SA-AVAE: A Sex-Aware Adversarial Variational Autoencoder Network for Biological Brain Age Estimation in IoMT-Enabled Multimodal Neuroimages
Rehman, Abd Ur Rehman, Azka Farooq, Muhammad Umar Lee, Taehyun Khan, Tariq M Razzak, Imran Gho, Sung-Min Lee, Aleum Chae, Dong-Kyu Usman, Muhammad
Rehman, Abd Ur
Rehman, Azka
Farooq, Muhammad Umar
Lee, Taehyun
Khan, Tariq M
Razzak, Imran
Gho, Sung-Min
Lee, Aleum
Chae, Dong-Kyu
Usman, Muhammad
Supervisor
Department
Computational Biology
Embargo End Date
Type
Journal article
Date
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Magnetic resonance imaging (MRI) of the brain, facilitated by IoMT-assisted telemedicine platforms, serves as a key biomarker for brain health determination through its structural and functional studies. Notably, combining structural MRI (sMRI) and functional MRI (fMRI) has the potential to improve brain age estimation by leveraging complementary data. However, fMRI data, being noisier than sMRI, complicates multimodal fusion. Traditional fusion methods often introduce more noise than useful information, which can reduce accuracy compared to using sMRI alone. In this paper, we propose a novel multimodal framework for biological brain age estimation, utilizing a sex-aware adversarial variational autoencoder (SA-AVAE). Our framework integrates adversarial and variational learning to effectively disentangle the latent features from both modalities. Specifically, we decompose the latent space into modality-specific distinct codes and shared codes to represent complementary and common information across modalities, respectively. To enhance the disentanglement, we introduce cross-reconstruction and shared-distinct distance ratio loss as regularization terms. Importantly, we incorporate sex information into the learned latent code, enabling the model to capture sex-specific aging patterns for brain age estimation via an integrated regressor module. We evaluate our model using the publicly available OpenBHB dataset, a comprehensive multi-site dataset for brain age estimation. Several ablation studies and comparisons with state-of-the-art methods demonstrate that our framework outperforms existing approaches and shows significant robustness across various age groups, highlighting its potential for real-time clinical applications in the early detection of neurodegenerative diseases.
Citation
A.U. Rehman, A. Rehman, M.U. Farooq, T. Lee, T.M. Khan, I. Razzak , et al., "SA-AVAE: A Sex-Aware Adversarial Variational Autoencoder Network for Biological Brain Age Estimation in IoMT-Enabled Multimodal Neuroimages," Internet of Things, vol. 37, pp. 101893-101893, 2026, https://doi.org/10.1016/j.iot.2026.101893.
Source
Internet of Things
Conference
Keywords
46 Information and Computing Sciences, 4611 Machine Learning, 3 Good Health and Well Being
Subjects
Source
Publisher
Elsevier