Reproduce “Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Model” 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
Moein Heidari, Alvin Kimbowa, Mahdi Tabatabaei, Afshin Bozorgpour, Sina Ghorbani Kolahi, River Jiang, Wenjin Chen, David J. Foran and 3 more
P2Echo unifies echocardiography segmentation across views by conditioning decoding on text specifying the view and target structure. Its DyITA module injects this guidance through decoder stages using dynamic projections and a differential operation. It achieves 96.94% mDice on internal 2CH testing, versus EchoONE’s 91.69%, and 82.22% on held-out HMC_QU, versus SAMUS’s 61.93%; results do not establish performance on unseen views or clinical outcomes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.