Home > Research > Publications & Outputs > Modeling Brain Aging with Explainable Triamese ViT

Electronic data

  • TriViT

    Accepted author manuscript, 30.6 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Modeling Brain Aging with Explainable Triamese ViT: Towards Deeper Insights into Autism Disorder

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print

Standard

Modeling Brain Aging with Explainable Triamese ViT: Towards Deeper Insights into Autism Disorder. / Zhang, Zhaonian; Aggarwal, Vaneet; Angelov, Plamen et al.
In: IEEE Journal of Biomedical and Health Informatics, 27.05.2025.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Zhang Z, Aggarwal V, Angelov P, Jiang R. Modeling Brain Aging with Explainable Triamese ViT: Towards Deeper Insights into Autism Disorder. IEEE Journal of Biomedical and Health Informatics. 2025 May 27. Epub 2025 May 27. doi: 10.1109/jbhi.2025.3574366

Author

Zhang, Zhaonian ; Aggarwal, Vaneet ; Angelov, Plamen et al. / Modeling Brain Aging with Explainable Triamese ViT : Towards Deeper Insights into Autism Disorder. In: IEEE Journal of Biomedical and Health Informatics. 2025.

Bibtex

@article{3e29e5b03842422189cab0587b2f5f71,
title = "Modeling Brain Aging with Explainable Triamese ViT: Towards Deeper Insights into Autism Disorder",
abstract = "Machine learning, particularly through advanced imaging techniques such as three-dimensional Magnetic Resonance Imaging (MRI), has significantly improved medical diagnostics. This is especially critical for diagnosing complex conditions like Alzheimer's disease. Our study introduces Triamese-ViT, an innovative Tri-structure of Vision Transformers (ViTs) that incorporates a built-in interpretability function, it has structure-aware explainability that allows for the identification and visualization of key features or regions contributing to the prediction, integrates information from three perspectives to enhance brain age estimation. This method not only increases accuracy but also improves interoperability with existing techniques. When evaluated, Triamese-ViT demonstrated superior performance and produced insightful attention maps. We applied these attention maps to the analysis of natural aging and the diagnosis of Autism Spectrum Disorder (ASD). The results aligned with those from occlusion analysis, identifying the Cingulum, Rolandic Operculum, Thalamus, and Vermis as important regions in normal aging, and highlighting the Thalamus and Caudate Nucleus as key regions for ASD diagnosis.",
author = "Zhaonian Zhang and Vaneet Aggarwal and Plamen Angelov and Richard Jiang",
year = "2025",
month = may,
day = "27",
doi = "10.1109/jbhi.2025.3574366",
language = "English",
journal = " IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "IEEE",

}

RIS

TY - JOUR

T1 - Modeling Brain Aging with Explainable Triamese ViT

T2 - Towards Deeper Insights into Autism Disorder

AU - Zhang, Zhaonian

AU - Aggarwal, Vaneet

AU - Angelov, Plamen

AU - Jiang, Richard

PY - 2025/5/27

Y1 - 2025/5/27

N2 - Machine learning, particularly through advanced imaging techniques such as three-dimensional Magnetic Resonance Imaging (MRI), has significantly improved medical diagnostics. This is especially critical for diagnosing complex conditions like Alzheimer's disease. Our study introduces Triamese-ViT, an innovative Tri-structure of Vision Transformers (ViTs) that incorporates a built-in interpretability function, it has structure-aware explainability that allows for the identification and visualization of key features or regions contributing to the prediction, integrates information from three perspectives to enhance brain age estimation. This method not only increases accuracy but also improves interoperability with existing techniques. When evaluated, Triamese-ViT demonstrated superior performance and produced insightful attention maps. We applied these attention maps to the analysis of natural aging and the diagnosis of Autism Spectrum Disorder (ASD). The results aligned with those from occlusion analysis, identifying the Cingulum, Rolandic Operculum, Thalamus, and Vermis as important regions in normal aging, and highlighting the Thalamus and Caudate Nucleus as key regions for ASD diagnosis.

AB - Machine learning, particularly through advanced imaging techniques such as three-dimensional Magnetic Resonance Imaging (MRI), has significantly improved medical diagnostics. This is especially critical for diagnosing complex conditions like Alzheimer's disease. Our study introduces Triamese-ViT, an innovative Tri-structure of Vision Transformers (ViTs) that incorporates a built-in interpretability function, it has structure-aware explainability that allows for the identification and visualization of key features or regions contributing to the prediction, integrates information from three perspectives to enhance brain age estimation. This method not only increases accuracy but also improves interoperability with existing techniques. When evaluated, Triamese-ViT demonstrated superior performance and produced insightful attention maps. We applied these attention maps to the analysis of natural aging and the diagnosis of Autism Spectrum Disorder (ASD). The results aligned with those from occlusion analysis, identifying the Cingulum, Rolandic Operculum, Thalamus, and Vermis as important regions in normal aging, and highlighting the Thalamus and Caudate Nucleus as key regions for ASD diagnosis.

U2 - 10.1109/jbhi.2025.3574366

DO - 10.1109/jbhi.2025.3574366

M3 - Journal article

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

ER -