Skip to main content
SpringerLink
Log in

Multi-level contexts aggregation for melanoma recognition under feature confusion regularization

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

Abstract

Due to variation in the appearance of the skin lesions, the noisy background, the small training dataset, and label imbalance, it is still a challenging task for melanoma recognition in dermoscopy images. Existing deep convolution network-based approaches usually adopted the global context captured in the fully connection layers (FC) to recognize melanoma, ignoring the local contexts which are beneficial for melanoma recognition. We adopted the DenseNet without FC to keep the maximum multi-scale skin lesion features flowing between layers. An attention module is designed to focus on the local contexts of the skin lesion captured in the intermediate Dense Blocks (InterDBs). After aggregating the local contexts and the global context captured in the last Dense Block (LastDB), the performance of melanoma recognition is improved. We proposed a novel feature confusion regularization, which reduces the Euclidean distance (\({L}_{2}\)) between features of the pair inputs with different labels to prevent the proposed network from extracting excessive discriminative features, specific for the samples in the small training set, and avoid overfitting. We trained the proposed network on the ISIC 2017 without using extra data and tested the robustness of it on the ISIC 2016, ISIC 2019. The experimental results show that our network outperforms the state-of-the-art studies, especially for average precision (0.694) and sensitivity (0.693), which are improved by 2.2 and 3.5%, respectively. Evaluation on the ISIC 2019 indicates our network improves by 8%, 3% for average precision and average sensitivity, respectively, which shows it is robust and suitable for clinical application.

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

Similar content being viewed by others

Data availability

Available.

Code availability

Available.

References

  1. Lequan, Yu., Chen, H., Dou, Qi., Qin, J., Heng, P.-A.: Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE Trans. Med. Imaging 36(4), 994–1004 (2017)

    Article  Google Scholar 

  2. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 2015 International Conference on Learning Representations (ICLR). San Diego, CA (2015)

  3. Bi, L., Kim, J., Ahn, E., Feng, D.: Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks. Available: https://arxiv.org/abs/1703.04197

  4. Devries, T., Ramachandram, D.: Skin lesion classification using deep multi-scale convolutional neural networks. Available: https://arxiv.org/pdf/1703.01402

  5. Zhang, J., Xie, Y., Xia, Y., Shen, C.: Attention residual learning for skin lesion classification. IEEE Trans. Med. Imaging 38(9), 2092–2103 (2019)

    Article  Google Scholar 

  6. Dubey, A., Gupta, O., Guo, P., Raskar, R., Farrell, R., Naik, N.: Pairwise confusion for fine-grained visual classification. In: 2018 European Conference on Computer Vision (ECCV), pp.71–88. Munich, Germany (2018)

  7. Lin, T., Goyal, P., Girshick, R., He, K. Dollár, P.: Focal loss for dense object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2999–3007.Venice (2017)

  8. Huang, G., Liu, Z., Van Der Maaten L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261-2269. Honolulu, HI (2017)

  9. Codella, N.C.F., Gutman, D., et al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). ISBI, pp.168–172. Washington, DC, USA (2018)

  10. Gutman, D., Codella, N.C., Celebi, E., Helba, B., Marchetti, M., Mishra, N.,Halpern, A.: Skin lesion analysis toward melanoma detection: A challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). arXiv preprint http://arxiv.org/abs/1605.01397 (2016)

  11. Combalia, M., Codella, N.C.F., Rotemberg, V., Helba, B., Vilaplana, V., Reiter, O., Carrera, C., Barreiro, A., Halpern, A.C., Puig, S., Malvehy, J.: BCN20000: Dermoscopic lesions in the wild 2019. Available: http://arxiv.org/abs/1908.02288

  12. Perez, F., Vasconcelos, C., Avila, S., Valle, E.: data augmentation for skin lesion analysis. In: ISIC Skin Image Analysis Workshop and Challenge @ MICCAI 2018, pp.303–311. Granada, Spain (2018)

  13. Wei, Z., Song, H., Chen, L., Li, Q., Han, G.: Attention-based denseunet network with adversarial training for skin lesion segmentation. IEEE Access 7, 136616–136629 (2019)

    Article  Google Scholar 

  14. Yang, X.L., Zeng, Z., Yong Yeo, S., Tan, C., Tey, H.L., Su, Y.: A novel multi-task deep learning model for skin lesion segmentation and classification. Available: https://arxiv.org/abs/1703.01025

  15. González-Díaz, I.: Incorporating the knowledge of dermatologists to convolutional neural networks for the diagnosis of skin lesions. 2017. Available: https://arxiv.org/abs/1703.01976

  16. Menegola, A., Tavares, J., Fornaciali, M., Li, L.T., de Avila, S.E.F., Valle, E.: RECOD titans at ISIC challenge 2017. Available: https://arxiv.org/pdf/1703.04819

  17. Yan, Y., Kawahara, J., Hamarneh, G.: Melanoma recognition via visual attention. In: Information Processing in Medical Imaging, pp. 793–804. Springer, Cham (2019)

  18. Codella, N.C.F., Nguyen, Q.-B., Pankanti, S., Gutman, D.A., Helba, B., Halpern, A.C., Smith, J.R.: Deep learning ensembles for melanoma recognition in dermoscopy images. IBM J. Res. Dev. (2017). https://doi.org/10.1147/JRD.2017.2708299

    Article  Google Scholar 

  19. Zhen, Y., Jiang, X., Zhou, F., Qin, J., Ni, D., Chen, S., Lei, B., Wang, T.: Melanoma recognition in dermoscopy images via aggregated deep convolutional features. IEEE Trans. Biomed. Eng. 66(4), 1006–1016 (2019)

    Article  Google Scholar 

  20. Oliveira, R.B., Pereira, A.S., Tavares, J.M.R.: Skin lesion computational diagnosis of dermoscopic images: ensemble models based on input feature manipulation. Comput. Methods Prog. Biomed. 149, 43–53 (2017)

    Article  Google Scholar 

  21. Pathan, S., Prabhu, K.G., Siddalingaswamy, P.: Automated detection of melanocytes related pigmented skin lesions: a clinical framework. Biomed. Signal Process. Control. 51, 59–72 (2019)

    Article  Google Scholar 

  22. Kassem, M.A., Hosny, K., Fouad, M.M.: Skin Lesions Classification Into Eight Classes for ISIC 2019 Using Deep Convolutional Neural Network and Transfer Learning. IEEE Access. 8, 14822–114832 (2020)

    Google Scholar 

Download references

Acknowledgements

Thanks for the support of the National Natural Science Foundation of China (61771056), and the National Key Technologies R & D Program of China (2017YFC0110700)

Funding

The research is supported by the National Natural Science Foundation of China (61771056), and the National Key Technologies R & D Program of China (2017YFC0110700).

Author information

Authors and Affiliations

  1. School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China

    Zenghui Wei, Feng Shi, Lei Chen, Qiang Li & Hong Song

  2. School of Information Engineering, Yellow River Conservancy Technical Institute, Kaifeng, China

    Zenghui Wei

Authors
  1. Zenghui Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Feng Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lei Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qiang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hong Song
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

ZW, HS conceived the idea of the study; ZW, HS designed the proposed method; ZW, FS, LC, and QL collected data and conducted the experiments; ZW, FS interpreted the results; ZW wrote the manuscript; HS revised the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Hong Song.

Ethics declarations

Conflicts of interest

There are no conflicts of interest regarding the publication of this article.

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

Wei, Z., Shi, F., Chen, L. et al. Multi-level contexts aggregation for melanoma recognition under feature confusion regularization. SIViP 16, 411–418 (2022). https://doi.org/10.1007/s11760-021-01949-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-021-01949-8

Keywords

Search

Navigation