Vision transformers for the prediction of mild cognitive impairment to Alzheimer’s disease progression using mid-sagittal sMRI
BackgroundAlzheimer’s disease (AD) is one of the most common causes of neurodegenerative disease affecting over 50 million people worldwide. However, most AD diagnosis occurs in the moderate to late stage, which means that the optimal time for treatment has already passed. Mild cognitive impairment...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Aging Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnagi.2023.1102869/full |
| _version_ | 1797847723135729664 |
|---|---|
| author | Gia Minh Hoang Ue-Hwan Kim Jae Gwan Kim |
| author_facet | Gia Minh Hoang Ue-Hwan Kim Jae Gwan Kim |
| author_sort | Gia Minh Hoang |
| collection | DOAJ |
| description | BackgroundAlzheimer’s disease (AD) is one of the most common causes of neurodegenerative disease affecting over 50 million people worldwide. However, most AD diagnosis occurs in the moderate to late stage, which means that the optimal time for treatment has already passed. Mild cognitive impairment (MCI) is an intermediate state between cognitively normal people and AD patients. Therefore, the accurate prediction in the conversion process of MCI to AD may allow patients to start preventive intervention to slow the progression of the disease. Nowadays, neuroimaging techniques have been developed and are used to determine AD-related structural biomarkers. Deep learning approaches have rapidly become a key methodology applied to these techniques to find biomarkers.MethodsIn this study, we aimed to investigate an MCI-to-AD prediction method using Vision Transformers (ViT) to structural magnetic resonance images (sMRI). The Alzheimer’s Disease Neuroimaging Initiative (ADNI) database containing 598 MCI subjects was used to predict MCI subjects’ progression to AD. There are three main objectives in our study: (i) to propose an MRI-based Vision Transformers approach for MCI to AD progression classification, (ii) to evaluate the performance of different ViT architectures to obtain the most advisable one, and (iii) to visualize the brain region mostly affect the prediction of deep learning approach to MCI progression.ResultsOur method achieved state-of-the-art classification performance in terms of accuracy (83.27%), specificity (85.07%), and sensitivity (81.48%) compared with a set of conventional methods. Next, we visualized the brain regions that mostly contribute to the prediction of MCI progression for interpretability of the proposed model. The discriminative pathological locations include the thalamus, medial frontal, and occipital—corroborating the reliability of our model.ConclusionIn conclusion, our methods provide an effective and accurate technique for the prediction of MCI conversion to AD. The results obtained in this study outperform previous reports using the ADNI collection, and it suggests that sMRI-based ViT could be efficiently applied with a considerable potential benefit for AD patient management. The brain regions mostly contributing to prediction, in conjunction with the identified anatomical features, will support the building of a robust solution for other neurodegenerative diseases in future. |
| first_indexed | 2024-04-09T18:16:00Z |
| format | Article |
| id | doaj.art-bcbe5c7c5f2b46339cc57729a132b9e6 |
| institution | Directory Open Access Journal |
| issn | 1663-4365 |
| language | English |
| last_indexed | 2024-04-09T18:16:00Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Aging Neuroscience |
| spelling | doaj.art-bcbe5c7c5f2b46339cc57729a132b9e62023-04-13T04:29:54ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652023-04-011510.3389/fnagi.2023.11028691102869Vision transformers for the prediction of mild cognitive impairment to Alzheimer’s disease progression using mid-sagittal sMRIGia Minh Hoang0Ue-Hwan Kim1Jae Gwan Kim2Department of Biomedical Science and Engineering, Gwangju Institute of Science and Technology, Gwangju, Republic of KoreaAI Graduate School, Gwangju Institute of Science and Technology, Gwangju, Republic of KoreaDepartment of Biomedical Science and Engineering, Gwangju Institute of Science and Technology, Gwangju, Republic of KoreaBackgroundAlzheimer’s disease (AD) is one of the most common causes of neurodegenerative disease affecting over 50 million people worldwide. However, most AD diagnosis occurs in the moderate to late stage, which means that the optimal time for treatment has already passed. Mild cognitive impairment (MCI) is an intermediate state between cognitively normal people and AD patients. Therefore, the accurate prediction in the conversion process of MCI to AD may allow patients to start preventive intervention to slow the progression of the disease. Nowadays, neuroimaging techniques have been developed and are used to determine AD-related structural biomarkers. Deep learning approaches have rapidly become a key methodology applied to these techniques to find biomarkers.MethodsIn this study, we aimed to investigate an MCI-to-AD prediction method using Vision Transformers (ViT) to structural magnetic resonance images (sMRI). The Alzheimer’s Disease Neuroimaging Initiative (ADNI) database containing 598 MCI subjects was used to predict MCI subjects’ progression to AD. There are three main objectives in our study: (i) to propose an MRI-based Vision Transformers approach for MCI to AD progression classification, (ii) to evaluate the performance of different ViT architectures to obtain the most advisable one, and (iii) to visualize the brain region mostly affect the prediction of deep learning approach to MCI progression.ResultsOur method achieved state-of-the-art classification performance in terms of accuracy (83.27%), specificity (85.07%), and sensitivity (81.48%) compared with a set of conventional methods. Next, we visualized the brain regions that mostly contribute to the prediction of MCI progression for interpretability of the proposed model. The discriminative pathological locations include the thalamus, medial frontal, and occipital—corroborating the reliability of our model.ConclusionIn conclusion, our methods provide an effective and accurate technique for the prediction of MCI conversion to AD. The results obtained in this study outperform previous reports using the ADNI collection, and it suggests that sMRI-based ViT could be efficiently applied with a considerable potential benefit for AD patient management. The brain regions mostly contributing to prediction, in conjunction with the identified anatomical features, will support the building of a robust solution for other neurodegenerative diseases in future.https://www.frontiersin.org/articles/10.3389/fnagi.2023.1102869/fullAlzheimer’s diseaseMCI conversion predictionvision transformerssMRI image analysisdeep learningAlzheimer’s disease diagnosis |
| spellingShingle | Gia Minh Hoang Ue-Hwan Kim Jae Gwan Kim Vision transformers for the prediction of mild cognitive impairment to Alzheimer’s disease progression using mid-sagittal sMRI Frontiers in Aging Neuroscience Alzheimer’s disease MCI conversion prediction vision transformers sMRI image analysis deep learning Alzheimer’s disease diagnosis |
| title | Vision transformers for the prediction of mild cognitive impairment to Alzheimer’s disease progression using mid-sagittal sMRI |
| title_full | Vision transformers for the prediction of mild cognitive impairment to Alzheimer’s disease progression using mid-sagittal sMRI |
| title_fullStr | Vision transformers for the prediction of mild cognitive impairment to Alzheimer’s disease progression using mid-sagittal sMRI |
| title_full_unstemmed | Vision transformers for the prediction of mild cognitive impairment to Alzheimer’s disease progression using mid-sagittal sMRI |
| title_short | Vision transformers for the prediction of mild cognitive impairment to Alzheimer’s disease progression using mid-sagittal sMRI |
| title_sort | vision transformers for the prediction of mild cognitive impairment to alzheimer s disease progression using mid sagittal smri |
| topic | Alzheimer’s disease MCI conversion prediction vision transformers sMRI image analysis deep learning Alzheimer’s disease diagnosis |
| url | https://www.frontiersin.org/articles/10.3389/fnagi.2023.1102869/full |
| work_keys_str_mv | AT giaminhhoang visiontransformersforthepredictionofmildcognitiveimpairmenttoalzheimersdiseaseprogressionusingmidsagittalsmri AT uehwankim visiontransformersforthepredictionofmildcognitiveimpairmenttoalzheimersdiseaseprogressionusingmidsagittalsmri AT jaegwankim visiontransformersforthepredictionofmildcognitiveimpairmenttoalzheimersdiseaseprogressionusingmidsagittalsmri |