X-FASNet: cross-scale feature-aware with self-attention network for cognitive decline assessment in Alzheimer's disease
Early diagnosis of Alzheimer's disease is critical for effective therapeutic intervention. The progressive nature of cognitive decline requires precise computational methods to detect subtle neuroanatomical changes in prodromal stages. Current multi-scale neural networks have limited cross-scal...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2025.1630838/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849235979819286528 |
|---|---|
| author | Wenhui Chen Shunwu Xu Yiran Peng Yiran Peng Hong Zhang Jian Zhang Huaihao Zheng Hao Yan Zhaowen Chen Zhaowen Chen |
| author_facet | Wenhui Chen Shunwu Xu Yiran Peng Yiran Peng Hong Zhang Jian Zhang Huaihao Zheng Hao Yan Zhaowen Chen Zhaowen Chen |
| author_sort | Wenhui Chen |
| collection | DOAJ |
| description | Early diagnosis of Alzheimer's disease is critical for effective therapeutic intervention. The progressive nature of cognitive decline requires precise computational methods to detect subtle neuroanatomical changes in prodromal stages. Current multi-scale neural networks have limited cross-scale feature integration capabilities, which constrain their effectiveness in identifying early neurodegenerative markers. This paper presents an Efficient Cross-Scale Feature-Aware Self-Attention Network (X-FASNet) designed to address these limitations through systematic hierarchical representation learning. The proposed architecture implements a dual-pathway multi-scale feature extraction approach to identify discriminative neuroanatomical patterns across various spatial resolutions, while integrating a novel cross-scale feature-aware self-attention module that enhances inter-scale information exchange and captures long-range dependencies. Quantitative evaluations on the DPC-SF dataset demonstrate that X-FASNet achieves superior performance with 93.7% accuracy and 0.973 F1-score, outperforming CONVADD by 10.8 percentage points in accuracy and 0.118 in F1-score, while also surpassing EfficientB2 on key performance metrics. Comprehensive experimentation across multiple neuroimaging datasets confirms that X-FASNet provides an effective computational framework for neurodegeneration assessment, characterized by enhanced detection of subtle anatomical variations and improved pathological pattern recognition. |
| format | Article |
| id | doaj-art-0a881cd747f84d2099ce0b6eb6ad72cf |
| institution | Kabale University |
| issn | 1664-2295 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj-art-0a881cd747f84d2099ce0b6eb6ad72cf2025-08-20T04:02:32ZengFrontiers Media S.A.Frontiers in Neurology1664-22952025-08-011610.3389/fneur.2025.16308381630838X-FASNet: cross-scale feature-aware with self-attention network for cognitive decline assessment in Alzheimer's diseaseWenhui Chen0Shunwu Xu1Yiran Peng2Yiran Peng3Hong Zhang4Jian Zhang5Huaihao Zheng6Hao Yan7Zhaowen Chen8Zhaowen Chen9Key Laboratory of Nondestructive Testing, Fujian Polytechnic Normal University, Fuzhou, ChinaKey Laboratory of Nondestructive Testing, Fujian Polytechnic Normal University, Fuzhou, ChinaKey Laboratory of Nondestructive Testing, Fujian Polytechnic Normal University, Fuzhou, ChinaFaculty of Innovation Engineering, Macau University of Science and Technology, Avenida Wai Long, Macau, ChinaKey Laboratory of Nondestructive Testing, Fujian Polytechnic Normal University, Fuzhou, ChinaKey Laboratory of Nondestructive Testing, Fujian Polytechnic Normal University, Fuzhou, ChinaKey Laboratory of Nondestructive Testing, Fujian Polytechnic Normal University, Fuzhou, ChinaKey Laboratory of Nondestructive Testing, Fujian Polytechnic Normal University, Fuzhou, ChinaKey Laboratory of Nondestructive Testing, Fujian Polytechnic Normal University, Fuzhou, ChinaFaculty of Innovation Engineering, Macau University of Science and Technology, Avenida Wai Long, Macau, ChinaEarly diagnosis of Alzheimer's disease is critical for effective therapeutic intervention. The progressive nature of cognitive decline requires precise computational methods to detect subtle neuroanatomical changes in prodromal stages. Current multi-scale neural networks have limited cross-scale feature integration capabilities, which constrain their effectiveness in identifying early neurodegenerative markers. This paper presents an Efficient Cross-Scale Feature-Aware Self-Attention Network (X-FASNet) designed to address these limitations through systematic hierarchical representation learning. The proposed architecture implements a dual-pathway multi-scale feature extraction approach to identify discriminative neuroanatomical patterns across various spatial resolutions, while integrating a novel cross-scale feature-aware self-attention module that enhances inter-scale information exchange and captures long-range dependencies. Quantitative evaluations on the DPC-SF dataset demonstrate that X-FASNet achieves superior performance with 93.7% accuracy and 0.973 F1-score, outperforming CONVADD by 10.8 percentage points in accuracy and 0.118 in F1-score, while also surpassing EfficientB2 on key performance metrics. Comprehensive experimentation across multiple neuroimaging datasets confirms that X-FASNet provides an effective computational framework for neurodegeneration assessment, characterized by enhanced detection of subtle anatomical variations and improved pathological pattern recognition.https://www.frontiersin.org/articles/10.3389/fneur.2025.1630838/fullAlzheimer's diseasemulti-scale modelcross-scale feature-aware self-attentionfeature fusioncognitive decline assessment |
| spellingShingle | Wenhui Chen Shunwu Xu Yiran Peng Yiran Peng Hong Zhang Jian Zhang Huaihao Zheng Hao Yan Zhaowen Chen Zhaowen Chen X-FASNet: cross-scale feature-aware with self-attention network for cognitive decline assessment in Alzheimer's disease Frontiers in Neurology Alzheimer's disease multi-scale model cross-scale feature-aware self-attention feature fusion cognitive decline assessment |
| title | X-FASNet: cross-scale feature-aware with self-attention network for cognitive decline assessment in Alzheimer's disease |
| title_full | X-FASNet: cross-scale feature-aware with self-attention network for cognitive decline assessment in Alzheimer's disease |
| title_fullStr | X-FASNet: cross-scale feature-aware with self-attention network for cognitive decline assessment in Alzheimer's disease |
| title_full_unstemmed | X-FASNet: cross-scale feature-aware with self-attention network for cognitive decline assessment in Alzheimer's disease |
| title_short | X-FASNet: cross-scale feature-aware with self-attention network for cognitive decline assessment in Alzheimer's disease |
| title_sort | x fasnet cross scale feature aware with self attention network for cognitive decline assessment in alzheimer s disease |
| topic | Alzheimer's disease multi-scale model cross-scale feature-aware self-attention feature fusion cognitive decline assessment |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2025.1630838/full |
| work_keys_str_mv | AT wenhuichen xfasnetcrossscalefeatureawarewithselfattentionnetworkforcognitivedeclineassessmentinalzheimersdisease AT shunwuxu xfasnetcrossscalefeatureawarewithselfattentionnetworkforcognitivedeclineassessmentinalzheimersdisease AT yiranpeng xfasnetcrossscalefeatureawarewithselfattentionnetworkforcognitivedeclineassessmentinalzheimersdisease AT yiranpeng xfasnetcrossscalefeatureawarewithselfattentionnetworkforcognitivedeclineassessmentinalzheimersdisease AT hongzhang xfasnetcrossscalefeatureawarewithselfattentionnetworkforcognitivedeclineassessmentinalzheimersdisease AT jianzhang xfasnetcrossscalefeatureawarewithselfattentionnetworkforcognitivedeclineassessmentinalzheimersdisease AT huaihaozheng xfasnetcrossscalefeatureawarewithselfattentionnetworkforcognitivedeclineassessmentinalzheimersdisease AT haoyan xfasnetcrossscalefeatureawarewithselfattentionnetworkforcognitivedeclineassessmentinalzheimersdisease AT zhaowenchen xfasnetcrossscalefeatureawarewithselfattentionnetworkforcognitivedeclineassessmentinalzheimersdisease AT zhaowenchen xfasnetcrossscalefeatureawarewithselfattentionnetworkforcognitivedeclineassessmentinalzheimersdisease |