Segmentation and Analysis of Corpus Callosum in Alzheimer MR Images using Total Variation Based Diffusion Filter and...

Area of Science:

• Neuroimaging
• Medical Image Analysis
• Biomarkers

Background:

• Alzheimer's Disease (AD) is a prevalent dementia impacting brain structures and cognitive functions.
• Early diagnosis of AD is crucial, and imaging biomarkers play a vital role.
• The Corpus Callosum (CC), a major white matter tract, shows alterations in AD, necessitating its analysis.

Purpose of the Study:

• To segment the Corpus Callosum (CC) using an edge-based level set method for characterizing CC atrophy in Alzheimer's Disease (AD).
• To evaluate the efficacy of Total Variation (TV) based diffusion filtering in pre-processing MRI images for enhanced CC segmentation.

Main Methods:

• Pre-processing of MRI images using Total Variation (TV) based diffusion filtering to improve edge information.
• Segmentation of the Corpus Callosum (CC) utilizing an edge-based level set method.
• Extraction of shape-based geometric features (area, perimeter, minor axis) from segmented CC for atrophy analysis.

Main Results:

• The edge-based level set method successfully segmented the CC in both normal and AD brain MRI scans.
• TV-based diffusion filtering preserved image texture and details, resulting in sharp CC boundaries for accurate segmentation.
• Significant percentage differences in geometric features (area: 5.97%, perimeter: 22.22%, minor axis: 9.52%) were observed between AD and normal subjects.

Conclusions:

• The proposed edge-based level set method with TV filtering is effective for segmenting the CC and quantifying atrophy in AD.
• The identified geometric features of the CC show potential as reliable biomarkers for AD diagnosis.
• This approach offers clinical utility in the early detection and assessment of Alzheimer's Disease.