Seeing Beyond the Airways: Asthma Prediction via Cross-Attention on Dual Retinal Modalities
Farooq, Umar Trinh, Matt Ly, Angelica Ameer, Asif Razzak, Imran Singh, Sonit
Farooq, Umar
Trinh, Matt
Ly, Angelica
Ameer, Asif
Razzak, Imran
Singh, Sonit
Supervisor
Department
Computational Biology
Embargo End Date
Type
Conference proceeding
Date
License
Language
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Asthma's systemic effects and chronic underdiagnosis trigger avoidable exacerbations and a heavy healthcare burden. Effort-dependent spirometry and specialist-only tests block population-scale screening. We propose a cross-modal attention framework for non-invasive asthma classification from dual retinal modalities, colour fundus photographs (CFP; Type 1: posterior pole view; Type 2: optic nerve head view) and optical coherence tomography (OCT) measurements, where systemic changes manifest in retinal structure and vasculature. Fundus images are encoded by a CNN backbone followed by multi-head self-attention (MHSA); OCT metrics are embedded by a lightweight feed-forward encoder; cross-modal attention (CMA) then fuses the two streams to capture intermodal dependencies. Trained and evaluated on a novel dual-modality dataset curated at UNSW Centre for Eye Health (CFEH), the model achieves an AUC of 0.97 and offers improved interpretability via attention-weight visualisations. These results support retinal biomarkers as a scalable pathway for early asthma detection and open a window to population-level oculomic screening for other systemic diseases (e.g., neurodegenerative and cardiovascular diseases), highlighting the promise of CMA for ocular imaging.
Citation
U. Farooq, M. Trinh, A. Ly, A. Ameer, I. Razzak, S. Singh, "Seeing Beyond the Airways: Asthma Prediction via Cross-Attention on Dual Retinal Modalities," 2025, pp. 1-6.
Source
Proceeding of 40th International Conference on Image and Vision Computing New Zealand (IVCNZ)
Conference
2025 40th International Conference on Image and Vision Computing New Zealand (IVCNZ)
Keywords
32 Biomedical and Clinical Sciences, 3212 Ophthalmology and Optometry, 3 Good Health and Well Being
Subjects
Source
2025 40th International Conference on Image and Vision Computing New Zealand (IVCNZ)
Publisher
IEEE