Abstract
The paper presents two methods for automatic identification of skin cancer in forms of melanoma. In the first method we design a Neural Network that help us to classify the skin lesions. The design of the Neural Network is discussed by analyzing the performance of the training process of the network and the number of target classes. The sensitivity, specificity and accuracy are then determined. The second method uses GoogleNet Convolutional Neural Network (CNN), which is pretrained with the large image database ImageNet. The CNN model is then fine-tuned to classify skin lesions using transfer learning. The classification accuracy is also calculated. The results obtained using the two methods were then compared. The experimental results on a free database demonstrates that the second method can provide high accuracy if some conditions are respected when designing the neural networks.
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
Brinker, T.J., et al.: Skin cancer classification using convolutional neural networks: systematic. Rev. J. Med. Internet Res. 20(10), e11936 (2018)
Argenziano, G., Soyer, H,P.: Dermoscopy of pigmented skin lesions: a valuable tool for early diagnosis of melanoma. Lancet Oncol. 2(7), 443–449 (2001)
Ara, A., Deserno, T.M.: A systematic review of automated melanoma detection in dermatoscopic images and its ground truth data. Proc. SPIE Int. Soc. Opt. Eng. 8318, 1–6 (2012)
Fabbrocini, G., et al.: Teledermatology: from prevention to diagnosis of nonmelanoma and melanoma skin cancer. Int. J. Telemed. Appl. 2011(17), 125762 (2011)
Hart, P.E., Stork, D.G., Duda, R.O.: Pattern Classification, 2nd edn. Wiley, Hoboken (2000)
Jianu, S.R.S., Ichim, L., Popescu, D., Chenaru, O.: Advanced processing techniques for detection and classification of skin lesions. In: 22nd International Conference on System Theory, Control and Computing (ICSTCC), pp. 498–503. Sinaia, Romania, 10–12 October 2018
Oliveira, R.B., Papa, J.P., Pereira, A.S., Tavares, J.M.R.S.: Computational methods for pigmented skin lesion classification in images: review and future trends. Neural Comput. Appl. 29(3), 613–636 (2016)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Pomponiu, V., Nejati, H., Cheung, N.M.: Deepmole: deep neural networks for skin mole lesion classification. In: Proceedings of the IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, 25–28 September 2016
Codella, N., Cai, J., Abedini, M., Garnavi, R., Halpern, A., Smith, J.R.: Deep learning, sparse coding, and SVM for melanoma recognition in dermoscopy images. In: 6th International Workshop on Machine Learning in Medical Imaging, pp. 118–126, Munich, Germany, 5–9 October 2015
Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115–118 (2017)
Gutman, D., et al.: Skin lesion analysis toward melanoma detection: a challenge. In: The International Symposium on Biomedical Imaging (ISBI) 2016, Hosted by the International Skin Imaging Collaboration (ISIC) (2016). arXiv, 04 May 2016
https://www.mathworks.com/help/deeplearning/examples/train-deep-learning-network-to-classify-new-images.html. Accessed 20 Jan 2019
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
El-khatib, H., Popescu, D., Ichim, L. (2019). Detection of Cancerous Lesions with Neural Networks. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science(), vol 11507. Springer, Cham. https://doi.org/10.1007/978-3-030-20518-8_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-20518-8_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20517-1
Online ISBN: 978-3-030-20518-8
eBook Packages: Computer ScienceComputer Science (R0)