Unsupervised anomaly detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS)using a deep residual autoencoder

TL;DR

This paper presents an unsupervised deep residual autoencoder approach for real-time anomaly detection in robotic-assisted surgery, achieving high precision and recall on surgical datasets, facilitating autonomous surgical systems.

Contribution

It introduces a novel unsupervised anomaly detection method using deep residual autoencoders for robotic surgery, enabling real-time detection without requiring extensive abnormal data.

Findings

Achieved 78.4% recall and 91.5% precision on Cholec80 dataset.

Achieved 95.6% recall and 88.1% precision on SARAS phantom dataset.

System processes frames in about 25 ms for real-time application.

Abstract

Anomaly detection in Minimally-Invasive Surgery (MIS) traditionally requires a human expert monitoring the procedure from a console. Data scarcity, on the other hand, hinders what would be a desirable migration towards autonomous robotic-assisted surgical systems. Automated anomaly detection systems in this area typically rely on classical supervised learning. Anomalous events in a surgical setting, however, are rare, making it difficult to capture data to train a detection model in a supervised fashion. In this work we thus propose an unsupervised approach to anomaly detection for robotic-assisted surgery based on deep residual autoencoders. The idea is to make the autoencoder learn the 'normal' distribution of the data and detect abnormal events deviating from this distribution by measuring the reconstruction error. The model is trained and validated upon both the publicly available Cholec80 dataset, provided with extra annotation, and on a set of videos captured on procedures using artificial anatomies ('phantoms') produced as part of the Smart Autonomous Robotic Assistant Surgeon (SARAS) project. The system achieves recall and precision equal to 78.4%, 91.5%, respectively, on Cholec80 and of 95.6%, 88.1% on the SARAS phantom dataset. The end-to-end system was developed and deployed as part of the SARAS demonstration platform for real-time anomaly detection with a processing time of about 25 ms per frame.