Скачать или смотреть MICCAI Industrial Talk: Unifying Biomedical Segmentation Tasks with Language

MICCAI Industrial Talk Series @ August 12, 2025, by Dr. Theodore Zhao from Microsoft

Speaker: Theodore Zhao, PhD, Senior Applied Scientist, Microsoft Health and Life Sciences Research

Abstract: Biomedical image analysis is fundamental for biomedical discovery. Recent advances in biomedical foundation models unlocked the possibility to unify biomedical image segmentation tasks across different imaging modalities and anatomies. This joint learning improves the accuracy for individual tasks and enables new applications through natural language prompting.

We first overview BiomedParse as an all-in-one tool for biomedical image analysis on all major image modalities, and discuss the remaining challenges. We then move on to techniques to tackle challenges such as small objects localization using Boltzmann attention sampling, as well as optimization for 3D segmentation tasks.

Bio: Dr. Theodore Zhao is a Senior Applied Scientist at Microsoft Health and Life Sciences Research, working on multimodal biomedical imaging models as well as biomedical natural language processing. Theodore earned his PhD in Applied Mathematics degree from University of Washington, where his research applied machine learning, stochastic modeling and optimization to applications in finance and healthcare. His research interests focus on machine learning, self-supervised learning, multimodal models, and stochastic modeling.