Comparative evaluation of instrument segmentation and tracking methods in minimally invasive surgery

TL;DR

This study compares various vision-based instrument segmentation and tracking methods in minimally invasive surgery, highlighting the superiority of deep learning approaches and the benefits of combining multiple methods, while also identifying ongoing challenges.

Contribution

The paper introduces a comprehensive validation dataset and provides a comparative analysis of different segmentation and tracking methods in surgical imaging.

Findings

Deep learning methods outperform traditional approaches in segmentation accuracy.

Combining multiple methods significantly improves segmentation results.

Instrument tracking remains challenging in complex surgical scenarios.

Abstract

Intraoperative segmentation and tracking of minimally invasive instruments is a prerequisite for computer- and robotic-assisted surgery. Since additional hardware like tracking systems or the robot encoders are cumbersome and lack accuracy, surgical vision is evolving as promising techniques to segment and track the instruments using only the endoscopic images. However, what is missing so far are common image data sets for consistent evaluation and benchmarking of algorithms against each other. The paper presents a comparative validation study of different vision-based methods for instrument segmentation and tracking in the context of robotic as well as conventional laparoscopic surgery. The contribution of the paper is twofold: we introduce a comprehensive validation data set that was provided to the study participants and present the results of the comparative validation study. Based on the results of the validation study, we arrive at the conclusion that modern deep learning approaches outperform other methods in instrument segmentation tasks, but the results are still not perfect. Furthermore, we show that merging results from different methods actually significantly increases accuracy in comparison to the best stand-alone method. On the other hand, the results of the instrument tracking task show that this is still an open challenge, especially during challenging scenarios in conventional laparoscopic surgery.