Part of the Endoscopic Vision Challenge


Detecting the surgical workflow online during a minimally invasive surgery has many applications, from surgeon skill evaluation and report generation to automatic triggering of actions in the OR. There exist many approaches that can detect the current workflow phase based on instruments in use, but this data usually requires unreliable, additional sensors, while laparoscopic or endoscopic video is always available in high quality.

In this sub-challenge, the focus is on the online-detection of surgical workflow directly from video data. Participants should pay attention not to take "future" information into account, as the evaluation will have incomplete datasets, simulating an ongoing surgery.

There is inherently a strong correlation between this sub-challenge and the instrument detection challenge. We do provide simple information about the instrument usage, so approaches for instrument detection should be easily adopted to this problem.