Unsupervised identification of surgical robotic actions from small non homogeneous datasets
This addresses the need for performance assessment and modeling in surgery, but it is incremental as it focuses on a specific training task with limited data.
The paper tackles the problem of automatically identifying surgical actions in robot-assisted surgery without manual annotations, achieving a 58% F1-score on a non-expert dataset, significantly outperforming the state-of-the-art at 24%.
Robot-assisted surgery is an established clinical practice. The automatic identification of surgical actions is needed for a range of applications, including performance assessment of trainees and surgical process modeling for autonomous execution and monitoring. However, supervised action identification is not feasible, due to the burden of manually annotating recordings of potentially complex and long surgical executions. Moreover, often few example executions of a surgical procedure can be recorded. This paper proposes a novel fast algorithm for unsupervised identification of surgical actions in a standard surgical training task, the ring transfer, executed with da Vinci Research Kit. Exploiting kinematic and semantic visual features automatically extracted from a very limited dataset of executions, we are able to significantly outperform state-of-the-art results on a dataset of non-expert executions (58\% vs. 24\% F1-score), and improve performance in the presence of noise, short actions and non-homogeneous workflows, i.e. non repetitive action sequences.