Surgical Workflow Recognition: from Analysis of Challenges to Architectural Study
This work provides a fair comparison of methods for surgical workflow recognition, which is incremental as it focuses on transferring existing approaches rather than introducing new ones.
The study evaluated combinations of model architectures for surgical workflow recognition in both laparoscopic and operating room settings, showing that methods designed for internal analysis can be transferred to external tasks with comparable performance gains.
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.