Reproduce “Label-Free Deep-Tissue Peripheral Nerve Detection with a Handheld Multimodal OCT Probe and NerveDetNet” 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
Yihan Wang, Ruilin You, Shaobai Li, Jiabin Chen, Bofan Song, Anh D. Le, Rongguang Liang
A framework combining a handheld multimodal Optical Coherence Tomography (OCT) probe with NerveDetNet, a 2.5D segmentation network, enables label-free, depth-resolved detection of peripheral nerves buried up to 1.4 mm beneath intact tissue. This system provides real-time, subsurface localization of nerves, relying on intrinsic intensity-based OCT structural signatures without exogenous labels.
Key insights
- Peripheral nerves possess intrinsic intensity-based OCT structural signatures, known as "Bands of Fontana," which provide consistent, depth-penetrable contrast for label-free detection beneath intact tissue.
- The Nerve Feature Correlation Module (NFCM) within NerveDetNet effectively utilizes spatial, frame-order, and shift-tolerant correlations across sparse OCT B-scans to enhance nerve localization accuracy.
- A lightweight 2.5D segmentation network, with specialized cross-frame cue integration, can efficiently achieve high accuracy in detecting attenuated and displaced nerve signals in sparsely sampled volumes, suitable for real-time surgical guidance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.