FUN-SIS: a Fully UNsupervised approach for Surgical Instrument Segmentation

TL;DR

FUN-SIS introduces a fully unsupervised method for surgical instrument segmentation in endoscopic videos, relying on motion cues and shape priors, eliminating the need for manual annotations and achieving near state-of-the-art accuracy.

Contribution

The paper presents a novel generative-adversarial framework and a learning-from-noisy-labels architecture for unsupervised surgical instrument segmentation, leveraging shape priors from existing datasets.

Findings

Achieves segmentation accuracy close to supervised methods.

Effectively utilizes unlabelled videos and shape priors.

Validates on multiple surgical datasets, including MICCAI 2017.

Abstract

Automatic surgical instrument segmentation of endoscopic images is a crucial building block of many computer-assistance applications for minimally invasive surgery. So far, state-of-the-art approaches completely rely on the availability of a ground-truth supervision signal, obtained via manual annotation, thus expensive to collect at large scale. In this paper, we present FUN-SIS, a Fully-UNsupervised approach for binary Surgical Instrument Segmentation. FUN-SIS trains a per-frame segmentation model on completely unlabelled endoscopic videos, by solely relying on implicit motion information and instrument shape-priors. We define shape-priors as realistic segmentation masks of the instruments, not necessarily coming from the same dataset/domain as the videos. The shape-priors can be collected in various and convenient ways, such as recycling existing annotations from other datasets. We leverage them as part of a novel generative-adversarial approach, allowing to perform unsupervised instrument segmentation of optical-flow images during training. We then use the obtained instrument masks as pseudo-labels in order to train a per-frame segmentation model; to this aim, we develop a learning-from-noisy-labels architecture, designed to extract a clean supervision signal from these pseudo-labels, leveraging their peculiar noise properties. We validate the proposed contributions on three surgical datasets, including the MICCAI 2017 EndoVis Robotic Instrument Segmentation Challenge dataset. The obtained fully-unsupervised results for surgical instrument segmentation are almost on par with the ones of fully-supervised state-of-the-art approaches. This suggests the tremendous potential of the proposed method to leverage the great amount of unlabelled data produced in the context of minimally invasive surgery.