Computational Precision Medicine: Radiology-Pathology Challenge on Brain Tumor Classification 2019 (CPM-RadPath): Participation Summary

MotivationData • Participation Summary • RegistrationPeople

Participation Summary

The challenge will consist of three phases: a training phase, a validation (or fine-tuning) phase, and a final test phase.

Training Phase — Data availability (July 15). Register here to download the CPM-RadPath paired radiology-pathology training data.

Validation Phase — Data availability (August 15). An independent set of paired radiology-pathology data will be made available to the participants in August, with the intention to allow them assess the generalizability of their methods in unseen data. Multiple submissions of classification results are allowed to the challenge platform.

Short Paper submission deadline (September 15). Participants will have to evaluate their methods on the training and validation datasets, and submit a short paper (~8 LNCS pages — together with the "LNCS Consent to Publish" form) describing their method and results, to the BrainLes CMT submission system, and make sure you choose CPM-RadPath as the "Track". This unified scheme should allow for appropriate preliminary comparisons and the creation of the pre- and post-conference proceedings. CPM-RadPath papers will be part of the BrainLes workshop proceedings distributed by LNCS. All paper submissions should use the LNCS template, available both in LaTeX (link here) and in MS Word (link here) format, directly from Springer (link here).

Test Data availability & Performance Evaluation (September 3-18). The test data are made available to each participating team that submitted a short paper, for a limited controlled time-window (48h) during 3 and 18 of September. The participants will analyze the images using their local computing infrastructure and will have to submit their classification results 48h later to the online evaluation portal.

Oral Presentations. The top-ranked participants will be contacted before the end of September to prepare slides for orally presenting their method during CPM-RadPath in MICCAI, on Oct.17.

Announcement of Final Results (Oct 17). Results of the challenge will be reported during the CPM-RadPath 2019 challenge in Shenzhen, China, which will run as part of a joint event with the MICCAI 2019 Brain Lesions (BrainLes) Workshop and the MICCAI 2019 BraTS Challenge.

Post-conference LNCS paper (Nov 15). All participated methods will be invited to extend their papers to 12 pages for inclusion to the LNCS proceedings of the BrainLes Workshop.

Joint post-conference journal paper. In the weeks following the challenge, all participating teams will be offered the opportunity to be involved to the joint manuscript summarizing the results of CPM-RadPath 2019, that will be submitted to a high-impact journal in the field. To be involved in this manuscript the participating teams will be asked to provide their algorithm in a Docker container that will allow its assessment for reproducibility of results. Further information of what exactly is expected from the participating teams can be found in the Data page.


Data Usage Agreement / Citations

You are free to use and/or refer to the CPM-RadPath datasets in your own research, provided that you always cite the following manuscript:

T. Kurc, S. Bakas, X. Ren, A. Bagari, A. Momeni, Y. Huang, L. Zhang, A. Kumar, M. Thibault, Q. Qi, Q. Wang, A. Kori, O. Gevaert, Y. Zhang, D. Shen, M. Khened, X. Ding, G. Krishnamurthi, J. Kalpathy-Cramer, J. Davis, T. Zhao, R. Gupta, J. Saltz, K. Farahani. "Segmentation and classification in digital pathology for glioma research: challenges and deep learning approaches". Frontiers in neuroscience, p.27, 2020.


CPM-RadPath 2019 runs in conjunction with the MICCAI 2019 conference, on Oct.17, as part of the full-day BrainLes Workshop.

Feel free to send any communication related to the CPM-RadPath challenge to