The TUM LapChole dataset for the M2CAI 2016 workflow challenge
This dataset addresses the need for standardized data in surgical workflow analysis for the medical AI community, but it is incremental as it builds upon existing datasets and challenges.
The authors introduced the TUM LapChole dataset, comprising 20 annotated laparoscopic cholecystectomy videos for surgical phase detection, with 15 videos for training and 5 for testing, which was used in the M2CAI 2016 challenge.
In this technical report we present our collected dataset of laparoscopic cholecystectomies (LapChole). Laparoscopic videos of a total of 20 surgeries were recorded and annotated with surgical phase labels, of which 15 were randomly pre-determined as training data, while the remaining 5 videos are selected as test data. This dataset was later included as part of the M2CAI 2016 workflow detection challenge during MICCAI 2016 in Athens.