ToothFairy2: Multi-Structure Segmentation in CBCT Volumes Banner
Join

Challenge Publication

All the Final Phase submission team members qualify as authors of the challenge. A paper resuming challenge results and including descriptions of the best proposals will be published after the challenge: at most two authors for each team may be eligible as authors of this paper.

All the participants are allowed to submit their own results in any venue (conferences, workshops, etc) with an embargo restriction of 6 months after the MICCAI2024 event. An exception is given for the challenge workshop proceedings: please refer to our call for papers.  

Call for Papers

We invite all the challenge participants to submit their submission descriptive document also as a full paper of our MICCAI workshop @MICCAI 2024.

The event, Supervised and Semi-supervised Multi-Structure Segmentation and Landmark Detection in Dental Data, host three MICCAI 2024 challenges: 

You can submit your work if you successfully participate in any of these three challenges. Moreover, any paper related to the topic covered by the challenges is more than welcome!

Submission Guidelines

Submission Site: https://openreview.net/group?id=MICCAI.org/2024/Workshop/ToothFairy

Important Dates: All submissions will be handled electronically via the workshop's OpenReview Website. The submission deadline is TO BE DEFINED. The decision to authors will be released on TO BE DEFINED.

Paper Format: Submitted papers (.pdf format) must use the Springer LNCS Latex Template. Please remember to add an abbreviated paper Title and Authors. Authors are prohibited from modifying the templates. We are concerned about modifications to margins, line spacing, font type, and font size of the paper only. If an author wishes to use other packages, the author must ensure the additional package does not alter the template.

Length: Papers should be at least 8 pages, including all text and figures. There is no limit to the pages of references.

Review Process: Our review process is single-blind, meaning that reviewers will know the identities of the authors, but authors will not know the identities of the reviewers.