Performance of Convolutional Neural Networks and Transfer Learning for Skeletal Bone Age Assessment

Main Article Content

Chadaporn Keatmanee, PhD
Songphon Klabwong, MSc
Kamolphong Osatavanichvong, MD
Chirotchana Suchato, MD

Abstract

OBJECTIVES: Bone age assessment is used by clinicians for estimating the maturity of a child’s skeletal system. Traditionally, physicians use template matching methods (GP and/or TW2). Time and accuracy of the evaluation rely on a physician’s experience. Therefore, this research proposes a fully automatic system for bone age assessment with cutting edge artificial Intelligence (AI) technology. 
 
MATERIAL AND METHODS: Convolutional Neural Network (CNNs), a Deep Learning (DL) technique is applied to skeletal bone age prediction combined with transfer learning algorithm. Hence, various kinds of transfer learning algorithms (ResNet-50, Inception-V3, and VGG-16) are investigated in training in the proposed model fed by a number of x-ray images (12,000 image approximately—imbalanced data). 

RESULT: VGG-16 shows significant accuracy compared to ResNet-50 and Inception-V3 (mae = 6.53, 20.52 and 43.11 months respectively)


CONCLUSION: The most effective pre-trained layer for CNNs in bone age assessment is VGG-16 according to the accuracy of its prediction. 



 

Downloads

Download data is not yet available.

Article Details

How to Cite
1.
Keatmanee C, Klabwong S, Osatavanichvong K, Suchato C. Performance of Convolutional Neural Networks and Transfer Learning for Skeletal Bone Age Assessment. BKK Med J [Internet]. 2019Jun.26 [cited 2020Dec.5];15(1):1. Available from: https://he02.tci-thaijo.org/index.php/bkkmedj/article/view/197910
Section
Original Article

References

Greulich, W. W., Pyle, S. I., and Todd, T. W. Radiographic atlas of skeletal development of the hand and wrist. Stanford: Stanford university press, 1959;2:150-159.

Tanner, J. M., Whitehouse, R. H., Cameron, N., Marshall, et al. Assessment of skeletal maturity and prediction of adult height (TW2 method). London: Academic press, 1975;16.

Wang S., Summers RM. Machine Learning and radiology. Med Image Anal, 2012;16:933-51.

Fausto M., Seyed-Ahmad A., Christine K., et al. Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound. Computer Vision and Image Understanding, 2017;164:92-102

Luis H.S. V., Rodrigo M.S. V., Flavio. H.D., et al. Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification. Engineering Applications of Artificial Intelligence, 2018;72:415-422 6

Krizhevsky, A., Sutskever, I., and Hinton, G. E. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, 2012:1097-1105.

Van Steenkiste T, Ruyssinck J, Janssens O, et al. Automated assessment of bone age using deep learning and Gaussian process regression. IEEE Engineering in Medicine and Biology Society Conference Proceedings.2018:674–7.

Yagang W., Qianni Z., Jungang H., and Yang J. Application of Deep learning in Bone age assessment. IOP Conference Series: Earth and Environmental Science. 2018;199(3):032012.

Matthew C., David B. L., Matthew P. L., et al. Deep Neural Nets: Pediatric Hand Radiographs. Radiology informatics [online]. 2019 [cited 2019 Jan 1]. Available from:https:// langlotzlab.stanford.edu/projects/pediatric-hand-radiographs/

Matthew C. Automated Bone Age Classification with Deep Neural Networks [online]. 2019 [cited 2019 Jan 1]. Available from: https://cs231n.stanford.edu/reports/2016/pdfs/310_ Report.pdf

Larson DB., Chen MC., Lungren MP., et al. Performance of a Deep-Learning Neural Network Model in Assessing Skeletal Maturity on Prediatric Hand Radiographs. Radiology. 2018;287(1):313-322.

Kotsiantis S., Kanellopoulos D. and Pintelas, P. Handling imbalanced datasets: A review. GESTS International Transactions on Computer Science and Engineering. 2015;30:25-36.

Rawat, W. and Wang, Z. Deep Convolutional Neural Networks for Image Classification. A Comprehensive Review. Neural computation. 2017;29(9):2352-2449.

Sinno J. P. and Qiang Y. A Survery on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering [online]. [cited 2019 Jan 1]. Available from: https://www.cse.ust. hk/~qyang/Docs/2009/tkde_transfer_learning.pdf
He, K., Zhang, X., Ren, S., and Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016:770-778.

Christian S., Vincent V., Sergey I., et al. Rethinking the Inception Architecture for Computer Vision. The CVPR paper provided by the Computer Vision foundation [online]. [cited 2019 Jan 1]. Available from: https://www.cv-foundation.org/ openaccess/content_cvpr_2016/papers/Szegedy_Rethinking_ the_Inception_CVPR_2016_paper.pdf

Karen S. and Andrew Z. Very Deep Convolutional Networks for Large-Scale Image Recognition [online]. [cited 2019 Jan 1]. Available from: https://arxiv.org/abs/1409.1556

RSNA Pediatric Bone age challenge [online]. 2017 [cited 2017 Oct 7]. Available from: https://rsnachallenges.cloudapp.net/ competitions/4

LeCun Y. Learning invariant feature hierarchies. Computer vision ECCV 2012. Workshops and demonstrations. Springer Berlin Heidelberg, 2012.

Jaderberg M., Karen S., and Andrew Z. Spatial transformer networks. Advances in Neural Information Processing Systems. 2015.