Unlocking the Potential of XAI for Improved Alzheimer’s Disease Detection and Classification Using a ViT-GRU Model
Alzheimer’s Disease (AD) is a significant cause of dementia worldwide, and its progression from mild to severe affects an individual’s ability to perform daily activities independently. The accurate and early diagnosis of AD is crucial for effective clinical intervention. Howev...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10385046/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849340555872436224 |
|---|---|
| author | S. M. Mahim Md. Shahin Ali Md. Olid Hasan Abdullah Al Nomaan Nafi Arefin Sadat Shakib Al Hasan Bryar Shareef Md. Manjurul Ahsan Md. Khairul Islam Md. Sipon Miah Ming-Bo Niu |
| author_facet | S. M. Mahim Md. Shahin Ali Md. Olid Hasan Abdullah Al Nomaan Nafi Arefin Sadat Shakib Al Hasan Bryar Shareef Md. Manjurul Ahsan Md. Khairul Islam Md. Sipon Miah Ming-Bo Niu |
| author_sort | S. M. Mahim |
| collection | DOAJ |
| description | Alzheimer’s Disease (AD) is a significant cause of dementia worldwide, and its progression from mild to severe affects an individual’s ability to perform daily activities independently. The accurate and early diagnosis of AD is crucial for effective clinical intervention. However, interpreting AD from medical images can be challenging, even for experienced radiologists. Therefore, there is a need for an automatic diagnosis of AD, and researchers have investigated the potential of utilizing Artificial Intelligence (AI) techniques, particularly deep learning models, to address this challenge. This study proposes a framework that combines a Vision Transformer (ViT) and a Gated Recurrent Unit (GRU) to detect AD characteristics from Magnetic Resonance Imaging (MRI) images accurately and reliably. The ViT identifies crucial features from the input image, and the GRU establishes clear correlations between these features. The proposed model overcomes the class imbalance issue in the MRI image dataset and achieves superior accuracy and performance compared to existing methods. The model was trained on the Alzheimer’s MRI Preprocessed Dataset obtained from Kaggle, achieving notable accuracies of 99.53% for 4-class and 99.69% for binary classification. It also demonstrated a high accuracy of 99.26% for 3-class on the AD Neuroimaging Initiative (ADNI) Baseline Database. These results were validated through a thorough 10-fold cross-validation process. Furthermore, Explainable AI (XAI) techniques were incorporated to make the model interpretable and explainable. This allows clinicians to understand the model’s decision-making process and gain insights into the underlying factors driving the AD diagnosis. |
| format | Article |
| id | doaj-art-b7d3048f87d2464a810a3ada2b76a35a |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b7d3048f87d2464a810a3ada2b76a35a2025-08-20T03:43:52ZengIEEEIEEE Access2169-35362024-01-01128390841210.1109/ACCESS.2024.335180910385046Unlocking the Potential of XAI for Improved Alzheimer’s Disease Detection and Classification Using a ViT-GRU ModelS. M. Mahim0https://orcid.org/0009-0008-7205-9390Md. Shahin Ali1https://orcid.org/0000-0003-2564-8746Md. Olid Hasan2Abdullah Al Nomaan Nafi3https://orcid.org/0000-0002-9032-7175Arefin Sadat4https://orcid.org/0000-0002-9433-0136Shakib Al Hasan5https://orcid.org/0000-0002-5426-8382Bryar Shareef6Md. Manjurul Ahsan7https://orcid.org/0000-0003-0900-7930Md. Khairul Islam8https://orcid.org/0000-0002-6973-1536Md. Sipon Miah9https://orcid.org/0000-0002-6986-1517Ming-Bo Niu10https://orcid.org/0000-0002-7514-3239Department of Biomedical Engineering, Islamic University, Kushtia, BangladeshDepartment of Biomedical Engineering, Islamic University, Kushtia, BangladeshDepartment of Biomedical Engineering, Islamic University, Kushtia, BangladeshDepartment of Information and Communication Technology, Islamic University, Kushtia, BangladeshDepartment of Medicine, Chandpur Medical College, Chandpur, BangladeshDepartment of Biomedical Engineering, Islamic University, Kushtia, BangladeshDepartment of Computer Science, University of Nevada, Las Vegas, Las Vegas, NV, USADepartment of Radiology, Machine and Hybrid Intelligence Laboratory, Northwestern University, Chicago, IL, USADepartment of Biomedical Engineering, Islamic University, Kushtia, BangladeshDepartment of Information and Communication Technology, Islamic University, Kushtia, BangladeshInternet of Vehicle2 to Road Research Institute, Chang’an University, Xi’an, ChinaAlzheimer’s Disease (AD) is a significant cause of dementia worldwide, and its progression from mild to severe affects an individual’s ability to perform daily activities independently. The accurate and early diagnosis of AD is crucial for effective clinical intervention. However, interpreting AD from medical images can be challenging, even for experienced radiologists. Therefore, there is a need for an automatic diagnosis of AD, and researchers have investigated the potential of utilizing Artificial Intelligence (AI) techniques, particularly deep learning models, to address this challenge. This study proposes a framework that combines a Vision Transformer (ViT) and a Gated Recurrent Unit (GRU) to detect AD characteristics from Magnetic Resonance Imaging (MRI) images accurately and reliably. The ViT identifies crucial features from the input image, and the GRU establishes clear correlations between these features. The proposed model overcomes the class imbalance issue in the MRI image dataset and achieves superior accuracy and performance compared to existing methods. The model was trained on the Alzheimer’s MRI Preprocessed Dataset obtained from Kaggle, achieving notable accuracies of 99.53% for 4-class and 99.69% for binary classification. It also demonstrated a high accuracy of 99.26% for 3-class on the AD Neuroimaging Initiative (ADNI) Baseline Database. These results were validated through a thorough 10-fold cross-validation process. Furthermore, Explainable AI (XAI) techniques were incorporated to make the model interpretable and explainable. This allows clinicians to understand the model’s decision-making process and gain insights into the underlying factors driving the AD diagnosis.https://ieeexplore.ieee.org/document/10385046/Alzheimer’s diseasedeep learningViT-GRUXAIattention map |
| spellingShingle | S. M. Mahim Md. Shahin Ali Md. Olid Hasan Abdullah Al Nomaan Nafi Arefin Sadat Shakib Al Hasan Bryar Shareef Md. Manjurul Ahsan Md. Khairul Islam Md. Sipon Miah Ming-Bo Niu Unlocking the Potential of XAI for Improved Alzheimer’s Disease Detection and Classification Using a ViT-GRU Model IEEE Access Alzheimer’s disease deep learning ViT-GRU XAI attention map |
| title | Unlocking the Potential of XAI for Improved Alzheimer’s Disease Detection and Classification Using a ViT-GRU Model |
| title_full | Unlocking the Potential of XAI for Improved Alzheimer’s Disease Detection and Classification Using a ViT-GRU Model |
| title_fullStr | Unlocking the Potential of XAI for Improved Alzheimer’s Disease Detection and Classification Using a ViT-GRU Model |
| title_full_unstemmed | Unlocking the Potential of XAI for Improved Alzheimer’s Disease Detection and Classification Using a ViT-GRU Model |
| title_short | Unlocking the Potential of XAI for Improved Alzheimer’s Disease Detection and Classification Using a ViT-GRU Model |
| title_sort | unlocking the potential of xai for improved alzheimer x2019 s disease detection and classification using a vit gru model |
| topic | Alzheimer’s disease deep learning ViT-GRU XAI attention map |
| url | https://ieeexplore.ieee.org/document/10385046/ |
| work_keys_str_mv | AT smmahim unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel AT mdshahinali unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel AT mdolidhasan unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel AT abdullahalnomaannafi unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel AT arefinsadat unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel AT shakibalhasan unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel AT bryarshareef unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel AT mdmanjurulahsan unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel AT mdkhairulislam unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel AT mdsiponmiah unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel AT mingboniu unlockingthepotentialofxaiforimprovedalzheimerx2019sdiseasedetectionandclassificationusingavitgrumodel |