Digital Mammography DREAM Challenge
Toward improving the predictive accuracy of digital mammography for the early detection of breast cancer
The goal of the Digital Mammography (DM) DREAM Challenge was to apply an open science, crowd-sourced approach to develop and assess algorithms for risk stratification of screening mammograms that can be used to improve breast cancer detection. These algorithms could potentially benefit interpretation of other tumor imaging, impacting a wide set of cancer patients. The DM Challenge encouraged teams to apply deep learning methods to a large set of mammography images of over 640k images from 80k women. Dozens of teams participated in this Challenge, resulting in the development of many novel approaches to cancer detection and the establishment of public standards and benchmarks in this field.
Read our our press release announcing the winners of the first phase of the DM Challenge.
More Challenges and Benchmarking Projects
NLPSandbox.io is one of the first tool-benchmarking platforms that securely connects developers to healthcare data providersLearn More
DREAM Challenges powered by Sage Bionetworks
Community competitions on fundamental questions about systems biology and translational medicine, and advance computational methodsLearn More
Wellcome Trust partners with Sage Bionetworks
The Wellcome Data Re-use Prizes show how data re-use can generate new insights that may lead to vital health benefitsLearn More