Meeting Banner
Abstract #5390

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

Yi-Ying Wu1,2, Yen-Chieh Ouyang2, Jyh-Wen Chai1,3, Kuan- Jung Pan1, Hsin-Che Wang4, Wen- Hsien Chen1, Hsian-Min Chen4, Chi-Chang Clayton Chen1,5, and Chein-I Chang6
1Department of Medical Imaging, Taichung Veterans General Hospital, Taichung, Taiwan, 2Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan, 3Department of Post-Baccalaureate Medicine, National Chung Hsing University, Taichung, Taiwan, 4Department of Medical Research, Taichung Veterans General Hospital, Taichung, Taiwan, 5Department of Medical Imaging, China Medical University Hospital, Taichung, Taiwan, 6Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore, MD, United States

Synopsis

Keywords:

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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords