Healthcare Domains

The translational nature of my AI research is grounded through close partnerships with clinical domain experts. I have built four active research pillars and am actively expanding. Below are some of the selected publications for the four themes. D. Mehta* corresponds to corresponding/first author.

AI for Neurology

Epilepsy management, Stroke outcome prediction, Parkinson’s assessment, and Multiple Sclerosis survival analysis. Developed with clinical partners at Monash, Alfred Health, and internationally.

"Development and validation of clinico-imaging machine learning and deep learning models to predict responses to initial antiseizure medications in epilepsy" — Nazem-Zadeh M., Chang R., Barnard S., Pardoe H., Kuzniecky R., Mishra D., Kamkar H., Nhu D.,D. Mehta, ..., Kwan P. — Epilepsia 2026

"A Clinical Guideline-Grounded Hybrid Agentic Framework for Holistic Epilepsy Management" — Pham K., Giritharan D., Guilherme C., Vo Qouc B., Verspoor K., Law M., Kwan P., Ge Z., D. Mehta* — MICCAI 2026

"Multimodal CT Perfusion–Based Deep Learning for Predicting Stroke Lesion Outcomes in Complete and No Recanalization Scenarios" — Yang H., George Y., D. Mehta, et al. — American Journal of Neuroradiology 2025

"Adaptive transformer modelling of density function for nonparametric survival analysis" — Zhang X., D. Mehta, et al. — Machine Learning 2025

"Towards automated and marker-less Parkinson disease assessment: predicting UPDRS scores" — D. Mehta* et al. — CVPR 2021

AI for Dermatology

Trustworthy and clinically deployed AI for skin lesion analysis. Developed in collaboration with Alfred Health, University of Queensland, Koita Center of Digital Health (India), and Molemap Pty. Ltd.

"Multi-task AI models in dermatology: Overcoming critical clinical translation challenges for enhanced skin lesion diagnosis" — D. Mehta*, et al. — Journal of the European Academy of Dermatology and Venerology (JEADV) 2025

"Assessment of image quality on the diagnostic performance of clinicians and deep learning models: Cross-sectional comparative reader study" — Oloruntoba A.I., Asghari-Jafarabadi M., Sashindranath M., Ingvar Å., ...D. Mehta, ..., Soyer H.P., Mar V.et al. — Journal of the European Academy of Dermatology and Venerology (JEADV) 2025

"Out-of-Distribution Detection for Long-Tailed and Fine-Grained Skin Lesion Images" — D. Mehta* et al. — MICCAI 2022 ⭐ (Early accept)

AI for Opthalmology

AI systems for automated analysis of retinal images for eye disease detection. Developed with Optain Health Pty. Ltd.

"Interpretable Few-Shot Retinal Disease Diagnosis with Concept-Guided Prompting" — D. Mehta* et al. — IPMI 2025

"Automated Quantification of Lens Cortex and Nuclear Opacity Based on Swept-Source Anterior Segment Optical Coherence Tomography" — Han X., Zhang X., ...D. Mehta et al. — Journal of Refractive Surgery 2025

AI for Histopathology Analysis

AI systems for automated analysis of whole slide images to support oncology and tissue pathology workflows. Developed with Australian Institute of Health Innovation at Macquire University

"TPMIL: Trainable Prototype Enhanced Multiple Instance Learning for Whole Slide Image Classification" — Yang L., D. Mehta* et al. — MIDL 2024

AI for Cardiology Expanding — Seeking Partnerships

I am actively looking for clinical collaborators in cardiology to develop and translate AI tools for cardiac disease management.

AI for Human Kinetics & Wearables Expanding — Seeking Partnerships

Interested in partnerships exploring wearable sensor data and human movement analytics for clinical applications.

Interested in a clinical collaboration? Get in touch → · ← Back to Research