Abstract
Skin cancer is among the most prominent types of cancer, which if not detected in the initial stages can metastasize and become fatal. As the number of Melanoma cases surges, the interest in using CAD (computer-aided diagnosis) for skin cancer prognosis is also rising. In this work, the proposed methodology is applied to HAM 10,000 dataset containing skin lesion images. This paper aims to implement neural network architectures on pre-processed segmented lesions for labeling the lesion image as benign or malignant. The images from the dataset are first pre-processed to remove the noise present, and then segmentation is performed to separate skin lesion from the background. Textural features are extracted from the segmented lesion, which are later used by perceptron and multilayer perceptron (MLP) for classification. Pre-processed images are classified using transfer learning models (ResNet-50, Inception-V3, MobileNet, Inception-ResNet-V2, and DenseNet201), where DenseNet201 has given the best performance and achieved an accuracy of 93.24% and AUC of 0.932.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cancer. World Health Organization. https://www.who.int/health-topics/cancer#tab=tab_1. Accessed July 06, 2020
Tschandl, P., Rosendahl, C., Kittler, H.: Data descriptor: The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data, vol. 5 (2018). https://doi.org/10.1038/sdata.2018.161
“Cancer Facts and Figures. American Cancer Society, 2021. https://www.cancer.org/content/dam/cancer-org/research/cancer-facts-and-statistics/annual-cancer-facts-and-figures/2021/cancer-facts-and-figures-2021.pdf. Accessed Feb. 23, 2021
Titus, L.J., et al.: Recent skin self-examination and doctor visits in relation to melanoma risk and tumour depth. Br. J. Dermatol. 168(3), 571–576 (2013). https://doi.org/10.1111/bjd.12003
Bhattacharya, A., Young, A., Wong, A., Stalling, S., Wei, M., Hadley, D.: Precision Diagnosis of Melanoma And Other Skin Lesions From Digital Images.,” AMIA Jt. Summits Transl. Sci. proceedings. AMIA Jt. Summits Transl. Sci. vol. 2017, pp. 220–22 (2017). Accessed: Feb. 13, 2021. http://www.ncbi.nlm.nih.gov/pubmed/28815132.
Xin, M., Wang, Y.: Research on image classification model based on deep convolution neural network. Eurasip J. Image Video Process. 2019(1), 1–11 (2019). https://doi.org/10.1186/s13640-019-0417-8
V. Ma and M. V. Karki, “Skin Cancer Detection using Machine Learning Techniques,” Jul. 2020. https://doi.org/10.1109/CONECCT50063.2020.9198489.
W. Sae-Lim, W. Wettayaprasit, and P. Aiyarak, “Convolutional Neural Networks Using MobileNet for Skin Lesion Classification,” in JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence, Jul. 2019, pp. 242–247. https://doi.org/10.1109/JCSSE.2019.8864155.
Ratul, M.A.R., Mozaffari, M.H., Lee, W.S., Parimbelli, E (2019) Skin lesions classification using deep learning based on dilated convolution. bioRxiv. bioRxiv, p. 860700. https://doi.org/10.1101/860700.
“The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions - ViDIR Dataverse. https://doi.org/10.7910/DVN/DBW86T. Aaccessed Feb. 14, 2021.
Rawat, J., Singh, A., Bhadauria, H.S., Virmani, J., Devgun, J.S.: Classification of acute lymphoblastic leukaemia using hybrid hierarchical classifiers. Multimed. Tools Appl. 76(18), 19057–19085 (Sep. 2017). https://doi.org/10.1007/s11042-017-4478-3
Rajinikanth, V., Satapathy, S.C., Dey, N., Fernandes, S.L., Manic, K.S.: Skin melanoma assessment using Kapur’s entropy and level set—A study with bat algorithm. Smart Innovation, Systems and Technologies 104, 193–202 (2019). https://doi.org/10.1007/978-981-13-1921-1_19
Ruela, M., Barata, C., Marques, J.S., Rozeira, J.: A system for the detection of melanomas in dermoscopy images using shape and symmetry features. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 5(2), 127–137 (Mar. 2017). https://doi.org/10.1080/21681163.2015.1029080
Telea, A.: An Image Inpainting Technique Based on the Fast Marching Method. J. Graph. Tools 9(1), 23–34 (Jan. 2004). https://doi.org/10.1080/10867651.2004.10487596
Rawat, J., Virmani, J., Singh, A., Bhadauria, H.S., Kumar, I., Devgan, J.S.: FAB classification of acute leukemia using an ensemble of neural networks. Evol. Intell. (2020). https://doi.org/10.1007/s12065-020-00491-9
Rawat, J., Singh, A., Bhadauria, H.S., Virmani, J., Devgun, J.S.: Computer assisted classification framework for prediction of acute lymphoblastic and acute myeloblastic leukemia. Biocybern. Biomed. Eng. vol. 37, no. 4, pp. 637–654 (2017). https://doi.org/10.1016/j.bbe.2017.07.003.
Haralick, R.M., Shanmugam, K., Dinstein, I.H.: Textural Features for Image Classification. IEEE Trans. Syst. Man Cybern. SMC-3(6), 610–621 (1973). https://doi.org/10.1109/TSMC.1973.4309314.
Rawat, J., Singh, A., Bhadauria, H.S., Virmani, J., Devgun, J.S.: Leukocyte Classification using Adaptive Neuro-Fuzzy Inference System in Microscopic Blood Images. Arab. J. Sci. Eng. 43(12), 7041–7058 (2018). https://doi.org/10.1007/s13369-017-2959-3
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Upadhyay, M., Rawat, J., Maji, S. (2022). Skin Cancer Image Classification Using Deep Neural Network Models. In: Bhateja, V., Tang, J., Satapathy, S.C., Peer, P., Das, R. (eds) Evolution in Computational Intelligence. Smart Innovation, Systems and Technologies, vol 267. Springer, Singapore. https://doi.org/10.1007/978-981-16-6616-2_44
Download citation
DOI: https://doi.org/10.1007/978-981-16-6616-2_44
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6615-5
Online ISBN: 978-981-16-6616-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)