Automatic White Matter Hyperintensity extraction in ICEM with Orthogonal Subspace Projection-Based Go-Decomposition Approach

Motivation: White matter hyperintensities (WMH) are associated with Alzheimer's disease and cognitive decline. Accurate and automated WMH detection is crucial for diagnosis and monitoring. Goal(s): To automate WMH segmentation using the OSP-GoDec method and ICEM, replacing manual feature selection and comparing performance with SPM-LPA. Approach: MRI data from Alzheimer's patients were preprocessed and augmented using the CBEP algorithm to generate hyperspectral images. OSP-GoDec identified high-signal WMH points, which were used to be training samples for ICEM-based automated segmentation. Results: The proposed method achieved higher accuracy in detecting WMH, especially smaller lesions, compared to SPM-LPA, demonstrating its effectiveness for automated analysis. Impact: Accurate automated detection of WMH can significantly improve diagnosis and monitoring of AD, enhancing clinical decision-making. This approach reduces reliance on manual segmentation, minimizes human error, and enables faster, more reliable analysis of brain MRI scans for better patient outcomes.