Real-time topology-aware M-mode OCT segmentation for robotic deep anterior lamellar keratoplasty (DALK) guidance

TL;DR

This paper introduces a real-time, topology-aware OCT segmentation system for robotic eye surgery that stabilizes boundary detection under noisy conditions, enabling effective guidance at over 80 Hz.

Contribution

A novel lightweight segmentation pipeline based on UNeXt with topology regularization for stable, real-time intraoperative OCT imaging in DALK procedures.

Findings

Achieves over 80 Hz processing speed on a single GPU.

Improves boundary stability compared to topology-agnostic methods.

Maintains real-time performance while enhancing segmentation robustness.

Abstract

Robotic deep anterior lamellar keratoplasty (DALK) requires accurate real time depth feedback to approach Descemet's membrane (DM) without perforation. M-mode intraoperative optical coherence tomography (OCT) provides high temporal resolution depth traces, but speckle noise, attenuation, and instrument induced shadowing often result in discontinuous or ambiguous layer interfaces that challenge anatomically consistent segmentation at deployment frame rates. We present a lightweight, topology aware M-mode segmentation pipeline based on UNeXt that incorporates anatomical topology regularization to stabilize boundary continuity and layer ordering under low signal to noise ratio conditions. The proposed system achieves end to end throughput exceeding 80 Hz measured over the complete preprocessing inference overlay pipeline on a single GPU, demonstrating practical real time guidance beyond model only timing. This operating margin provides temporal headroom to reject low quality or dropout frames while maintaining a stable effective depth update rate. Evaluation on a standard rabbit eye M-mode dataset using an established baseline protocol shows improved qualitative boundary stability compared with topology agnostic controls, while preserving deployable real time performance.