Advertisement

Journal of Medical Systems

, 43:283 | Cite as

The Application of Deep Learning in the Risk Grading of Skin Tumors for Patients Using Clinical Images

  • Xin-yu Zhao
  • Xian Wu
  • Fang-fang Li
  • Yi Li
  • Wei-hong Huang
  • Kai Huang
  • Xiao-yu He
  • Wei Fan
  • Zhe Wu
  • Ming-liang Chen
  • Jie Li
  • Zhong-ling Luo
  • Juan Su
  • Bin XieEmail author
  • Shuang ZhaoEmail author
Patient Facing Systems
Part of the following topical collections:
  1. Patient Facing Systems

Abstract

According to diagnostic criteria, skin tumors can be divided into three categories: benign, low degree and high degree malignancy. For high degree malignant skin tumors, if not detected in time, they can do serious harm to patients’ health. However, in clinical practice, identifying malignant degree requires biopsy and pathological examination which is time costly. Furthermore, in many areas, due to the severe shortage of dermatologists, it’s inconvenient for patients to go to hospital for examination. Therefore, an easy to access screening method of malignant skin tumors is needed urgently. Firstly, we spend 5 years to build a dataset which includes 4,500 images of 10 kinds of skin tumors. All instances are verified pathologically thus trustworthy; Secondly, we label each instance to be either low-risk, high-risk or dangerous in which Junctional nevus, Intradermal nevus, Dermatofibroma, Lipoma and Seborrheic keratosis are low-risk, Basal cell carcinoma, Bowen’s disease and Actinic keratosis are high-risk, Squamous cell carcinoma and Malignant melanoma are dangerous; Thirdly, we apply the Xception architecture to build the risk degree classifier. The area under the curve (AUC) for three risk degrees reach 0.959, 0.919 and 0.947 respectively. To further evaluate the validity of the proposed risk degree classifier, we conduct a competition with 20 professional dermatologists. The results showed the proposed classifier outperforms dermatologists. Our system is helpful to patients in preliminary screening. It can identify the patients who are at risk and alert them to go to hospital for further examination.

Keywords

Convolutional neural network Skin tumor Risk grade Preliminary screening 

Notes

Acknowledgements

First, second and third authors contributed equally to this paper. Authors are grateful to all the doctors and nurses in Department of Dermatology, Xiangya Hospital Central South University.

Funding

This research was funded by National Key R&D Program of China (2018YFC0117000), Specialized Basic Work of Science and Technology (2015FY111100) and Hunan Provincial Science and Technology Department (2018SK2092).

Compliance with Ethical Standards

All the authors of this article are aware of the content.

Conflict of Interest

The authors declare that they have no conflict of interest.

Ethical Approval

This article does not contain any studies with human participants performed by any of the authors.

References

  1. 1.
    Apalla, Z., Lallas, A., Sotiriou, E., Lazaridou, E., and Ioannides, D., Epidemiological trends in skin cancer. Dermatol Pract Concept. 7(2):1, 2017.CrossRefGoogle Scholar
  2. 2.
    Wernli, K. J., Henrikson, N. B., Morrison, C. C., Nguyen, M., Pocobelli, G., and Blasi, P. R., Screening for skin cancer in adults: Updated evidence report and systematic review for the US preventive services task force. JAMA. 316(4):436–447, 2016.CrossRefGoogle Scholar
  3. 3.
    Zhao, S., Wu, L., Kuang, Y., Su, J., Luo, Z., Wang, Y., Li, J., Zhang, J., Chen, W., Li, F., and He, Y., Downregulation of CD147 induces malignant melanoma cell apoptosis via the regulation of IGFBP2 expression. Int J Oncol. 53(6):2397–2408, 2018.PubMedPubMedCentralGoogle Scholar
  4. 4.
    de Polo, A., Luo, Z., Gerarduzzi, C., Chen, X., Little, J. B., and Yuan, Z. M., AXL receptor signalling suppresses p53 in melanoma through stabilization of the MDMX–MDM2 complex. J Mol Cell Biol. 9(2):154–165, 2017.CrossRefGoogle Scholar
  5. 5.
    Liu, X. S., Genet, M. D., Haines, J. E., Mehanna, E. K., Wu, S., Chen, H. I., Chen, Y., Qureshi, A. A., Han, J., Chen, X., and Fisher, D. E., ZBTB7A suppresses melanoma metastasis by transcriptionally repressing MCAM. Mol Cancer Res. 13(8):1206–1217, 2015.CrossRefGoogle Scholar
  6. 6.
    Zeng, W., Su, J., Wu, L., Yang, D., Long, T., Li, D., Kuang, Y., Li, J., Qi, M., Zhang, J., and Chen, X., CD147 promotes melanoma progression through hypoxia-induced MMP2 activation. Curr Mol Med. 14(1):163–173, 2014.CrossRefGoogle Scholar
  7. 7.
    Luo, Z., Zeng, W., Tang, W., Long, T., Zhang, J., Xie, X., Kuang, Y., Chen, M., Su, J., and Chen, X., CD147 interacts with NDUFS6 in regulating mitochondrial complex I activity and the mitochondrial apoptotic pathway in human malignant melanoma cells. Curr Mol Med. 14(10):1252–1264, 2014.CrossRefGoogle Scholar
  8. 8.
    Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., and Kim, R., Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA – J Am Med Assoc. 316(22):2402–2410, 2016.CrossRefGoogle Scholar
  9. 9.
    Gurovich, Y., Hanani, Y., Bar, O., Nadav, G., Fleischer, N., Gelbman, D., Basel-Salmon, L., Krawitz, P. M., Kamphausen, S. B., Zenker, M., and Bird, L. M., Identifying facial phenotypes of genetic disorders using deep learning. Nature medicine. 25(1):60, 2019.CrossRefGoogle Scholar
  10. 10.
    Kooi, T., Litjens, G., Van Ginneken, B., Gubern-Mérida, A., Sánchez, C. I., Mann, R., den Heeten, A., and Karssemeijer, N., Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal. 35:303–312, 2017.CrossRefGoogle Scholar
  11. 11.
    Liao, H., A deep learning approach to universal skin disease classification. University of Rochester Department of Computer Science, CSC, 2016.Google Scholar
  12. 12.
    Liao, H., Li, Y., Luo, J., Skin disease classification versus skin lesion characterization: Achieving robust diagnosis using multi-label deep neural networks. In 2016 23rd International Conference on Pattern Recognition (ICPR) 2016 Dec 4 (pp. 355-360). IEEE.Google Scholar
  13. 13.
    Haofu, L, Luo, J., A deep multi-task learning approach to skin lesion classification. InWorkshops at the Thirty-First AAAI Conference on Artificial Intelligence 2017 Mar 21.Google Scholar
  14. 14.
    Sun, X., Yang, J., Sun, M., Wang, K., A benchmark for automatic visual classification of clinical skin disease images. InEuropean Conference on Computer Vision 2016 Oct 8 (pp. 206-222). Springer, Cham.Google Scholar
  15. 15.
    Codella, N. C., Nguyen, Q. B., Pankanti, S., Gutman, D. A., Helba, B., Halpern, A. C., and Smith, J. R., Deep learning ensembles for melanoma recognition in dermoscopy images. IBM Journal of Research and Development. 61(4/5):5–1, 2017.CrossRefGoogle Scholar
  16. 16.
    Yu, L., Chen, H., Dou, Q., Qin, J., and Heng, P. A., Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE Trans Med Imaging. 36(4):994–1004, 2017.CrossRefGoogle Scholar
  17. 17.
    Zhang, J., Xie, Y., Wu, Q., Xia, Y., Skin lesion classification in dermoscopy images using synergic deep learning. In International Conference on Medical Image Computing and Computer-Assisted Intervention 2018 Sep 16 (pp. 12-20). Springer, Cham.CrossRefGoogle Scholar
  18. 18.
    Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., and Thrun, S., Dermatologist-level classification of skin cancer with deep neural networks. Nature. 542(7639):115, 2017.CrossRefGoogle Scholar
  19. 19.
    Han, S. S., Kim, M. S., Lim, W., Park, G. H., Park, I., and Chang, S. E., Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm. J Invest Dermatol. 138(7):1529–1538, 2018.CrossRefGoogle Scholar
  20. 20.
    Haenssle, H. A., Fink, C., Schneiderbauer, R., Toberer, F., Buhl, T., Blum, A., Kalloo, A., Hassen, A. B., Thomas, L., Enk, A., and Uhlmann, L., Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol. 29(8):1836–1842, 2018.CrossRefGoogle Scholar
  21. 21.
    Walker, B. N., Rehg, J. M., Kalra, A., Winters, R. M., Drews, P., Dascalu, J., David, E. O., Dascalu, A., Dermoscopy diagnosis of cancerous lesions utilizing dual deep learning algorithms via visual and audio (sonification) outputs: Laboratory and prospective observational studies. EBioMedicine, 2019.Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of AutomationCentral South UniversityChangshaChina
  2. 2.Tencent Medical AI LabBeijingChina
  3. 3.Department of DermatologyXiangya Hospital Central South UniversityChangshaChina
  4. 4.Hunan Key Laboratory of Skin Cancer and PsoriasisChangshaChina
  5. 5.Hunan Engineering Research Center of Skin Health and DiseaseChangshaChina
  6. 6.Mobile Health Ministry of Education - China Mobile Joint LaboratoryXiangya Hospital Central South UniversityChangshaChina

Personalised recommendations