Reproduce “Differentiable Inverse Rendering Recovers Intrinsic Properties from Intravascular Optical Coherence Tomography” 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

Ajay Manicka, Karim Kadry, Sebastian Ruiz-Lopera, Maryam Alsharqi, Sanjana Arji, Samuel Ruiperez-Campillo, Nestor Uribe-Patarroyo, Brett E. Bouma and 2 more

The authors recover per-pixel optical attenuation coefficients from one OCT B-scan by optimizing a differentiable forward model, without training data. In phantoms, attenuation tracked intralipid concentration with a slope of 0.663 mm⁻¹ per percentage point (R² = 0.990), versus 0.623 for curve-fitting. Applied to 29,269 clinical frames, the method showed transfer and relative contrast, not absolute clinical accuracy.

Summary by alphaXiv.

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