Abstract
Nowadays, skin cancer is one of the most popular diseases which affected by ozone depletion, chemical environmental pollution and so on. It is very important for recognizing and treatments. There are many devices that support to capture high-quality skin image to be able for disease diagnose by expert systems. However, the difficult problem is that extracting region of interesting (ROI) for disease diagnosis. This paper presents an approach candidate diseased region extraction using hybrid deep learning of the Residual neural network (ResNet50) architecture and the Atrous convolutional neural network (ACNN). Then the ROI is fed to recognition system for diseased diagnoses. The imbalance of recall measures between classes affected the performance of existing models is deal with data augmentation technique. The proposed learning architecture is suitable for multi skin diseases segmentation and solved under fitting and avoided overfitting problems, achieved improving performance when used hybrid of learning models. Experimental results illustrated that the segmentation system based on deep feature processing combine with data augmentation reach high accuracy.
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
Schadendorf, D., et al.: Melanoma. Lancet 392, 971–984 (2018)
Carli, P., et al.: Pattern analysis, not simplified algorithms, is the most reliable method for teaching dermoscopy for melanoma diagnosis to residents in dermatology. Br. J. Dermatol. 148, 981–984 (2003)
Combalia, M., et al.: Bcn20000: dermoscopic lesions in the wild, arXiv preprint arXiv:1908.02288 (2019)
Pham, T.C., et al.: A comparative study for classification of skin cancer. In: 2019 International Conference on System Science and Engineering (ICSSE), pp. 267–272 (2019)
Tschandl, P., et al.: Expert-level diagnosis of nonpigmented skin cancer by combined convolutional neural networks. JAMA Dermatol. 155, 58–65 (2019)
Pham, T.-C., et al.: AI outperformed every dermatologist: improved dermoscopic melanoma diagnosis through customizing batch logic and loss function in an optimized Deep CNN architecture, arXiv, pp. 1–21 (2020)
Brinker, T.J., et al.: Comparing artificial intelligence algorithms to 157 German dermatologists: the melanoma classification benchmark. Eur. J. Cancer 111, 30–37 (2019)
Pham, T.-C., Luong, C.-M., Visani, M., Hoang, V.-D.: Deep CNN and data augmentation for skin lesion classification. In: Nguyen, N.T., Hoang, D.H., Hong, T.-P., Pham, H., Trawiński, B. (eds.) ACIIDS 2018. LNCS (LNAI), vol. 10752, pp. 573–582. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75420-8_54
Jha, B.S., Bharti, K.: Regenerating retinal pigment epithelial cells to cure blindness: a road towards personalized artificial tissue. Curr. Stem Cell Rep. 1, 79–91 (2015). https://doi.org/10.1007/s40778-015-0014-4
Majurski, M., et al.: Cell image segmentation using generative adversarial networks, transfer learning, and augmentations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshop (2019)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, William M., Frangi, Alejandro F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Qian, C., et al.: A two-stage method for skin lesion analysis, arXiv preprint arXiv:1809.03917 (2018)
Hasan, S.N., et al.: Skin lesion segmentation by using deep learning techniques. In: 2019 Medical Technologies Congress, pp. 1–4 (2019)
Matsunaga, K., et al.: Image classification of melanoma, nevus and seborrheic keratosis by deep neural network ensemble. ArXiv e-prints (2017)
González-DÃaz, I.: Incorporating the knowledge of dermatologists to convolutional neural networks for the diagnosis of skin lesions. ArXiv e-prints (2017)
Menegola, A., et al.: Towards automated melanoma screening: exploring transfer learning schemes. ArXiv e-prints (2016)
Menegola, A., et al.: Knowledge transfer for melanoma screening with deep learning. ArXiv e-prints (2017)
Menegola, A., et al.: RECOD Titans at ISIC challenge 2017. ArXiv e-prints (2017)
Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017)
Codella, N.C.F., et al.: Deep learning ensembles for melanoma recognition in dermoscopy images. IBM J. Res. Dev. 61(4/5), 5:1–5:15 (2017)
Barata, C., et al.: Improving dermoscopy image classification using color constancy. IEEE J. Biomed. Health Inform. 19, 1146–1152 (2014)
Ercal, F., et al.: Neural network diagnosis of malignant melanoma from color images. IEEE Trans. Biomed. Eng. 41, 837–845 (1994)
Wong, S.C., et al.: Understanding data augmentation for classification: when to warp?. Presented at the Digital Image Computing: Techniques and Applications (DICTA), Gold Coast, QLD, Australia (2016)
He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Luc, P., et al.: Semantic segmentation using adversarial networks, arXiv preprint arXiv:1611.08408 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hoang, VD., Hoang, VT., Jo, KH. (2020). Hybrid Deep Learning and Data Augmentation for Disease Candidate Extraction. In: Ohyama, W., Jung, S. (eds) Frontiers of Computer Vision. IW-FCV 2020. Communications in Computer and Information Science, vol 1212. Springer, Singapore. https://doi.org/10.1007/978-981-15-4818-5_21
Download citation
DOI: https://doi.org/10.1007/978-981-15-4818-5_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-4817-8
Online ISBN: 978-981-15-4818-5
eBook Packages: Computer ScienceComputer Science (R0)