Skip to main content

Advertisement

Springer Nature Link
Log in

A microcalcification cluster detection method based on deep learning and multi-scale feature fusion

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

To accurately identify microcalcification clusters (MCs) in x-ray images to detect breast cancer earlier, a new MC target detection method which combines a deep fine-grained cascade-enhanced network (FCE-Net) and a multi-scale feature fusion algorithm (MFF) is proposed. First, a deep convolutional neural network model FCE-Net is established to extract characteristics of MCs. FCE-Net constructs a convolutional subnetwork within the convolutional module to enhance the multi-branch structure and thus improves the detailed feature extraction performance of MCs. Then, a multi-level, fine-grained convolutional map is generated and a multi-scale feature fusion algorithm (MFF) is constructed. In order to solve the problem of fine-grained target semantic information enhancement, MFF up-samples the basic feature map twice and then laterally connects to the previous layer. Then, through the parallel regression calculation and feature classification, the confidence and regional coordinates of MC objects are obtained. Finally, the target area is classified and bounding box adjustment is performed in the merged layer of the region of interest. We perform the proposed method on the MIAS breast cancer data set. By training and testing, the accuracy of detection is 97.16% under the N5 parameter settings. The overall model improves the detection efficiency of small targets by 5–10%.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

References

  1. Feng R, Wang H, Ding Y et al (2016) To investigate the screening model of breast cancer. J Clin Radiol 35(1):36–40

    Google Scholar 

  2. Jeh SK, Kim SH, Choi JJ et al (2016) Comparison of automated breast ultrasonography to handheld ultrasonography in detecting and diagnosing breast lesions. Acta Radiol 57(2):162

    Article  Google Scholar 

  3. Chen W, Zheng R (2015) Incidence, mortality and survival analysis of breast cancer in China. Chin J Clin Oncol 42(13):668–674

    Google Scholar 

  4. Gong H, Wang Y (2007) Detection of clustered microcalcifications in mammograms based on wavelet transformation and graphics theory. Opt Tech 33(5):769–771

    Google Scholar 

  5. Wang L, Zhu M, Deng L et al (2009) Automatic detection on clustered microcalcifications on mammograms based on 2D particles. J Comput Res Dev 46(9):1438–1445

    Google Scholar 

  6. Wang D, Li Z, Wang L et al (2012) MRI in the diagnosis of breast lesions with clustered microcalcifications showing on mammography. Radiol Pract 27(10):1089–1094

    Google Scholar 

  7. Cao P, Li B, Liu X et al (2013) Microcalcifications clusters recognition based on optimized cost-sensitive SVM combinational algorithm. J Northeast Univ (Nat Sci) 34(8):1100–1104

    Google Scholar 

  8. Gao C, Hayward RB, Müller M (2017) Move prediction using deep convolutional neural networks in Hex. IEEE Trans Games. https://doi.org/10.1109/tg.2017.2785042

    Article  Google Scholar 

  9. Berg WA, Campassi C, Langenberg P et al (2000) Breast imaging reporting and data system. Am J Roentgenol 174(6):1769–1777

    Article  Google Scholar 

  10. He K, Zhang X, Ren S et al (2015) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770–778

  11. Zagoruyko S, Komodakis N (2016) Wide residual networks. arXiv:1605.07146 [cs.CV]

  12. Wu Z, Shen C, Hengel AVD (2016) Wider or deeper: revisiting the ResNet model for visual recognition. arXiv:1611.10080 [cs.CV]

  13. Lee Y, Kim H, Park E et al (2017) Wide-residual-inception networks for real-time object detection. In: 2017 IEEE Intelligent Vehicles Symposium (IV), pp 758–764

  14. Szegedy C, Vanhoucke V, Ioffe S et al (2015) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2818–2826

  15. Szegedy C, Ioffe S, Vanhoucke V et al (2016) Inception-v4, Inception-ResNet and the impact of residual connections on learning. arXiv:1602.07261 [cs.CV]

  16. Redmon J, Divvala S, Girshick R et al (2015) You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 779–788

  17. Ren S, He K, Girshick R et al (2015) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149

    Article  Google Scholar 

  18. He K, Zhang X, Ren S et al (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904–1916

    Article  Google Scholar 

  19. Lin T Y, Dollar P, Girshick R et al (2016) Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 936–944

  20. Yip M, Mackenzie A, Lewis E et al (2011) Image resampling effects in mammographic image simulation. Phys Med Biol 56(22):275–286

    Article  Google Scholar 

  21. Li W, Dong P, Xiao B et al (2016) Object recognition based on the Region of Interest and optimal Bag of Words model. Neurocomputing 172(C):271–280

    Article  Google Scholar 

  22. Kanamori T (2010) Deformation of log-likelihood loss function for multiclass boosting. Neural Netw 23(7):843–864

    Article  Google Scholar 

  23. Girshick R (2015) Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, pp 1440–1448. https://doi.org/10.1109/iccv.2015.169

  24. He K, Zhang X, Ren S et al (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1026–1034

  25. Nesterov Y, Spokoiny V (2017) Random gradient-free minimization of convex functions. Found Comput Math 17(2):527–566

    Article  MathSciNet  Google Scholar 

  26. Botev A, Lever G, Barber D (2017) Nesterov’s accelerated gradient and momentum as approximations to regularised update descent. In: 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, pp 1899–1903. https://doi.org/10.1109/ijcnn.2017.7966082

  27. Liu W, Wen Y, Yu Z et al (2016) Large-margin Softmax loss for convolutional neural networks. In: Proceedings of the 33rd International Conference on Machine Learning, pp 507–516

  28. Kline DM, Berardi VL (2005) Revisiting squared-error and cross-entropy functions for training neural network classifiers. Neural Comput Appl 14(4):310–318

    Article  Google Scholar 

  29. Guo S, Liu X, Wang Z (2017) Unified method for vehicle detection and attribute recognition. J Image Gr 22(11):1503–1511

    Google Scholar 

  30. Zhang T, Cai R, Li Z et al (2012) Hierarchical object representations for visual recognition via weakly supervised learning. In: Asian Conference on Computer Vision. Springer, pp 474–485

  31. Weng Y, Tian Y, Lu D et al (2017) Fine-grained bird classification based on deep region networks. J Image Gr 22(11):1521–1531

    Google Scholar 

Download references

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China (Grant No. 41877527) and Natural Science Basic Research Plan in Shaan Xi Province of China (Program No. 2016JM6023).

Author information

Authors and Affiliations

  1. School of Management, Xi’an University of Architecture and Technology, Xi’an, China

    Xinsheng Zhang & Zhe Wang

Authors
  1. Xinsheng Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Zhe Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Xinsheng Zhang.

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

Zhang, X., Wang, Z. A microcalcification cluster detection method based on deep learning and multi-scale feature fusion. J Supercomput 75, 5808–5830 (2019). https://doi.org/10.1007/s11227-019-02867-w

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-019-02867-w

Keywords