An initiative to improve the accuracy of mammography screening has commenced with a $1.2 million incentive for research leading to algorithms that would improve cancer detection while reducing false positives.
Sage Bionetworks and Dream Challenges are leading the Digital Mammography Dream Challenge with funding from the Laura and John Arnold Foundation (LJAF) to develop predictive algorithms to reduce the recall rate of mammography screening.
The Digital Mammography Dream Challenge will run through mid-2017. Data experts from inside and outside the medical field are welcome to create algorithms that will help doctors determine whether a patient's mammogram has a high or low likelihood of harboring breast cancer and whether or not a patient should undergo additional testing.
Researchers participating in the challenge will use anonymous patient data from a database that includes some 650,000 digitized mammograms. The algorithms will be evaluated using data on patient outcomes and will be scored based on accuracy. Algorithms that identify the lowest number of false positives while maintaining high rates of cancer detection will receive the highest ranking on a leaderboard that can be viewed publicly.
