Healthc Inform Res.  2018 Jan;24(1):86-92. 10.4258/hir.2018.24.1.86.

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

• Lee JH
• Kim KG

• KMID: 2403300
• DOI: http://doi.org/10.4258/hir.2018.24.1.86

Abstract

OBJECTIVES
A diagnostic need often arises to estimate bone age from X-ray images of the hand of a subject during the growth period. Together with measured physical height, such information may be used as indicators for the height growth prognosis of the subject. We present a way to apply the deep learning technique to medical image analysis using hand bone age estimation as an example.
METHODS
Age estimation was formulated as a regression problem with hand X-ray images as input and estimated age as output. A set of hand X-ray images was used to form a training set with which a regression model was trained. An image preprocessing procedure is described which reduces image variations across data instances that are unrelated to age-wise variation. The use of Caffe, a deep learning tool is demonstrated. A rather simple deep learning network was adopted and trained for tutorial purpose.
RESULTS
A test set distinct from the training set was formed to assess the validity of the approach. The measured mean absolute difference value was 18.9 months, and the concordance correlation coefficient was 0.78.
CONCLUSIONS
It is shown that the proposed deep learning-based neural network can be used to estimate a subject's age from hand X-ray images, which eliminates the need for tedious atlas look-ups in clinical environments and should improve the time and cost efficiency of the estimation process.

Keyword

Bone Age; Deep Learning; Python; Tensorflow; X-ray Imaging

MeSH Terms

Boidae
Hand
Learning*
Prognosis

Figure

• 

  Figure 1 Skeletal anatomy [4] and an X-ray image of a hand [5].

• 

  Figure 2 Example input image [5] with marked feature points.

• 

  Figure 3 Data preparation process.

• 

  Figure 4 Caffenet architecture [1].

• 

  Figure 5 Error versus iteration in linear and log scales.

Reference

1. Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012; 25:1097–1105.

2. Greulich WW, Pyle SI. Radiographic atlas of skeletal development of the hand and wrist. 2nd ed. Stanford (CA): Stanford University Press;1959.

3. Tanner JM, Whitehouse RH. Clinical longitudinal standards for height, weight, height velocity, weight velocity, and stages of puberty. Arch Dis Child. 1976; 51(3):170–179.

4. Visual Dictionary Online. Hand [Internet]. [place unknown]: Visual Dictionary Online;c2017. cited at 2018 Jan 5. Available from: http://visual.merriam-webster.com/human-being/anatomy/skeleton/hand.php.

5. Radiological Society of North America. Pediatric bone age challenge [Internet]. Oak Brook (IL): Radiological Society of North America;c2017. cited at 2018 Jan 5. Available from: http://rsnachallenges.cloudapp.net/competitions/4.

6. Berkeley Artificial Intelligence Research. Caffe Installation [Internet]. Berkeley (CA): Berkeley Artificial Intelligence Research;c2014. cited at 2018 Jan 5. Available from: http://caffe.berkeleyvision.org/installation.html.

7. BVLC/caffe [Internet]. [place unknown: place unknown]: c2017. cited at 2018 Jan 5. Available from: https://github.com/BVLC/caffe/tree/master/models/bvlc_reference_caffenet.

8. Deng J, Dong W, Socher R, Li LJ, Li K, Li FF. ImageNet: a large-scale hierarchical image database. In : Proceedings of IEEE Conference on Computer Vision and Pattern Recognition; 2009 Jun 20-25; Miami, FL: p. 248–255.

9. Wikipedia. Backpropagation [Internet]. [place unknown]: Wikipedia;c2017. cited at 2018 Jan 5. Available from: https://en.wikipedia.org/wiki/Backpropagation.