Abstract
There are various of skin pigmented lesions with high risk. Melanoma is one of the most dangerous forms of skin cancer. It is one of the important research directions of medical artificial intelligence to carry out classification research of skin pigmented lesions based on deep learning. It can assist doctors to make clinical diagnosis and make patients receive treatment as soon as possible to improve survival rate. Aiming at the similar and imbalanced dermoscopic image data of pigmented lesions, this paper proposes a deep residual network improved by Squeeze-and-Excitation module, and dynamic update class-weight, in batches, with model ensemble adjustment strategies to change the attention of imbalanced data. The results show that the above method can increase the average precision by 9.1%, the average recall by 15.3%, and the average F1-score by 12.2%, compared with the multi-class classification using the deep residual network. Thus, the above method is a better classification model and weight adjustment strategy.
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
Conic, R.Z., Cabrera, C.I., Khorana, A.A., et al.: Determination of the impact of melanoma surgical timing on survival using the national cancer database. J. Am. Acad. Dermatol. 78(1), 40–46 (2017)
Cancer Facts and Figures (2019). https://www.cancer.org. Last accessed 10 May 2019
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2017)
Esteva, A., Kuprel, B., Novoa, R.A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115–118 (2017)
Vasconcelos, C.N., Vasconcelos, B.N.: Experiments using deep learning for dermoscopy image analysis. Pattern Recognit. Lett. 16(3), 68–77 (2017)
Ge, Z., Demyanov, S., Bozorgtabar, B., et al.: Exploiting local and generic features for accurate skin lesions classification using clinical and dermoscopy imaging. In: IEEE International Symposium on Biomedical Imaging (2017)
Yu, L., Chen, H., Dou, Q., et al.: Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE Trans. Med. Imag. 36(4), 994–1004 (2017)
Li, Y., Shen, L.: Skin lesion analysis towards melanoma detection using deep learning network. Sensors 18(2), 322 (2005)
Svetnik, V., Wang, T., Tong, C., et al.: Boosting: an ensemble learning tool for compound classification and QSAR modeling. J. Chem. Inf. Model. 45(3), 786–799 (2005)
Tschandl, P., Rosendahl, C., Kittler, H.: The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5, 180161 https://doi.org/10.1038/sdata.2018.161 (2018)
Codella, N., et al.: Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC). https://arx-iv.org/abs/1902.03368
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. Comput. Vis. Pattern Recogn. 770–778 (2016)
Xie, S., Girshick, R., Dollar, P., et al.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society (2017)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Keras. https://keras.io. Last accessed 10 May 2019
Tensorflow. https://tensorflow.google.cn. Last accessed 5 Apr 2019
Lin, M., Chen, Q., Yan, S.: Network in network (2013). https://arxiv.org/abs/1312.4400
Acknowledgments
This study was financially supported by program Research on Artificial Intelligence Innovation Technology for Mental Health Service, which is funded by the Beijing High-level Foreign Talents Subsidy Program 2019. The program number is Z201919. Our team continues to conduct research on artificial intelligence and big data analytics in the medical field, hoping to help human health with the power of data. And we are grateful to all study participants.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Qi, Y., Lin, S., Huang, Z. (2019). Classification of Skin Pigmented Lesions Based on Deep Residual Network. In: Wang, H., Siuly, S., Zhou, R., Martin-Sanchez, F., Zhang, Y., Huang, Z. (eds) Health Information Science. HIS 2019. Lecture Notes in Computer Science(), vol 11837. Springer, Cham. https://doi.org/10.1007/978-3-030-32962-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-32962-4_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32961-7
Online ISBN: 978-3-030-32962-4
eBook Packages: Computer ScienceComputer Science (R0)