Selected work
Publications
A record of published and accepted work, followed by current manuscripts and research directions.
Published Work
Published · 2026-07-05
Fairness in federated medical imaging: a systematic review through the dual fairness lens
Artificial Intelligence Review · 2026-07-05 · Journal article
A systematic review that studies collaboration fairness across institutions and group fairness across patient populations as two connected dimensions of fairness in federated medical imaging.
Published · 2025-12-25
MedLiteNet: Lightweight Hybrid Medical Image Segmentation Model for the Medical Internet of Things (MIoT)
IEEE Journal of Selected Areas in Sensors · 2026 · Journal article · Publication date: 2025-12-25
A lightweight hybrid CNN–Transformer model for medical image segmentation, representing my earlier work in efficient and deployable medical AI.
Current Work
In progress
HD-Cal: Few-Shot Reliability Estimation for Cross-Domain Hallucination Heterogeneity in Chest X-Ray Vision-Language Models
Medical vision-language models · reliability audit · cross-domain evaluation
A deployment-oriented reliability audit that examines how hallucination and error behaviour varies across chest X-ray domains and findings, and estimates localized reliability with few-shot target-domain information.
Planned direction
Context-adjusted fair deferral
Reliability–fairness bridge · future method work
A future direction for separating finding difficulty from demographic under-service, so that deployment-time deferral can respond to genuine unreliability without shifting burden unfairly across groups.