Accuracy of Optical Coherence Tomography Denoising Across 281 Trials

Abstract

Despite sustained attention from the research community, optical coherence tomography denoising remains difficult to study outside well-funded laboratories. We introduce a transformer-based framework and benchmark it against established baselines across 1362 trials. Our measurements agree with theoretical predictions to within 24%, resolving an open discrepancy in the literature. We discuss limitations and outline directions for follow-up work at the undergraduate level.