SegMatch: semi-supervised surgical instrument segmentation
Open Access
- 23 April 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-17
Abstract
Surgical instrument segmentation is recognised as a key enabler in providing advanced surgical assistance and improving computer-assisted interventions. In this work, we propose SegMatch, a semi-supervised learning method to reduce the need for expensive annotation for laparoscopic and robotic surgical images. SegMatch builds on FixMatch, a widespread semi-supervised classification pipeline combining consistency regularization and pseudo-labelling, and adapts it for the purpose of segmentation. In our proposed SegMatch, the unlabelled images are first weakly augmented and fed to the segmentation model to generate pseudo-labels. In parallel, images are fed to a strong augmentation branch and consistency between the branches is used as an unsupervised loss. To increase the relevance of our strong augmentations, we depart from using only handcrafted augmentations and introduce a trainable adversarial augmentation strategy. Our FixMatch adaptation for segmentation tasks further includes carefully considering the equivariance and invariance properties of the augmentation functions we rely on. For binary segmentation tasks, our algorithm was evaluated on the MICCAI Instrument Segmentation Challenge datasets, Robust-MIS 2019 and EndoVis 2017. For multi-class segmentation tasks, we relied on the recent CholecInstanceSeg dataset. Our results show that SegMatch outperforms fully-supervised approaches by incorporating unlabelled data, and surpasses a range of state-of-the-art semi-supervised models across different labelled to unlabelled data ratios.Keywords
All Related Versions
Funding Information
- EPSRC Centre for Doctoral Training in Smart Medical Imaging at King’s College London and Imperial College London (EP/S022104/1)
- Wellcome Trust / EPSRC (WT203148/Z/16/Z; NS/A000049/1)
- Medtronic / RAEng Research Chair (RCSRF1819\7\34)
This publication has 38 references indexed in Scilit:
- Scalable Joint Detection and Segmentation of Surgical Instruments with Weak Supervision2021
- Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation2020
- ISINet: An Instance-Based Approach for Surgical Instrument Segmentation2020
- Unsupervised Surgical Instrument Segmentation via Anchor Generation and Semantic Diffusion2020
- Learning Motion Flows for Semi-supervised Instrument Segmentation from Robotic Surgical Video2020
- Learning Where to Look While Tracking Instruments in Robot-Assisted Surgery2019
- Incorporating Temporal Prior from Motion Flow for Instrument Segmentation in Minimally Invasive Surgery Video2019
- Deep Co-Training for Semi-Supervised Image Recognition2018
- Augmenting Image Classifiers Using Data Augmentation Generative Adversarial Networks2018
- Concurrent Segmentation and Localization for Tracking of Surgical Instruments2017