Single- and Multi-Task Architectures for Tool Presence Detection Challenge at M2CAI 2016

TL;DR

This paper compares single- and multi-task deep learning architectures for detecting surgical tools in laparoscopic videos, highlighting the importance of larger datasets for significant performance improvements.

Contribution

It introduces and evaluates single- and multi-task deep architectures for tool detection in surgical videos, emphasizing the need for more data to enhance results.

Findings

Multi-task architecture slightly improves detection accuracy.

More training data leads to significant performance gains.

Call for increased dataset sharing in the surgical community.

Abstract

The tool presence detection challenge at M2CAI 2016 consists of identifying the presence/absence of seven surgical tools in the images of cholecystectomy videos. Here, we propose to use deep architectures that are based on our previous work where we presented several architectures to perform multiple recognition tasks on laparoscopic videos. In this technical report, we present the tool presence detection results using two architectures: (1) a single-task architecture designed to perform solely the tool presence detection task and (2) a multi-task architecture designed to perform jointly phase recognition and tool presence detection. The results show that the multi-task network only slightly improves the tool presence detection results. In constrast, a significant improvement is obtained when there are more data available to train the networks. This significant improvement can be regarded as a call for action for other institutions to start working toward publishing more datasets into the community, so that better models could be generated to perform the task.