Page History

...

As explained in the Challenge Management System Evaluation Report, challenge hosts and participants cannot do it alone. The computing resourcing needed to process these large datasets may be beyond what is available to individual participants. For the organizers, creating an infrastructure that is secure, robust, and scalable can require resources that are beyond the reach of many researchers. Additionally, imaging formats for pathology images can be proprietary and interoperability between formats can require additional software development efforts.

Over the last few years, “Grand Challenges” have become popular in several imaging-based research communities. A “Grand Challenge” is designed to validate and compare imaging analysis algorithms. The algorithms are applied to a single dataset and the results for each algorithm are compared against a previously-determined ground-truth dataset.

The Pilot Challenges sub-project of CTIIP will make a set of integrated data from TCIA and TCGA publicly available to researchers who will participate in three complementary "pilot challengePilot Challenge" projects. (this only happened in the first challenge to figure out which image was from which tumor–look at Miccai ) As opposed to a more rigorous "grand" challenge, each pilot challenge will function as a proof of concept to learn how to scale challenges up in the future.

A team from Massachusetts General Hospital will guide the pilot challenges, using the Medical Imaging Challenge Infrastructure (MedICI), a system that supports medical imaging challenges.

The proposed work fits into the above-described environment by developing and executing infrastructure that can be used to run Challenges on a smaller scale with data sets of reduced size and will demonstrate the infrastructure as capable of running Grand Challenges. 

The MedICI system will utilize the CodaLab framework, a newly developed, open-source challenge platform developed by Microsoft Research and others in the medical imaging and machine learning communities.  Because CodaLab does not have built-in imaging handling, display or annotation capabilities, we will build on two application packages, ePad and caMicroscope, to provide those features. 

This challenge is part of the Computational Brain Tumor Cluster of Event (CBTC) 2015 which will be held on Oct 9 in Munich, Germany, in conjunction with MICCAI 2015. It will consist of a morning workshop and afternoon challenges.

...