AlzheimerViT: harnessing lightweight vision transformer architecture for proactive Alzheimer’s screening

BackgroundAlzheimer’s is a disease in the human brain characterized by gradual memory loss, confusion, and alterations in behavior. It is a complex and continuously degenerative disorder of the nervous system, which still has early detection and diagnosis as challenges to overcome. The disease cause...

Full description

Saved in:
Bibliographic Details
Main Authors: C. Kishor Kumar Reddy, Hafsa Ihteshamuddin Ahmed, Muhammad Mohzary, T. Monika Singh, Mohammed Shuaib, Shadab Alam, Hani Mohammed Alnami
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1568312/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334076745449472
author C. Kishor Kumar Reddy
Hafsa Ihteshamuddin Ahmed
Muhammad Mohzary
Muhammad Mohzary
T. Monika Singh
Mohammed Shuaib
Shadab Alam
Hani Mohammed Alnami
Hani Mohammed Alnami
author_facet C. Kishor Kumar Reddy
Hafsa Ihteshamuddin Ahmed
Muhammad Mohzary
Muhammad Mohzary
T. Monika Singh
Mohammed Shuaib
Shadab Alam
Hani Mohammed Alnami
Hani Mohammed Alnami
author_sort C. Kishor Kumar Reddy
collection DOAJ
description BackgroundAlzheimer’s is a disease in the human brain characterized by gradual memory loss, confusion, and alterations in behavior. It is a complex and continuously degenerative disorder of the nervous system, which still has early detection and diagnosis as challenges to overcome. The disease causes significant damage in individuals suffering from the disorder as they progressively lose cognitive ability. Its diagnosis and management depend primarily on the ability to diagnose early to initiate proper intervention. Unfortunately, this remains a difficult feat, given the resemblance of early signs of the disease with symptoms associated with normal aging and other disorders involving cognition. While clinical tests have their limitations, brain imaging such as MRI can provide detailed insights into changes in the brain. Deep learning techniques, mainly when applied to MRI data, have proven helpful in the early detection of Alzheimer’s Disease.MethodsIn the proposed study, a lightweight, self-attention-based vision transformer (ViT) is employed to predict Alzheimer’s disease using MRI images from the OASIS-3 dataset. Data pre-processing and augmentation techniques have been added to strengthen the model’s generalization ability and enhance model performance, which is visualized using Grad-Cam.ResultsThe proposed model achieves exceptional results with an accuracy of 98.57%, approximate precision of 98.7%, Recall of about 98.47%, and specificity of 98.67%. It also achieves a Kappa Score of 97.2% and an AUC ROC Score of 99%.ConclusionThis paper, along with comprehensive data pre-processing and augmentation, represents one of the major steps toward achieving more robust and clinically applicable models for Alzheimer’s disease prediction. The proposed study indicates that deep learning models have the potential to enhance the diagnosis of Alzheimer’s disease. By integrating Deep learning techniques with careful data processing, more reliable early detection models can be developed, which in turn leads to better treatment outcomes.
format Article
id doaj-art-2b37086b1b5a4cc18b801575e87e38f1
institution Kabale University
issn 2296-858X
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-2b37086b1b5a4cc18b801575e87e38f12025-08-20T03:45:40ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-06-011210.3389/fmed.2025.15683121568312AlzheimerViT: harnessing lightweight vision transformer architecture for proactive Alzheimer’s screeningC. Kishor Kumar Reddy0Hafsa Ihteshamuddin Ahmed1Muhammad Mohzary2Muhammad Mohzary3T. Monika Singh4Mohammed Shuaib5Shadab Alam6Hani Mohammed Alnami7Hani Mohammed Alnami8Department of Computer Science and Engineering, Stanley College of Engineering and Technology for Women, Hyderabad, IndiaDepartment of Computer Science and Engineering, Stanley College of Engineering and Technology for Women, Hyderabad, IndiaDepartment of Computer Science, College of Engineering and Computer Science, Jazan University, Jazan, Saudi ArabiaEngineering and Technology Research Center, Jazan University, Jazan, Saudi ArabiaDepartment of Computer Science and Engineering, Stanley College of Engineering and Technology for Women, Hyderabad, IndiaDepartment of Computer Science, College of Engineering and Computer Science, Jazan University, Jazan, Saudi ArabiaDepartment of Computer Science, College of Engineering and Computer Science, Jazan University, Jazan, Saudi ArabiaDepartment of Computer Science, College of Engineering and Computer Science, Jazan University, Jazan, Saudi ArabiaEngineering and Technology Research Center, Jazan University, Jazan, Saudi ArabiaBackgroundAlzheimer’s is a disease in the human brain characterized by gradual memory loss, confusion, and alterations in behavior. It is a complex and continuously degenerative disorder of the nervous system, which still has early detection and diagnosis as challenges to overcome. The disease causes significant damage in individuals suffering from the disorder as they progressively lose cognitive ability. Its diagnosis and management depend primarily on the ability to diagnose early to initiate proper intervention. Unfortunately, this remains a difficult feat, given the resemblance of early signs of the disease with symptoms associated with normal aging and other disorders involving cognition. While clinical tests have their limitations, brain imaging such as MRI can provide detailed insights into changes in the brain. Deep learning techniques, mainly when applied to MRI data, have proven helpful in the early detection of Alzheimer’s Disease.MethodsIn the proposed study, a lightweight, self-attention-based vision transformer (ViT) is employed to predict Alzheimer’s disease using MRI images from the OASIS-3 dataset. Data pre-processing and augmentation techniques have been added to strengthen the model’s generalization ability and enhance model performance, which is visualized using Grad-Cam.ResultsThe proposed model achieves exceptional results with an accuracy of 98.57%, approximate precision of 98.7%, Recall of about 98.47%, and specificity of 98.67%. It also achieves a Kappa Score of 97.2% and an AUC ROC Score of 99%.ConclusionThis paper, along with comprehensive data pre-processing and augmentation, represents one of the major steps toward achieving more robust and clinically applicable models for Alzheimer’s disease prediction. The proposed study indicates that deep learning models have the potential to enhance the diagnosis of Alzheimer’s disease. By integrating Deep learning techniques with careful data processing, more reliable early detection models can be developed, which in turn leads to better treatment outcomes.https://www.frontiersin.org/articles/10.3389/fmed.2025.1568312/fullAlzheimer’s diseaseMobileViTdata augmentationdisease detectiondeep learning
spellingShingle C. Kishor Kumar Reddy
Hafsa Ihteshamuddin Ahmed
Muhammad Mohzary
Muhammad Mohzary
T. Monika Singh
Mohammed Shuaib
Shadab Alam
Hani Mohammed Alnami
Hani Mohammed Alnami
AlzheimerViT: harnessing lightweight vision transformer architecture for proactive Alzheimer’s screening
Frontiers in Medicine
Alzheimer’s disease
MobileViT
data augmentation
disease detection
deep learning
title AlzheimerViT: harnessing lightweight vision transformer architecture for proactive Alzheimer’s screening
title_full AlzheimerViT: harnessing lightweight vision transformer architecture for proactive Alzheimer’s screening
title_fullStr AlzheimerViT: harnessing lightweight vision transformer architecture for proactive Alzheimer’s screening
title_full_unstemmed AlzheimerViT: harnessing lightweight vision transformer architecture for proactive Alzheimer’s screening
title_short AlzheimerViT: harnessing lightweight vision transformer architecture for proactive Alzheimer’s screening
title_sort alzheimervit harnessing lightweight vision transformer architecture for proactive alzheimer s screening
topic Alzheimer’s disease
MobileViT
data augmentation
disease detection
deep learning
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1568312/full
work_keys_str_mv AT ckishorkumarreddy alzheimervitharnessinglightweightvisiontransformerarchitectureforproactivealzheimersscreening
AT hafsaihteshamuddinahmed alzheimervitharnessinglightweightvisiontransformerarchitectureforproactivealzheimersscreening
AT muhammadmohzary alzheimervitharnessinglightweightvisiontransformerarchitectureforproactivealzheimersscreening
AT muhammadmohzary alzheimervitharnessinglightweightvisiontransformerarchitectureforproactivealzheimersscreening
AT tmonikasingh alzheimervitharnessinglightweightvisiontransformerarchitectureforproactivealzheimersscreening
AT mohammedshuaib alzheimervitharnessinglightweightvisiontransformerarchitectureforproactivealzheimersscreening
AT shadabalam alzheimervitharnessinglightweightvisiontransformerarchitectureforproactivealzheimersscreening
AT hanimohammedalnami alzheimervitharnessinglightweightvisiontransformerarchitectureforproactivealzheimersscreening
AT hanimohammedalnami alzheimervitharnessinglightweightvisiontransformerarchitectureforproactivealzheimersscreening