Reproduce “Anatomy Might Be All You Need: Forecasting What to Do During Surgery” 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

Gary Sarwin, Alessandro Carretta, Victor Staartjes, Matteo Zoli, Diego Mazzatenta, Luca Regli, Carlo Serra, Ender Konukoglu

The authors forecast an instrument’s future movement in pituitary-surgery video from recent detections of the instrument and surrounding anatomy. A temporal model predicts bounding-box changes over 8 or 16 frames. At 8 frames, four-direction accuracy is 60.58% with anatomy and 50.71% with instrument detections alone, excluding movements below 0.1; this is direction classification, not exact-location accuracy.

Summary by alphaXiv.

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