FedSurg EndoVis 2024: Challenge Subset of Appendix300
References to related material | https://doi.org/10.25532/OPARA-1173 | |
Type of the data | Dataset | |
Total size of the dataset | 892587865 | |
Author | Kirchner, Max | |
Author | Kolbinger, Fiona R | |
Author | Jenke, Alexander C | |
Author | Saldanha, Oliver L | |
Author | Pfeiffer, Kevin | |
Author | Kanjo, Weam | |
Author | Kather, Jakob N. | |
Author | Bodenstedt, Sebastian | |
Author | Speidel, Stefanie | |
Upload date | 2026-08-27T17:31:52Z | |
Publication date | 2026-08-27T17:31:52Z | |
Publication date | 2026-08-27 | |
Abstract of the dataset | This deposit contains the supplementary data for the FedSurg EndoVis 2024 Challenge, the first federated learning challenge in Surgical Data Science, held at MICCAI 2024. The challenge used a preliminary subset of the Appendix300 dataset, a multi-institutional collection of laparoscopic appendectomy recordings from German university and community hospitals, annotated with intraoperative appendicitis severity grades 0 to 5 following Gomes et al. The challenge cohort comprises 223 recordings across four centers, split into 153 training and 70 test cases. The deposit includes a CSV file specifying which Appendix300 samples were used in the challenge and their assignment to centers and to the training and test splits, together with two recordings that were used in the challenge but excluded from the final Appendix300 dataset because the available footage was shorter than the nominal 100 second window or the appendix was not clearly visible at the annotated timestamp. This deposit does not contain the appendectomy video recordings themselves, with the exception of the two excluded cases named above. The video data and accompanying clinical metadata are available separately as the Appendix300 dataset at https://doi.org/10.25532/OPARA-1173. The challenge evaluation and ranking code is available at https://gitlab.com/nct_tso_public/challenges/miccai2024/snippet, and the example federated learning setup at https://gitlab.com/nct_tso_public/challenges/miccai2024/FedSurg24. Use of this material requires citation of both the FedSurg challenge paper and the Appendix300 data descriptor. Released under CC BY. | |
Public reference to this page | https://opara.zih.tu-dresden.de/handle/123456789/2847 | |
Public reference to this page | https://doi.org/10.25532/OPARA-1534 | |
Publisher | Technische Universität Dresden | |
Licence | Attribution 4.0 International | en |
URI of the licence text | http://creativecommons.org/licenses/by/4.0/ | |
Specification of the discipline(s) | 2::22::205::205-25 | |
Title of the dataset | FedSurg EndoVis 2024: Challenge Subset of Appendix300 | |
Funding Acknowledgement | This work was co-funded by the European Union through NEARDATA under grant agreement ID 101092644, the German Research Foundation (DFG, Deutsche Forschungsgemeinschaft) as part of Germany’s Excellence Strategy – EXC 2050/1 – Project ID 390696704 – Cluster of Excellence “Centre for Tactile Internet with Human-in-the-Loop” (CeTI) of Dresden University of Technology, and the Federal Ministry of Education and Research of Germany in the program of “Souverän. Digital. Vernetzt.”, a joint project 6G-life with the project identification number 16KISK001K. Furthermore, FRK receives support from the German Cancer Research Center (CoBot 2.0), the Joachim Herz Foundation (Add-On Fellowship for Interdisciplinary Life Science), the Central Indiana Corporate Partnership AnalytiXIN Initiative, the Evan and Sue Ann Werling Pancreatic Cancer Research Fund, and the Indiana Clinical and Translational Sciences Institute (EPAR4157) funded, in part, by Grant Number UM1TR004402 from the National Institutes of Health, National Center for Advancing Translational Sciences, Clinical and Translational Sciences Award. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. | |
Public project website(s) | https://gitlab.com/nct_tso_public/challenges/miccai2024/snippet | |
Public project website(s) | https://gitlab.com/nct_tso_public/challenges/miccai2024/FedSurg24 |
Collections
