A Deep Neural Network Approach to Detect and Classify Skin  Cancer

Aurooj Farooq Jeelani; Monika Mehra; Ravinder Pal Singh

doi:10.55524/

Authors

Aurooj Farooq Jeelani M. Tech Scholar, Department of Electronics and Communications Engineering, RIMT University, Mandi Gobingarh, Punjab, India Author
Monika Mehra Professor & Head, Department of Electronics and Communications Engineering, RIMT University, Mandi Gobingarh, Punjab, India Author
Ravinder Pal Singh Technical Head and Professor, Department of Research, Innovation & Incubation, RIMT University, Mandi Gobingarh, Punjab, India Author

DOI:

https://doi.org/10.55524/

Keywords:

Skin Cancer, CNN, Deep Learning, Kaggle, Python

Abstract

Among all cancers, skin cancer is one of the serious disease which effects major population across the globe. If the detection and diagnosis would not happen in early stages it can be spread to other body parts rapidly from sunlight because the tissues and skin cells get effected when exposed to sunlight. Although there are many systems available with the medical industry but this research is proposed to improve the performance of existing system by employing deep learning feature of Artificial Intelligence (AI) using Convolution Neural Networks (CNN), where Convolution Neural Networks (CNN) has been implemented using 3x3 and 5x5 matrix along with Graphical User Interface (GUI) generation so to provide better user experience (UX). This research accomplished the desired parameters with values to achieve 80.55% accuracy and 0.63% loss while training and testing the model. The research has been supported with the datasets from kaggle and International Symposium on Biomedical Imaging (ISBI) 2019 contest collection with 6,594 RGB photos. The data set contains nine clinical types skin cancer, such as actinic keratosis, basal cell carcinoma, benign keratosis, dermatofibroma, melanoma, nevus, seborrheic keratosis, squamous cell carcinoma, vascular lesions. The performance of the proposed research has been correlated and compared with the existing techniques i.e. Visual Geometry Group 16 (VGG16) and VGG19.

Downloads

Download data is not yet available.

References

M. Celebi, Y. Aslandogan, W. Stoecker, H. Iyatomi, H. Oka and X. Chen, "Unsupervised border detection in dermoscopy images," Skin Research andTechnology, vol. 13, no. 4, pp. 454-462, 2007.

M. Fleming, C. Steger and e. al., "Techniques for a structural analysis of dermatoscopic imagery," Computerized Medical Imaging and Graphics, vol. 22, no.5, pp. 375-389, 1998.

E. Proksch, J. Brandner and J. Jensen, "The skin: an indispensable barrier,"Experimental Dermatology, vol. 17, no. 12, pp. 1063-1072, 2008.

K. Madison, ""Barrier function of the skin: "la raison d'être" of the epidermis"," JInvest Dermatol, vol. 121, no. 2, pp. 231-241, 2003.

M. Stücker, A. Struk, P. Altmeyer, M. Herde, H. Baumgärtl and D. Lübbers, "The cutaneous uptake of atmospheric oxygen contributes significantly to the oxygen supply of human dermis and epidermis," The Journal of Physiology,

vol. 538, no. 3,pp. 985-994, 2002.

T. DiChiara, "Pictures of Moles and Melanoma skin cancer – Learn o tell thedifference with pictures.”, 2010. [7] B. Hibler, Q. Qi and A. Rossi, "Current state of imaging in dermatology," Seminars in Cutaneous Medicine and Surgery, vol. 35, no. 1, pp. 2-8, 2016.

M. Thoma, Analysis and Optimization of Convolutional Neural Network Architectures, Department of Computer Science, FZI Research Center of InformationTechnology, 2017.

D. Gutman, N. Codella, E. Celebi, B. Helba, M. Marchetti, N. Mishra and A. Halpern,"Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International”, 2016.

Kawahara J, BenTaieb A, Hamarneh G. Deep features to classify skin lesions. Proceedings of the 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI); 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI); April 13-16, 2016; Prague, Czech Republic. 2016.

Nasr-Esfahani E, Samavi S, Karimi N, Soroushmehr SMR, Jafari MH, Ward K, Najarian K. Melanoma detection by analysis of clinical images using convolutional neural network. Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); August 16-20, 2016; Orlando, FL. 2016.

DeVries T., Ramachandram D. Skin Lesion Classification Using Deep Multi-Scale Convolutional Neural Networks. [(accessed on 13 February 2021)];arXiv. 2017

Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017 Dec 02;542(7639):115–118.

Noortaz R., Mohammad S., Karl A. Detection and Classification of Skin Cancer Using a Parallel CNN Model; 2020 IEEE International Women in Engineering (WIE) Conference; 978-0-7381-3144-3/2020

Wermter S., Weber C., Duch W., Honkela T., Koprinkova Hristova P., Magg S., Palm G., Villa A.E.P., editors. Artificial Neural Networks and Machine Learning– ICANN 2014. Volume 8681. Springer International Publishing; Cham, Switzerland: 2014. pp. 837–844.