A novel interpreted deep network for Alzheimer’s disease prediction based on inverted self attention and vision transformer
Abstract In the world, Alzheimer’s disease (AD) is the utmost public reason for dementia. AD causes memory loss and disturbing mental function impairment in aging people. The loss of memory and disturbing mental function brings a significant load on patients as well as on society. So far, there is n...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-15007-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849330252958924800 |
|---|---|
| author | Wardah Ibrar Muhammad Attique Khan Ameer Hamza Saddaf Rubab Omar Alqahtani M. Turki-Hadj Alouane Sokea Teng Yunyoung Nam |
| author_facet | Wardah Ibrar Muhammad Attique Khan Ameer Hamza Saddaf Rubab Omar Alqahtani M. Turki-Hadj Alouane Sokea Teng Yunyoung Nam |
| author_sort | Wardah Ibrar |
| collection | DOAJ |
| description | Abstract In the world, Alzheimer’s disease (AD) is the utmost public reason for dementia. AD causes memory loss and disturbing mental function impairment in aging people. The loss of memory and disturbing mental function brings a significant load on patients as well as on society. So far, there is no actual treatment that can cure AD; however, early diagnosis can slow down this disease. Deep learning has shown substantial success in diagnosing AZ disease. However, challenges remain due to limited data, improper model selection, and extraction of irrelevant features. In this work, we proposed a fully automated framework based on the fusion of a vision transformer and a novel inverted residual bottleneck with self-attention (IRBwSA) for AD diagnosis. In the first step, data augmentation was performed to balance the selected dataset. After that, the vision model is designed and modified according to the dataset. Similarly, a new inverted bottleneck self-attention model is developed. The designed models are trained on the augmented dataset, and extracted features are fused using a novel search-based approach. Moreover, the designed models are interpreted using an explainable artificial intelligence technique named LIME. The fused features are finally classified using a shallow wide neural network and other classifiers. The experimental process was conducted on an augmented MRI dataset, and 96.1% accuracy and 96.05% precision rate were obtained. Comparison with a few recent techniques shows the proposed framework’s better performance. |
| format | Article |
| id | doaj-art-cb8e186c028e4b20b2ce38b703a76f14 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-cb8e186c028e4b20b2ce38b703a76f142025-08-20T03:46:58ZengNature PortfolioScientific Reports2045-23222025-08-0115111810.1038/s41598-025-15007-7A novel interpreted deep network for Alzheimer’s disease prediction based on inverted self attention and vision transformerWardah Ibrar0Muhammad Attique Khan1Ameer Hamza2Saddaf Rubab3Omar Alqahtani4M. Turki-Hadj Alouane5Sokea Teng6Yunyoung Nam7Department of Computer Science, HITEC UniversityDepartment of Artificial Intelligence, Prince Mohammad Bin Fahd UniversityDepartment of Computer Science, HITEC UniversityDepartment of Computer Engineering, College of Computing and Informatics, University of SharjahCollege of Computer Science, King Khalid UniversityCollege of Computer Science, King Khalid UniversityDepartment of ICT Convergence, Soonchunhyang UniversityDepartment of ICT Convergence, Soonchunhyang UniversityAbstract In the world, Alzheimer’s disease (AD) is the utmost public reason for dementia. AD causes memory loss and disturbing mental function impairment in aging people. The loss of memory and disturbing mental function brings a significant load on patients as well as on society. So far, there is no actual treatment that can cure AD; however, early diagnosis can slow down this disease. Deep learning has shown substantial success in diagnosing AZ disease. However, challenges remain due to limited data, improper model selection, and extraction of irrelevant features. In this work, we proposed a fully automated framework based on the fusion of a vision transformer and a novel inverted residual bottleneck with self-attention (IRBwSA) for AD diagnosis. In the first step, data augmentation was performed to balance the selected dataset. After that, the vision model is designed and modified according to the dataset. Similarly, a new inverted bottleneck self-attention model is developed. The designed models are trained on the augmented dataset, and extracted features are fused using a novel search-based approach. Moreover, the designed models are interpreted using an explainable artificial intelligence technique named LIME. The fused features are finally classified using a shallow wide neural network and other classifiers. The experimental process was conducted on an augmented MRI dataset, and 96.1% accuracy and 96.05% precision rate were obtained. Comparison with a few recent techniques shows the proposed framework’s better performance.https://doi.org/10.1038/s41598-025-15007-7Alzheimer diseaseMRIBottleneckSelf-attentionFusionShallow neural networks |
| spellingShingle | Wardah Ibrar Muhammad Attique Khan Ameer Hamza Saddaf Rubab Omar Alqahtani M. Turki-Hadj Alouane Sokea Teng Yunyoung Nam A novel interpreted deep network for Alzheimer’s disease prediction based on inverted self attention and vision transformer Scientific Reports Alzheimer disease MRI Bottleneck Self-attention Fusion Shallow neural networks |
| title | A novel interpreted deep network for Alzheimer’s disease prediction based on inverted self attention and vision transformer |
| title_full | A novel interpreted deep network for Alzheimer’s disease prediction based on inverted self attention and vision transformer |
| title_fullStr | A novel interpreted deep network for Alzheimer’s disease prediction based on inverted self attention and vision transformer |
| title_full_unstemmed | A novel interpreted deep network for Alzheimer’s disease prediction based on inverted self attention and vision transformer |
| title_short | A novel interpreted deep network for Alzheimer’s disease prediction based on inverted self attention and vision transformer |
| title_sort | novel interpreted deep network for alzheimer s disease prediction based on inverted self attention and vision transformer |
| topic | Alzheimer disease MRI Bottleneck Self-attention Fusion Shallow neural networks |
| url | https://doi.org/10.1038/s41598-025-15007-7 |
| work_keys_str_mv | AT wardahibrar anovelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT muhammadattiquekhan anovelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT ameerhamza anovelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT saddafrubab anovelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT omaralqahtani anovelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT mturkihadjalouane anovelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT sokeateng anovelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT yunyoungnam anovelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT wardahibrar novelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT muhammadattiquekhan novelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT ameerhamza novelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT saddafrubab novelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT omaralqahtani novelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT mturkihadjalouane novelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT sokeateng novelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer AT yunyoungnam novelinterpreteddeepnetworkforalzheimersdiseasepredictionbasedoninvertedselfattentionandvisiontransformer |