaining comparable precision (93.05%) to SWI, which achieved a 80.32% sensitivity and 95.40% precision. These findings suggest that ultra-highresolution MinIP, particularly when combined with a sliding window technique, can substantially enhance the detection of CMBs in deep learning models.