News

Digital Mammography DREAM Challenge

June 29, 2016

Digital Mammography DREAM Challenge

DM Banner v3

$1.2 M Digital Mammography Challenge Aims to Improve the Accuracy of Mammograms

Contest aims to crowd-source machine learning algorithms to help reduce the false positive mammography rate

SEATTLE, WA – September 7, 2016 – A coalition of oncology and technology partners led by Sage Bionetworks and DREAM Challenges today announced the opening of the training phase for the Digital Mammography DREAM Challenge, an open-science data competition designed to improve the accuracy of mammography screening. With funding from Laura and John Arnold foundation (LJAF), the Challenge will award up to $1.2 million to data scientists, researchers, and coding experts who develop predictive algorithms that achieve milestone goals related to reducing the recall rate of mammography screening. Interested participants can sign up at https://www.synapse.org/Digital_Mammography_DREAM_Challenge.

Read Full Press Release

Digital Mammography DREAM Challenge

Sage Bionetworks, in partnership with the open science DREAM Challenges community and with support from the Laura and John Arnold Foundation, announces the launch of the first of the Coding4Cancer (C4C) Challenges: the Digital Mammography DREAM Challenge. This $1.2 million prize competition will aim to improve the accuracy of digital-image breast cancer detection in order to improve patient outcomes and reduce healthcare costs.

The primary benefit of this Challenge will be to establish new quantitative tools based in deep learning that can help decrease the recall rate of screening mammography, with a potential impact on shifting the balance of routine breast cancer screening towards more benefit and less harm. Participating teams will be asked to submit predictive models based on over 640,000 de-identified digital mammography images from over 86000 patients, with corresponding clinical variables.

Anonymous Challenge data has been contributed by Group Health Cooperative through the NCI-funded Breast Cancer Surveillance Consortium and by the Icahn School of Medicine at Mount Sinai. Cloud computing will be provided by Amazon Web Services and the IBM Watson Health Cloud.  All competition results will be placed into the public domain, with the algorithms made available to researchers and for commercialization.

The Digital Mammography Challenge, which will be conducted by Sage Bionetworks and DREAM Challenges, is the first in a series of competitions held as part of the Coding for Cancer initiative. The concept for these coding challenges was sparked by a story I read in 2010 about a study that showed how annual CT scans reduced smokers’ risk of dying from lung cancer by 20 percent. The researchers also found, however, that there was a high false-positive rate associated with CT scans. It prompted me and others to think about ways to improve the accuracy of cancer screenings by using machine learning and algorithms to help radiologists determine which patients should receive biopsies.

DM Challenge Flier Image