Topology-based deep-learning segmentation method for deep anterior lamellar keratoplasty (DALK) surgical guidance using M-mode OCT data

TL;DR

This paper introduces a topology-based deep-learning segmentation method that enhances the accuracy, speed, and robustness of corneal layer detection in OCT data, aiding DALK surgical procedures.

Contribution

The paper presents a novel topology-aware loss function integrated into a deep-learning model, improving segmentation performance under noisy OCT signals for surgical guidance.

Findings

Outperforms traditional loss-based segmentation methods.

Provides fast and accurate corneal layer detection.

Demonstrates robustness across various datasets.

Abstract

Deep Anterior Lamellar Keratoplasty (DALK) is a partial-thickness corneal transplant procedure used to treat corneal stromal diseases. A crucial step in this procedure is the precise separation of the deep stroma from Descemet's membrane (DM) using the Big Bubble technique. To simplify the tasks of needle insertion and pneumo-dissection in this technique, we previously developed an Optical Coherence Tomography (OCT)-guided, eye-mountable robot that uses real-time tracking of corneal layers from M-mode OCT signals for control. However, signal noise and instability during manipulation of the OCT fiber sensor-integrated needle have hindered the performance of conventional deep-learning segmentation methods, resulting in rough and inaccurate detection of corneal layers. To address these challenges, we have developed a topology-based deep-learning segmentation method that integrates a topological loss function with a modified network architecture. This approach effectively reduces the effects of noise and improves segmentation speed, precision, and stability. Validation using in vivo, ex vivo, and hybrid rabbit eye datasets demonstrates that our method outperforms traditional loss-based techniques, providing fast, accurate, and robust segmentation of the epithelium and DM to guide surgery.