ORIGINAL RESEARCH article
Front. Neurosci.
Sec. Brain Imaging Methods
Volume 19 - 2025 | doi: 10.3389/fnins.2025.1653565
This article is part of the Research TopicImpact of Neurophysiological Biomarkers on Alzheimer's Functional and Cognitive OutcomesView all articles
A pipelined resource efficient convolutional neural network architecture for detecting and diagnosing Alzheimer's disease using brain sMRI
Provisionally accepted
Prasath T
Sumathi V*- Vellore Institute of Technology, Chennai, Chennai, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Alzheimer's disease (AD) is a progressive neurological disorder affecting memory and cognitive abilities amongst elderly. The progression of the disease can be overcome if detected early and treatments carried in time. The traditional methods for the detection and diagnosis of AD results in high time complexity and resource utilization. To overcome this, Resource Efficient Convolutional Neural Network (RECNN) is designed and developed in this study for the detection and diagnosis of AD using brain MRI images. This method adopts the following modules namely Gabor transformation, data augmentation and classification with anomalous pixel segmentation algorithm. The spatial frequency pixel property transformation is carried out by the functional Gabor transforms to improve the detection rate. Data augmentation approach is used to increase the number of brain image samples. RECNN is utilized to classify the images and the classified AD images are segmented by functional morphological method. The segmented images are further used to identify the pixels affected by AD to diagnose them as either mild or advanced cases. Two separate datasets are used to train and test the suggested AD detection techniques presented in this study. The experimental outcomes of this RECNN approach are also compared with the other conventional AD detection techniques.
Keywords: Alzheimer Disease, Gabor transformation, Data augmentation, CNN classifications, Fuzzy c-mean
Received: 25 Jun 2025; Accepted: 22 Sep 2025.
Copyright: © 2025 T and V. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Sumathi V, vsumathi@vit.ac.in
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.