Abstract
In this paper, a two stage method is proposed for bone image abnormality detection. The core idea of this method is based on our observation and analysis of the abnormal images. The abnormal images are divided into two categories: one is the abnormal images containing abnormal objects, the other is the abnormal images of the bone with inconspicuous lesions. The abnormal images containing abnormal objects are easy to be classified, so that we can focus on the abnormal images which are difficult to classify. The proposed two stage method enables the classifier to extract better features and learn better classification parameters for the abnormal images that are difficult to classify. We carried out experiments on a large-scale X-ray dataset MURA. SENet154 and DenseNet201 are used as the classification networks. Compare to one stage method, the proposed method can improve test accuracies by 1.71% (SENet154) and 1.43% (DenseNet201), respectively, which shows the effectiveness of the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Woolf, A.D., Pfleger, B.: Burden of major musculoskeletal conditions. Bull. World Health Organ. 81(9), 646–656 (2003)
Olmarker, K.: The bone and joint decade 2000–2010. Eur. Spine J. 7(4), 269 (1998)
Nafsiah, M., Indra, M.S., Indang, T., Iqbal, E., Karen, H.S., Pungkas, B.A., et al.: On the road to universal health care in indonesia, 1990–2016: a systematic analysis for the global burden of disease study 2016. The Lancet (2018). S0140673618305956
Spanhol, F.A., Oliveira, L.S., Petitjean, C., Heutte, L.: Breast cancer histo pathological image classification using convolutional neural networks. In: International Joint Conference on Neural Networks. IEEE (2016)
Wei, L., Peng, C., Dazhe, Z., Junbo, W.: Pulmonary nodule classification with deep convolutional neural networks on computed tomography images. Comput. Math. Methods Med. 2016, 1–7 (2016)
Roth, H.R., Lu, L., Seff, A., Cherry, K.M., Hoffman, J., Wang, S., et al.: A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations. Med Image Comput. Comput. Assist. Interv. (2014)
Rajpurkar, P., et al.: Mura: Large dataset for abnormality detection in musculoskeletal radiographs. arXiv preprint arXiv:1712.06957 (2017)
Banga, D., Waiganjo, P.: Abnormality detection in musculoskeletal radiographs with convolutional neural networks (Ensembles) and Performance Optimization. arXiv preprint arXiv:1908.02170 (2019)
Kaliyugarasan, S.K.:Â Deep transfer learning in medical imaging. MS thesis. The University of Bergen (2019)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)
Pizer, S.M., Amburn, E.P., Austin, J.D., Cromartie, R.: Adaptive histogram eqalization and its variations. In: Computer Vision, Graphics, and Image Processing (CVGIP), vol. 39, pp. 355–368 (1987)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Acknowledgement
This study was supported by the National Natural Science Foundation of China (NSFC) under Grant no. 61563039.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Shao, Y., Wang, X. (2020). A Two Stage Method for Abnormality Diagnosis of Musculoskeletal Radiographs. In: Lu, Y., Vincent, N., Yuen, P.C., Zheng, WS., Cheriet, F., Suen, C.Y. (eds) Pattern Recognition and Artificial Intelligence. ICPRAI 2020. Lecture Notes in Computer Science(), vol 12068. Springer, Cham. https://doi.org/10.1007/978-3-030-59830-3_53
Download citation
DOI: https://doi.org/10.1007/978-3-030-59830-3_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59829-7
Online ISBN: 978-3-030-59830-3
eBook Packages: Computer ScienceComputer Science (R0)