EPSCoR Research Fellows: NSF: Cost-Effective AI for Image Analysis

About This Grant

This Research Infrastructure Improvement EPSCoR Research Fellows project provides a fellowship to an assistant professor and training for a graduate student at the University of Louisiana at Lafayette (UL Lafayette). This work is conducted in collaboration with researchers at Massachusetts Eye and Ear Hospital. Through the fellowship, the principal investigator will conduct basic research in Artificial Intelligence (AI), motivated by the challenges associated with constructing AI models to detect glaucoma using low-cost smartphone-based fundus images of the eye. The project integrates computer science, AI, and ophthalmology, proposing multi-domain meta-learning and domain-calibrated co-learning frameworks that adapt hospital-grade images to enhance performance in smartphone-acquired images. This award will provide research results that can be used to broaden access to glaucoma screening, help alleviate healthcare costs associated with late-stage glaucoma diagnosis, and strengthen research and educational programs at UL Lafayette. It will also provide hands-on training for graduate students in AI for healthcare applications. This project will conduct research on the challenges associated with developing cost-effective Artificial Intelligence (AI) models for image analysis. It will introduce novel multi-domain joint meta-learning and domain-calibrated co-learning frameworks to enhance the accuracy of AI models trained on low-quality image data. A focal example is the type of analysis needed for glaucoma detection using fundus eye photos acquired with smartphone devices. The AI models will be tested by using high-quality hospital-grade images to guide training on limited smartphone images, addressing challenges related to data scarcity and domain shift. The project will enhance research infrastructure at UL Lafayette by supporting faculty advancement in AI for healthcare, establishing a new research direction in cost-effective AI for healthcare, and providing hands-on training opportunities for graduate students. Research activities will facilitate clinical collaboration with researchers at the Massachusetts Eye and Ear Hospital, promote student participation in interdisciplinary research, and support the development of new curriculum in medical AI. The fellowship will strengthen institutional capacity for healthcare-focused computing research and contribute to workforce development in AI and biomedicine. This project is supported by the EPSCoR Research Infrastructure Improvement Program: EPSCoR Research Fellows, which supports early- and mid-career investigators in eligible jurisdictions to develop collaborations at the nation’s private, government or academic research institutions. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.