Abstract
Melanoma is one of the most aggressive types of skin cancer as it rapidly spreads to various areas of the body. With the increase and fatal nature of melanoma, it is of utmost importance to establish computer assisted diagnostic support systems to aid physicians in diagnosing skin cancer. In this paper, we make use of deep learning and transfer learning by testing 14 pre-trained models for the classification and detection of skin cancer. Historically, the data in which Deep Convolutional Neural Networks are fed and trained on comes predominantly from European datasets resulting in biased data. To overcome this issue, we first determine the differences of melanoma that lie within people of different skin tones. Thereafter, we make use of the GrabCut segmentation technique to accurately segment the lesion from the surrounding skin tone in order to solely focus on the lesion. The pre-trained CNN, Squeezenet1-1, achieved the best experimental results with an accuracy rate of 93.42%, sensitivity of 92.11% and specificity of 94.74%. The experimental results achieved indicate that there is a possible solution to the underrepresented data of dark-skinned people.
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
Assogba, M., Vianou, A., Azehoun-Pazou, G.: A method of automatic black skin lesion’s macroscopic image analysis Géraud Azehoun-Pazou Letia Epac 01 BP 2009 Cotonou Rep BENIN, 4, 2278–7720 (2014)
Skin Cancer Foundation. https://www.skincancer.org/. Accessed 16 July 2019
Skin Cancer Facts. www.skincancer.org/skin-cancer-information/skin-cancer-fact. Accessed 18 Apr 2019
Zhang, Y.J., Tavares, J.M.R.S.: Computational Modeling of Objects Presented in Images: Fundamentals, Methods, and Applications. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-319-09994-1
Brinker, T., et al.: Skin cancer classification using convolutional neural networks: systematic review (2018)
AI-Driven dermatology could leave dark-skinned patients behind. https://www.theatlantic.com/health/archive/2018/08/machine-learning-dermatology-skin-color/567619/. Accessed 21 July 2019
Fujisawa, Y., et al.: Deep learning-based, computer-aided classifier developed with a small dataset of clinical images surpasses board-certified dermatologists in skin tumor diagnosis. Br. J. Dermatol. (2018). https://doi.org/10.1111/bjd.16924
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
A simple way to understand machine learning vs deep learning. https://www.zendesk.com/blog/machine-learning-and-deep-learning/. Accessed 23 July 2019
Haenssle, H.A., et al.: Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann. Oncol. 29, 1836–1842 (2018)
What’s new in digital health. https://www.dermengine.com/blog/artificial-intelligence-in-dermatology-diagnosis-deep-learning. Accessed 17 July 2019
Pillay, V., Viriri, S.: Skin cancer detection from macroscopic images, pp. 1–9 (2019). https://doi.org/10.1109/ICTAS.2019.8703611
Cancer facts and figures. https://www.cancer.org/research/cancer-facts-statistics/all-cancer-facts-figures/cancer-facts-figures-2019.html. Accessed 11 Sept 2019
Hu, S., Soza-Vento, R.M., Parker, D.F., et al.: Comparison of stage at diagnosis of melanoma among Hispanic, black, and white patients in Miami-Dade County, Florida. Arch Dermatol. 142(6), 704–8 (2006)
Skin Cancer Foundation. https://www.skincancer.org/blog/ask-the-expert-is-there-a-skin-cancer-crisis-in-people-of-color. Accessed 11 Sept 2019
Skin Cancer Foundation. Skin Cancer Facts and Statistics. https://www.skincancer.org/skin-cancer-information/skin-cancer-facts/. Accessed 11 Sept 2019
AIM at Melanoma Foundation. Melanoma in People of Colour. https://www.aimatmelanoma.org/melanoma-risk-factors/melanoma-in-people-of-color/. Accessed 11 Sept 2019
Parvathy, R., Livingston, J.: A review on various graph cut based image segmentation schemes (2013)
Franke, M.: Color image segmentation based on an iterative graph cut algorithm using time-of-flight cameras. In: Mester, R., Felsberg, M. (eds.) DAGM 2011. LNCS, vol. 6835, pp. 462–467. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23123-0_49
Kulkarni, M., Nicolls, F.: Interactive image segmentation using graph cuts. In: Proceedings of 20th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA 2009), Stellenbosch, South Africa (2009)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019). https://doi.org/10.1186/s40537-019-0197-0
Abbas, Q., Emre Celebi, M., Garcia, I.F., Ahmad, W.: Melanoma recognition framework based on expert definition of ABCD for dermoscopic images. Skin Res. Technol. 19, e93–e102 (2013). https://doi.org/10.1111/j.1600-0846.2012.00614.x
Giotis, I., Molders, N., Land, S., Biehl, M., Jonkman, M.F., Petkov, N.: MED-NODE: a computer-assisted melanoma diagnosis system using non-dermoscopic images. Expert Syst. Appl. 42(19), 6578–6585 (2015). https://doi.org/10.1016/j.eswa.2015.04.034
Dermatology database used in MED-NODE. http://www.cs.rug.nl/~imaging/databases/melanoma_naevi/. Accessed 9 Aug 2019
Derm101. http://www.dermquest.com. Accessed 9 Aug 2019
DermIs. http://www.dermis.net. Accessed 9 Aug 2019
Jia, D., Wei, D., Richard, S., Li-Jia, L., Kai, L., Li, F.-F.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009 (2009)
An introduction to transfer learning in machine Learning. https://medium.com/kansas-city-machine-learning-artificial-intelligen/an-introduction-to-transfer-learning-in-machine-learning-7efd104b6026. Accessed 20 Aug 2019
Transfer learning introduction. https://www.hackerearth.com/practice/machine-learning/transfer-learning/transfer-learning-intro/tutorial/. Accessed 20 Aug 2019
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)
Vision Transform. https://docs.fast.ai/vision.transform.html. Accessed 20 Aug 2019
Batch normalization in neural networks. https://towardsdatascience.com/batch-normalization-in-neural-networks-1ac91516821c. Accessed 20 Aug 2019
Accelerate the training of deep neural networks with batch normalization. https://machinelearningmastery.com/batch-normalization-for-training-of-deep-neural-networks/. Accessed 20 Aug 2019
Matthews correlation coefficient. https://en.wikipedia.org/wiki/Matthews_correlation_coefficient. Accessed 20 Aug 2019
Goyal, M., Yap, M.H.: Multi-class semantic segmentation of skin lesions via fully convolutional networks (2017)
Mendes, D.B., Silva, N.C.: Skin lesions classification using convolutional neural networks in clinical images. CoRR, abs/1812.02316 (2018)
Han, S.S., et al.: Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm. J. Invest. Dermatol. 138, 1529–1538 (2018)
Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017)
Ramezani, M., Karimian, A., Moallem, P.: Automatic detection of malignant melanoma using macroscopic images. J. Med. Sig. Sens. 4, 281 (2014)
Shalu, Kamboj, A.: A color-based approach for melanoma skin cancer detection. In: First International Conference on Secure Cyber Computing and Communication (ICSCCC), Jalandhar, India, pp. 508–513 (2018). https://doi.org/10.1109/ICSCCC.2018.8703309
Hosny, K., Kassem, M., Fouad, M.: Skin cancer classification using deep learning and transfer learning (2018). https://doi.org/10.1109/CIBEC.2018.8641762
Nasr-Esfahani, E., et al.: Melanoma detection by analysis of clinical images using convolutional neural network. In: 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, 2016, pp. 1373–1376 (2016) https://doi.org/10.1109/EMBC.2016.7590963
Ly, P., Bein, D., Verma, A.: New compact deep learning model for skin cancer recognition. In: 9th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pp. 255–261 (2018)
Kalouche, S.: Vision-based classification of skin cancer using deep learning (2016). https://www.semanticscholar.org/paper/Vision-Based-Classification-ofSkin-Cancer-usingKalouche/b57ba909756462d812dc20fca157b3972bc1f533
Mendonça, T., Ferreira, P., Marques, J., Marçal, A., Rozeira, J.: PH2 - A dermoscopic image database for research and benchmarking. In: Conference proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, pp. 5437–5440 (2013). https://doi.org/10.1109/EMBC.2013.6610779
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Pillay, V., Hirasen, D., Viriri, S., Gwetu, M. (2020). Melanoma Skin Cancer Classification Using Transfer Learning. In: Hernes, M., Wojtkiewicz, K., Szczerbicki, E. (eds) Advances in Computational Collective Intelligence. ICCCI 2020. Communications in Computer and Information Science, vol 1287. Springer, Cham. https://doi.org/10.1007/978-3-030-63119-2_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-63119-2_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63118-5
Online ISBN: 978-3-030-63119-2
eBook Packages: Computer ScienceComputer Science (R0)