Skip to main content
SpringerLink
Log in

Femoral head segmentation based on improved fully convolutional neural network for ultrasound images

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Developmental dysplasia of the hip is a medical term representing the hip joint instability that appears mainly in infants. The assessment metric of physician is based on the femoral head coverage rate, which needs to segment the femoral head area in 2D ultrasound images. In this paper, we propose an approach to automatically segment the femoral head. The proposed method consists of two parts, firstly, mean filtering, morphological processing and least squares operation are used to detect the ilium and acetabular bone baseline to coarsely obtain the region of interest of the femoral head, then followed by an improved fully convolutional neural network named FNet which integrates the convolution encoder–decoder architecture, pooling indices and residual connection operation for more accurate segmentation. FNet is trained in a cascaded way, which can help the network learn more features with a limited dataset and thus further improve the segmentation performance. Experimental results show that the proposed method achieved an average dice, recall and IoU value of 0.946, 0.937 and 0.897. Moreover, the features learned by convolutional layers are visualized to demonstrate that FNet can focus on significant features, which is helpful to restore the contour of the femoral head more precisely. In conclusion, the proposed method is capable of segmenting femoral head accurately and guiding the diagnosis of developmental dysplasia of the hip.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Kocer, H.E., Cevik, K.K., Sivri, M., et al.: Measuring the effect of filters on segmentation of developmental dysplasia of the hip. Iran. J. Radiol. 13(3), 1–10 (2016)

    Article  Google Scholar 

  2. Tosun, H.B., Bulut, M., Karakurt, L., Belhan, O., Serbest, S.: Evaluation of the results of hip ultrasonography which applied for screening of developmental hip dysplasia. Fırat Med. J. 15(4), 178–183 (2010)

    Google Scholar 

  3. de Luis-Garcia, R., Aja-Fernandez, S., Cardenes-Almeida, R., et al.: Analysis of ultrasound images based on local statistics. Application to the diagnosis of developmental dysplasia of the hip. In: Presented at IEEE Ultrasonics Symposium (2007)

  4. Bonny, S., Chanu, Y.J., Singh, K.M.: Speckle reduction of ultrasound medical images using Bhattacharyya distance in modified non-local mean filter. SIViP 13(2), 299–305 (2019)

    Article  Google Scholar 

  5. Al-Bashir, A.K., Al-Abed, M., Sharkh, F.M.A., et al.: Algorithm for automatic angles measurement and screening for developmental dysplasia of the hip (DDH). In: Presented at the 37th Annual International Conference of the IEEE, Engineering in Medicine and Biology Society (EMBC) (2015)

  6. Herring, J.A.: Developmental dysplasia of the hip. In: Herring, J.A. (ed.) Tachdjian’s Pediatric Orthopaedics, pp. 513–534. W.B. Saunders Co., Philadelphia (2003)

    Google Scholar 

  7. Graf, R.: The diagnosis of congenital hip dislocation by the ultrasound compound treatment. Arch. Orthop. Trauma Surg. 97(3), 117–133 (1980)

    Article  Google Scholar 

  8. Graf, R.: Classification of hip joint dysplasia by means of sonography. Arch. Orthop. Trauma Surg. 102(4), 248–255 (1984)

    Article  MathSciNet  Google Scholar 

  9. Tang, M., Zhang, Z., Cobzas, D., et al.: Segmentation-by-detection: a cascade network for volumetric medical image segmentation. In: Presented at IEEE 15th International Symposium on Biomedical Imaging (2018)

  10. Chandra, S.S., Xia, Y., Engstrom, C., et al.: Focused shape models for hip joint segmentation in 3D magnetic resonance images. Med. Image Anal. 18(3), 567–578 (2014)

    Article  Google Scholar 

  11. Cen, G., Cai, N., Wu, J., et al.: Detonator coded character spotting based on convolutional neural networks. Signal Image Video Process. (2019). https://doi.org/10.1007/s11760-019-01525-1

    Article  Google Scholar 

  12. Fan, S., Wang, R., Wu, Z., et al.: High-speed tracking based on multi-CF filters and attention mechanism. Signal Image Video Process. (2019). https://doi.org/10.1007/s11760-019-01527-z

    Article  Google Scholar 

  13. Feng, X., Yao, H., Zhang, S.: An efficient way to refine DenseNet. Signal Image Video Process. 13, 1–7 (2019)

    Article  Google Scholar 

  14. Mithra, K.S., Emmanuel, W.R.S.: Automated identification of mycobacterium bacillus from sputum images for tuberculosis diagnosis. Signal Image Video Process. 13, 1–8 (2019)

    Article  Google Scholar 

  15. Nezamabadi, K., Naseri, Z., Moghaddam, H.A., et al.: Lung HRCT pattern classification for cystic fibrosis using convolutional neural network. Signal Image Video Process. 13, 1–8 (2019)

    Article  Google Scholar 

  16. Prasoon, A., Petersen, K., Igel, C., Lauze, F., Dam, E., Nielsen, M.: Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. In: Presented at International Conference on Medical Image Computing and Computer-Assisted Intervention (2013). https://doi.org/10.1007/978-3-642-40763-5_31

  17. Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Presented at International Conference on Medical Image Computing and Computer-Assisted Intervention (2015). https://doi.org/10.1007/978-3-319-24574-4_28

  18. Stollenga, M.F., Byeon, W., Liwicki, M., Schmid-huber, J.: Parallel multi-dimensional LSTM, with application to fast biomedical volumetric image segmentation. In: Presented at Advances in Neural Information Processing Systems (2015). http://papers.nips.cc/paper/5642-parallel-multi-dimensional-lstm-with-application-to-fast-biomedical-volumetric-image-segmentation. Accessed 28 Aug 2019

  19. Roth, H.R., Lu, L., Farag, A., Shin, H.-C., Liu, J., Turkbey, E. B., Summer, R.M.: Deeporgan: multi-level deep convolutional networks for automated pancreas segmentation. In: Presented at International Conference on Medical Image Computing and Computer-Assisted Intervention (2015). https://doi.org/10.1007/978-3-319-24553-9_68

  20. Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Presented at International Conference on Medical Image Computing and Computer-Assisted Intervention (2016). https://doi.org/10.1007/978-3-319-46723-8_49

  21. Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.-M., Larochelle, H.: Brain tumor segmentation with deep neural networks. Med. Image Anal. 35, 18–31 (2017)

    Article  Google Scholar 

  22. Chen, H., Dou, Q., Yu, L., Qin, J., Heng, P.-A.: Voxresnet: deep voxelwise residual networks for brain segmentation from 3D MR images. NeuroImage 170, 446–455 (2017)

    Article  Google Scholar 

  23. Badrinarayanan, V., Handa, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv preprint arXiv:1505.07293 (2015)

  24. He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Presented at Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016). https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html. Accessed 28 Aug 2019

  25. Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Presented at Proceedings of the 27th International Conference on Machine Learning (ICML-10) (2010). https://www.cs.toronto.edu/~hinton/absps/reluICML.pdf. Accessed 28 Aug 2019

  26. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint: arXiv:1502.03167 (2015)

  27. Dunlap, J.: Queue-linear flood fill: a fast flood fill algorithm. http://www.codeproject.com/KB/GDI-plus/queuelinearfloodfill.aspx. Accessed 28 Aug 2019

  28. Chollet, F.: Keras: deep learning library for theano and tensorflow, vol. 7, no. 8 (2015). https://keras.io/k. Accessed 28 Aug 2019

  29. Abadi, M., Barham, P., Chen, J., et al.: Tensorflow: a system for large-scale machine learning. In: Presented at OSDI (2016). https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf. Accessed 28 Aug 2019

  30. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. (2014). https://arxiv.org/abs/1412.6980

  31. Milletari, F., Navab, N., Ahmadi, S. A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: Presented at IEEE Fourth International Conference on 3D Vision (2016). https://ieeexplore.ieee.org/abstract/document/7785132/. Accessed 28 Aug 2019

  32. Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Presented at Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)

Download references

Acknowledgements

We would like to thank the Shenzhen Children’s Hospital for providing data to support this project. This work was supported by National Key R&D Program of China (2017YFC0110700), National Natural Science Foundation of China (61771056), Key projects of Beijing Natural Science Foundation (4161004) and Beijing Science and Technology Plan Project (Z161100000216143, Z171100000117001).

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Beijing Institute of Technology, Beijing, 100081, China

    Lei Chen, Yutao Cui & Hong Song

  2. Shenzhen Children’s Hospital, Shenzhen, 518038, China

    Bingxuan Huang & Bei Xia

  3. School of Optics and Electronics, Beijing Institute of Technology, Beijing, 100081, China

    Jian Yang

  4. Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100080, China

    Di Zhao

Authors
  1. Lei Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yutao Cui
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hong Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bingxuan Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jian Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Di Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Bei Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hong Song.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, L., Cui, Y., Song, H. et al. Femoral head segmentation based on improved fully convolutional neural network for ultrasound images. SIViP 14, 1043–1051 (2020). https://doi.org/10.1007/s11760-020-01637-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-020-01637-z

Keywords

Search

Navigation