The goal of the RSNA 2017 Machine Learning Challenge was to develop an algorithm which can most accurately determine skeletal age on a validation set of pediatric hand radiographs. Over 300 teams participated from around the world. 16 Bit entered the competition and achieved a mean absolute difference (MAD) of 4.265 months and concordance correlation coefficient (CCC) of 0.991 placing them 1st in the competition. This application enables others to predict skeletal age from pediatric hand x-rays.
Join us at the 2017 RSNA Conference on Monday, November 27, 9:30 - 11:00 AM at the Machine Learning Showcase in the North Technical Exhibits Building, Hall B, McCormick Place, Chicago.
Analyze Your Image
The training set used contained 12,612 images from two U.S. hospitals. Training set had a maximum age of 228 months (19 years), mininimum age of 1 month, mean age of 127 months (10 years 7 months) and a standard deviation of 42 months (3 years 6 months). See more details here.
 Cree M. Gaskin, MD MBA S. Lowell Kahn, J. Christoper Bertozzi, Paul M. Bunch. Skeletal Development of the Hand and Wrist: A Radiographic Atlas and Digital Bone Age Companion. Oxford University Press, Feb 1, 2011. (Adapted from Greulich WW, Pyle SI. Radiographic atlas of skeletal development of the hand and wrist. 2nd ed. Stanford, Calif: Stanford University Press, 1959.)