A robust deep learning framework for cerebral microbleeds recognition in GRE and SWI MRI

Area of Science:

• Neuroimaging and Artificial Intelligence
• Medical Diagnostics
• Cerebrovascular Diseases

Background:

• Cerebral microbleeds (CMB) are crucial MRI biomarkers for neurological conditions, but manual detection is inefficient and variable.
• Accurate CMB quantification is vital for assessing disease severity, stroke risk, and cognitive decline.
• Automated deep learning methods face challenges with CMB heterogeneity and false positives.

Purpose of the Study:

• To develop and validate a deep learning model for accurate and robust automated detection of cerebral microbleeds (CMB).
• To enhance CMB detection accuracy and reduce false positives using both 3D CNN and YOLO-based approaches.
• To ensure the model's performance across diverse public and private MRI datasets.

Main Methods:

• Utilized gradient echo (GRE) and susceptibility-weighted (SWI) MRI modalities from ADNI, AIBL, OATS, and MAS datasets.
• Developed a 3D convolutional neural network (CNN) for initial CMB detection.
• Integrated a You Only Look Once (YOLO)-based approach to refine detection and minimize false positives.

Main Results:

• The deep learning pipeline demonstrated high performance across all four datasets, with balanced accuracies ranging from 0.889 to 0.968.
• Achieved excellent AUC scores, indicating strong discriminative ability in CMB detection.
• Key metrics like precision, sensitivity, and F1-score were consistently high, underscoring the model's effectiveness.

Conclusions:

• Deep learning models show significant potential for improving the early diagnosis of conditions associated with cerebral microbleeds.
• The proposed automated detection method offers a robust and accurate solution, overcoming limitations of manual inspection.
• This advancement can support clinical decision-making and treatment planning for cerebrovascular and neurological disorders.