Reproduce “SuPRA: Surgical Phase Recognition and Anticipation for Intra-Operative Planning” 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

Maxence Boels, Yang Liu, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin

SuPRA makes video analysis jointly perform current-phase recognition and predict upcoming phase segments. It encodes video frames in temporal windows, compresses observed features with max-pooling, and uses learned queries to classify future phases and estimate their durations. On AutoLaparo21, it achieves 66.1% accuracy for next-phase prediction, versus SKiT’s 60.2%; this is a benchmark result, not evidence of clinical benefit.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.