Abstract
Hip dysplasia is a genetic disease that causes the laxity of the hip joint and is one of the most common skeletal diseases found in dogs. Diagnosis is performed through an X-ray analysis by a specialist and the only way to reduce the incidence of this condition is through selective breeding. Thus, there is a need for an automated tool that can assist the specialist in diagnosis. In this article, our objective is to develop models that allow segmentation of the femur and acetabulum, serving as a foundation for future solutions for the automated detection of hip dysplasia. The studied models present state-of-the-art results, reaching dice scores of 0.98 for the femur and 0.93 for the acetabulum.
This work was financed by project Dys4Vet (POCI-01-0247-FEDER-046914), co-financed the European Regional Development Fund (ERDF) through COMPETE2020 - the Operational Programme for Competitiveness and Internationalisation (OPCI). The authors are also grateful for all the conditions made available by FCT- Portuguese Foundation for Science and Technology, under the projects UIDB/04033/2020, UIDB/CVT/00772/2020 and Scientific Employment Stimulus-Institutional Call-CEECINST/00127/2018 UTAD.
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
Ginja, M.M., Silvestre, A.M., Gonzalo-Orden, J.M., Ferreira, A.J.: Diagnosis, genetic control and preventive management of canine hip dysplasia: a review, pp. 269–276, June 2010. https://pubmed.ncbi.nlm.nih.gov/19428274/
Fries, C.L., Remedios, A.M.: The pathogenesis and diagnosis of canine hip dysplasia: a review, pp. 494–502 (1995)
Ginja, M.M., et al.: Hip dysplasia in Estrela mountain dogs: prevalence and genetic trends 1991-2005. Vet. J. 182(2), 275–282 (2009) https://pubmed.ncbi.nlm.nih.gov/18722145/
Ginja, M.M., et al.: Early hip laxity examination in predicting moderate and severe hip dysplasia in Estrela mountain dog. J. Small Anim. Pract. 49(12), 641–646 (2008)
Richardson, D.C.: The role of nutrition in canine hip dysplasia, pp. 529–540 (1992)
Flückiger, M.: Scoring radiographs for canine hip dysplasia - the big three organizations in the world. Eur. J. Companion Anim. Pract. 17, 135–140 (2007). Table 1. www.fci.org
Shah, R., Sharma, P.: Bone segmentation from X-ray images: challenges and techniques. In: Bhateja, V., Nguyen, B., Nguyen, N., Satapathy, S., Le, D.N. (eds.) Information Systems Design and Intelligent Applications. AISC, vol. 672, pp. 853–862. Springer, Singapore (2018). https://doi.org/10.1007/978-981-10-7512-4_84
Lianghui, F., Gang, H.J., Yang, J., Bin, Y.: Femur segmentation in X-ray image based on improved U-Net. In: IOP Conference Series: Materials Science and Engineering, vol. 533, no. 1 (2019)
Siddique, N., Paheding, S., Elkin, C.P., Devabhaktuni, V.: U-Net and its variants for medical image segmentation: a review of theory and applications. IEEE Access (2021). https://arxiv.org/abs/2011.01118v1
Kim, M., et al.: Deep learning in medical imaging, pp. 657–668 (2019). /pmc/articles/PMC6945006//pmc/articles/PMC6945006/?report=abstract. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6945006/
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2015). https://arxiv.org/abs/1411.4038v2
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28. https://arxiv.org/abs/1505.04597v1
Ouertani, F., Vazquez, C., Cresson, T., De Guise, J.: Simultaneous extraction of two adjacent bony structures in X-ray images: application to hip joint segmentation. In: Proceedings - International Conference on Image Processing, ICIP, vol. 2015, pp. 4555–4559. IEEE Computer Society, December 2015
Hussain, D., Al-Antari, M.A., Al-Masni, M.A., Han, S.M., Kim, T.S.: Femur segmentation in DXA imaging using a machine learning decision tree. J. X-Ray Sci. Technol. 26(5), 727–746 (2018). https://www.researchgate.net/publication/326597757
Xu, W., He, J, Shu, Y., Zheng, H.: Advances in convolutional neural networks. In: Advances and Applications in Deep Learning. IntechOpen, October 2020. https://www.intechopen.com/chapters/73604
Bullock, J., Cuesta-Lazaro, C., Quera-Bofarull, A.: XNet: a convolutional neural network (CNN) implementation for medical X-ray image segmentation suitable for small datasets, p. 69 (2019)
Ding, L., Zhao, K., Zhang, X., Wang, X., Zhang, J.: A lightweight U-Net architecture multi-scale convolutional network for pediatric hand bone segmentation in X-ray image. IEEE Access 7, 68436–68445 (2019)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: 32nd International Conference on Machine Learning, ICML 2015, vol. 1, pp. 448–456. PMLR, June 2015. http://proceedings.mlr.press/v37/ioffe15.html
Shen, W., et al.: Automatic segmentation of the femur and tibia bones from X-ray images based on pure dilated residual U-Net. Inverse Probl. Imaging (2020). https://www.aimsciences.org/article/doi/10.3934/ipi.2020057
McEvoy, F.J., et al.: Deep transfer learning can be used for the detection of hip joints in pelvis radiographs and the classification of their hip dysplasia status. Vet. Radiol. Ultrasound 62, no. 4, pp. 387–393, July 2021. https://onlinelibrary.wiley.com/doi/full/10.1111/vru.12968. https://onlinelibrary.wiley.com/doi/abs/10.1111/vru.12968. https://onlinelibrary.wiley.com/doi/10.1111/vru.12968
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement, April 2018. https://arxiv.org/abs/1804.02767v1
Gomes, D.A., Alves-Pimenta, S., Ginja, M.M., Filipe, V.: Predicting canine hip dysplasia in X-ray images using deep learning. In: International Conference on Optimization, Learning Algorithms and Applications, Bragança, Portugal, pp. 1–8 (2021)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016, pp. 2818–2826. IEEE Computer Society, December 2016. https://arxiv.org/abs/1512.00567v3
Buhrmester, V., Münch, D., Arens, M.: Analysis of explainers of black box deep neural networks for computer vision: a survey (2019). https://arxiv.org/abs/1911.12116v1
Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection, December 2016. https://arxiv.org/abs/1612.03144v2
Wada, K.: Labelme: image polygonal annotation with Python (2016). https://github.com/wkentaro/labelme
Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. In: 36th International Conference on Machine Learning, ICML 2019, vol. 2019. International Machine Learning Society (IMLS), pp. 10691–10700, May 2019. https://arxiv.org/abs/1905.11946v5
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 318–327 (2020). https://arxiv.org/abs/1708.02002v2
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
da Silva, D.E.M. et al. (2022). Semantic Segmentation of Dog’s Femur and Acetabulum Bones with Deep Transfer Learning in X-Ray Images. In: Abraham, A., Gandhi, N., Hanne, T., Hong, TP., Nogueira Rios, T., Ding, W. (eds) Intelligent Systems Design and Applications. ISDA 2021. Lecture Notes in Networks and Systems, vol 418. Springer, Cham. https://doi.org/10.1007/978-3-030-96308-8_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-96308-8_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96307-1
Online ISBN: 978-3-030-96308-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)