Pseudo-label Guided Cross-video Pixel Contrast for Robotic Surgical Scene Segmentation with Limited Annotations

TL;DR

This paper introduces PGV-CL, a semi-supervised learning method using pseudo-label guided cross-video contrast to improve surgical scene segmentation with limited annotations, outperforming existing methods.

Contribution

The paper proposes a novel pseudo-label guided cross-video contrast learning approach for semi-supervised surgical scene segmentation, effectively leveraging unlabeled data and cross-video semantics.

Findings

Outperforms state-of-the-art semi-supervised methods across different labeling ratios.

Surpasses fully supervised training on EndoVis18 with only 10.1% labeled data.

Demonstrates robustness and effectiveness on multiple surgical datasets.

Abstract

Surgical scene segmentation is fundamentally crucial for prompting cognitive assistance in robotic surgery. However, pixel-wise annotating surgical video in a frame-by-frame manner is expensive and time consuming. To greatly reduce the labeling burden, in this work, we study semi-supervised scene segmentation from robotic surgical video, which is practically essential yet rarely explored before. We consider a clinically suitable annotation situation under the equidistant sampling. We then propose PGV-CL, a novel pseudo-label guided cross-video contrast learning method to boost scene segmentation. It effectively leverages unlabeled data for a trusty and global model regularization that produces more discriminative feature representation. Concretely, for trusty representation learning, we propose to incorporate pseudo labels to instruct the pair selection, obtaining more reliable representation pairs for pixel contrast. Moreover, we expand the representation learning space from previous image-level to cross-video, which can capture the global semantics to benefit the learning process. We extensively evaluate our method on a public robotic surgery dataset EndoVis18 and a public cataract dataset CaDIS. Experimental results demonstrate the effectiveness of our method, consistently outperforming the state-of-the-art semi-supervised methods under different labeling ratios, and even surpassing fully supervised training on EndoVis18 with 10.1% labeling.