Fakrul Islam Tushar, PhD
Dr. Tushar directs the Tushar Lab, a newly established research group advancing data-centric AI for health care and medicine through data discovery, intelligent tools and the integration of clinical, simulated and synthetic datasets. His work spans large-scale data curation using weak supervision and human-AI collaboration, virtual imaging trials for reproducible in-silico evaluation and generative modeling for synthetic medical image creation. The lab’s overarching goal is to develop trustworthy, rigorously evaluated and clinically grounded AI systems for health care and medical imaging.
Dr. Tushar’s research has been published in leading venues including Medical Image Analysis, Radiology: Artificial Intelligence, SPIE Journal of Medical Imaging, and Artificial Intelligence in Medicine, with presentations at RSNA and SPIE Medical Imaging. He is committed to open and reproducible science; his toolkits, datasets and benchmarking resources are publicly available through his GitHub and lab website.
Prior to joining the University of Arizona, Dr. Tushar conducted research in health AI and generative AI at the Center for Virtual Imaging Trials (CVIT) at Duke University. Before his time at CVIT, he served as a research associate at Duke University Medical Center from 2019 to 2021, where he contributed to interdisciplinary projects at the intersection of medical imaging and computational modeling.
Degrees
- PhD: Electrical and Computer Engineering, Duke University, 2025
- MSc: Medical Imaging and Applications (Erasmus Mundus), University of Girona, Spain, 2019
- BSc: Electrical and Electronic Engineering, American International University-Bangladesh, Dhaka, 2017
data-centric AI and weak supervision, trustworthy AI evaluation for medical imaging, foundation model benchmarking, virtual imaging trials and in silico evaluation, generative AI and medical image synthesis