Endoscopic surgical tool localization using tool presence labels Banner
Join

**The training data corresponding to this challenge has been released with the 2022 challenge publication (https://arxiv.org/pdf/2305.07152.pdf) and is free for use with proper citation**


**This Challenge has ended and is NO LONGER accepting applications. Please be on a lookout here for next year's challenge website.**


Surgical Tool Localization in endoscopic videos



News:

  • 8th October, 2023: Challenge concluded and results announced
  • 23rd September, 2023: Submission phase ended
  • 29th August, 2023: Final testing phase open
  • 3rd July, 2023: Preliminary testing phase open
  • 1st May, 2023: Challenge is live and accepting applications


Overview:
The ability to automatically detect and track surgical instruments in endoscopic video will enable many transformational interventions. Assessing surgical performance and efficiency, identifying skilled tool use and choreography, and planning operational and logistical aspects of OR resources are just some of the applications that would benefit. The annotations needed to train machine learning models to robustly identify and localize surgical tools, however, are difficult to obtain. Annotating bounding boxes frame-by-frame in video is tedious and time consuming, yet a wide variety of surgical tools and surgeries must be captured for robust training. Moreover, ongoing annotator training is needed to stay up to date with surgical instrument innovation. In robot-assisted surgery, potentially informative data like timestamps of instrument installation and removal, can be programmatically harvested. The ability to use only tool presence labels to localize tools would significantly reduce the annotation workload needed to train robust tool detection, localization, and tracking models. In this challenge, we invite the surgical data science community to leverage tool presence data as weak labels to train machine learning models to localize and classify tools with bounding boxes in video frames.
This challenge will take place as part of EndoVis challenge at MICCAI 2023 in Vancouver, Canada!
(Note: This year's challenge is a repeat of the SurgToolLoc 2022 challenge (which was also held as part of EndoVis at MICCAI 2022). Please check out 2022 challenge's website for more details at https://surgtoolloc.grand-challenge.org/)


Prizes:

Top performing teams will be awarded cash prizes of up to $6,000. See the prizes page for more details.


Interested in participating in the challenge? Check out the getting started page!


For any questions, please post it on the forum or use the contact us page to email direct queries.