Localizing the Thickness of Cortical Regions to Descriptor the Vital Factors for Alzheimer’s Disease Using UNET Deep Learning

Abstract

Alzheimer’s disease (AD) stands as a formidable global health challenge, impacting millions of lives. Timely detection and localization of affected brain regions are pivotal for understanding its progression and developing effective treatments. This research introduces a cutting-edge approach to address these critical concerns. Traditionally, exploring the influence of AD on the human brain has been a complex task. Existing methods often face limitations in accurately localizing the most affected brain regions, impeding our understanding of the disease's focal impact. Additionally, the need for efficient and precise cortical thickness analysis techniques has driven the quest for innovative solutions. In this paper, we proposed the DL+DiReCT method, a high-precision strategy that integrates deep learning-based neuroanatomy segmentations with Diffeomorphic Registration-based Cortical Thickness (DiReCT). This approach streamlines the measurement of cortical thickness, enabling rapid and precise localization of AD-affected regions within the brain. Our method significantly contributes to enhancing our understanding of the localized effects of Alzheimer’s disease. Our extensive study, involving 434 subjects from the ADNI dataset and rigorous data augmentation and optimization, has yielded remarkable outcomes. This approach has far-reaching implications for discerning the specific regions of the brain affected by AD, shedding light on their consequences for essential physiological factors.