Surgical Workflow Recognition: from Analysis of Challenges to Architectural Study

TL;DR

This paper evaluates various model architectures for surgical workflow recognition, comparing internal and external analysis methods, and demonstrates the transferability of internal analysis models to external tasks with comparable improvements.

Contribution

It provides a comprehensive comparison of different architectures for both internal and external surgical workflow recognition, highlighting the transferability of internal models to external analysis.

Findings

Internal analysis models can be adapted for external recognition with similar performance gains.

Different model architectures show comparable effectiveness across tasks.

The study offers a fair comparison framework for future research in surgical workflow recognition.

Abstract

Algorithmic surgical workflow recognition is an ongoing research field and can be divided into laparoscopic (Internal) and operating room (External) analysis. So far many different works for the internal analysis have been proposed with the combination of a frame-level and an additional temporal model to address the temporal ambiguities between different workflow phases. For the External recognition task, Clip-level methods are in the focus of researchers targeting the local ambiguities present in the OR scene. In this work we evaluate combinations of different model architectures for the task of surgical workflow recognition to provide a fair comparison of the methods for both Internal and External analysis. We show that methods designed for the Internal analysis can be transferred to the external task with comparable performance gains for different architectures.