Large-vocabulary segmentation for medical images with text prompts.

ABSTRACT: This paper aims to build a model that can Segment Anything in 3D medical images, driven by medical terminologies as Text prompts, termed as SAT. Our main contributions are three-fold: (i) We construct the first multimodal knowledge tree on human anatomy, including 6502 anatomical terminologies; Then, we build the largest and most comprehensive segmentation dataset for training, collecting over 22K 3D scans from 72 datasets, across 497 classes, with careful standardization on both image and label space; (ii) We propose to inject medical knowledge into a text encoder via contrastive learning and formulate a large-vocabulary segmentation model that can be prompted by medical terminologies in text form. (iii) We train SAT-Nano (110M parameters) and SAT-Pro (447M parameters). SAT-Pro achieves c

SUBMITTER: Zhao Z 

PROVIDER: S-EPMC12405521 | biostudies-literature | 2025 Sep

REPOSITORIES: biostudies-literature