Neel Dey is an Instructor at the A. A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, and Harvard Medical School. He is broadly interested in building robust machine learning methods to analyze biomedical images, with a particular emphasis on approaches for automatic generalization to unseen datasets and messy clinical contexts. He was previously a postdoctoral associate at MIT CSAIL and received his Ph.D. in Computer Science from NYU.
Education
Ph.D.
Select Publications
Dey, N., Billot, B., Wong, H.E., Wang, C.J., Ren, M., Grant, P.E., Dalca, A.V. and Golland, P., 2025. Learning
General-Purpose Biomedical Volume Representations using Randomized Synthesis. International Conference on Learning Representations (ICLR).
Elaldi, A., Gerig, G. and Dey, N., 2024. Equivariant spatio-hemispherical networks for diffusion MRI
deconvolution. Advances in Neural Information Processing Systems (NeurIPS).
Dey, N., Abulnaga, M., Billot, B., Turk, E.A., Grant, E., Dalca, A.V. and Golland, P., 2024. AnyStar: Domain
randomized universal star-convex 3D instance segmentation. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
Highlights
– Received nine Outstanding Reviewer (or equivalent) awards from major conferences
– Pearl Brownstein Doctoral Research Award from NYU CSE for “doctoral research which shows the greatest promise” (equivalent to best departmental Ph.D. thesis)
– Deborah Rosenthal, MD Award for “Outstanding Performance on the Ph.D. Qualifying Exam” (given to 1–2 qualifying students each year in NYU CSE)
Associated Labs
Laboratory for Computational Neuroimaging