2materialandmethods.docVIP

Automated determination of bone age from hand X-rays at the end of puberty, and its applicability for age estimation Hans Henrik Thodberg1, Rick R van Rijn2, Oskar G Jenni3, and David D Martin4 1Visiana, S?ller?dvej 57C, 2840 Holte, Denmark, email: thodberg@, corresponding author 2Academic Medical Center, Amsterdam, Meibergdreef 9, 1105 AZ Amsterdam, Netherlands 3Child Development Center, University Children’s Hospital Zürich, Steinwiesstrasse 75, 8032 Zürich, Switzerland 4Tubingen University Children’s Hospital, Hoppe-Seyler-Strasse 1, 72076 Tübingen, and Filderklinik, Im Haberschlai 7, 70794, Filderstadt, Germany Abstract The BoneXpert method for automated determination of bone age from hand X-rays was introduced in 2009, covering the Greulich-Pyle bone age range up to 17 years for boys and 15 years for girls. This paper presents an extension of the method up to bone age 19 years for boys and 18 years for girls. The extension was developed based on images from the First Zurich Longitudinal Study of 231 healthy children born in 1954-56 and followed with annual X-rays of both hands until the age of 20 years. The method was validated on two cross-sectional studies of healthy children from Rotterdam and Los Angeles. We found a root mean square deviation from manual rating of 0.68 and 0.49 years in these two studies for boys in the bone age range 17-19 years. For girls, the deviations were 0.77 and 0.63 years respectively, in the bone age range 15-18 years. The method is applied to infer the age probability distribution for healthy Caucasian European males. Considering a population with age 16-21 years, the method can be used to decide whether the subject is above 18 years with an error rate of 20.5%, of which 5.0% are children classified as adults and 15.5 % are adults classified as children. To apply this method in other ethnicities would require a study of the average of “bone age – age” at the end of puberty, i.e. how much this population is shifted relative