Cortical and Subcortical Structural Segmentation in Alzheimer’s Disease

  • Jafar Zamani
  • Ali Sadr
  • Amir-Homayoun Javadi
Keywords: Magnetic Resonance Imaging; Alzheimer’s Disease; Automatic Segmentation; Atrophy; Hippocampus

Abstract

Purpose: Alzheimer’s disease is a neurodegenerative disease that begins before clinical symptoms emerge. Amyloid-beta plaques and tau neurofibrillary tangles are the hallmark lesions of Alzheimer’s Disease (AD). Amyloid-beta plaques deposition is associated with increased hippocampal volume loss. The tissue volume measures reflect multiple underlying pathologies contributing to neurodegeneration, of which are the most characteristics of AD. Anatomical atrophy, as evidenced using Magnetic Resonance Imaging (MRI), is one of the most validated, easily accessible and widely used biomarkers of AD. Measurements of whole brain and hippocampal atrophy rates from serial structural MRI are potential markers of the underlying neuroaxonal damage and disease progression in AD. In this study, we extract automatically subcortical brain structures in AD and control subjects.
Materials and Methods: In this study we used 20 images (10 AD patients and 10 controls) taken from the Minimal Interval Resonance Imaging in Alzheimer's Disease (MIRIAD) dataset. We obtained volumes of Cerebrospinal Fluid (CSF), White Matter (WM), Grey Matter (GM), brain hemispheres, cerebellum and brainstem using volBrain pipeline. Subcortical brain structure segments and related volumes and label maps information were extracted. We compared left and right sides of some of the important brain area in AD for obtaining a biomarker with brain atrophy. Amygdala, caudate and hippocampus have shown to be undergone atrophy in AD.
Results: We provided volume information of some intracranial areas such as brain hemispheres, cerebellum and brainstem.
Conclusion: The results showed smaller hippocampal volume in AD patients compared to the controls. In addition to hippocampus, similar atrophy is also observable in amygdala and caudate.

Published
2019-10-30
Section
Articles