Reproduce “Topology-Informed Prompt-Conditioned Universal Segmentation of Uterine Structures from Ultrasound and MRI” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yongheng Sun, Yuexi Gu, Jingwen Sun, Maureen Kohi, Mingxia Liu
TPUS tests joint segmentation of uterine ultrasound and MRI, using modality-specific stems, a shared core, class prompts, and topology-informed training for datasets with different label spaces. On held-out UMD MRI cases, it reports macro-averaged Dice of 0.693±0.254, versus 0.680±0.257 for MultiTalent. Evaluation covers only one ultrasound and one MRI dataset.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.