Applying Deep Learning in Medical Images: The Case of Bone Age Estimation

Abstract

Objectives: A diagnostic need often arises to estimate bone age from X-ray images of the hand of a subject during the growthperiod. Together with measured physical height, such information may be used as indicators for the height growth prognosisof the subject. We present a way to apply the deep learning technique to medical image analysis using hand bone age estimationas an example. Methods: Age estimation was formulated as a regression problem with hand X-ray images as inputand estimated age as output. A set of hand X-ray images was used to form a training set with which a regression model wastrained. An image preprocessing procedure is described which reduces image variations across data instances that are unrelatedto age-wise variation. The use of Caffe, a deep learning tool is demonstrated. A rather simple deep learning network wasadopted and trained for tutorial purpose. Results: A test set distinct from the training set was formed to assess the validityof the approach. The measured mean absolute difference value was 18.9 months, and the concordance correlation coefficientwas 0.78. Conclusions: It is shown that the proposed deep learning-based neural network can be used to estimate a subject’sage from hand X-ray images, which eliminates the need for tedious atlas look-ups in clinical environments and should improvethe time and cost efficiency of the estimation process.