Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)

A CNN-Based Approach For The Detectıon Of Skın Cancer

Authors
Smita Rani Sahu1, *, Vaddi Bhargavi1, Kunchala Keerthi1, Itrajula Sai Kumar1, Gara Srikanth1
1Dept of Information Technology, Aditya Institute of Technology and Management, Tekkali, Andhra Pradesh, India
*Corresponding author. Email: smitasahu57@gmail.com
Corresponding Author
Smita Rani Sahu
Available Online 30 July 2024.
DOI
10.2991/978-94-6463-471-6_10How to use a DOI?
Keywords
Skin Disease; Skin Cancer; Convolutional Neural Network; Root Mean Square propagation; Squamous cell carcinoma (SCC); Basal cell carcinoma (BCC)
Abstract

Skin is the largest organ of the body. It frequently deals with a variety of problems indicating internal as well as external factors. Skin issues can be caused by pollutants in the environment, UV radiation, and poor skincare habits. There are many issues related to the skin like acne, sunburn, rosacea, and many more, and one of the major issues is skin cancer. Skin cancer is a type of cancer that originates in the cells of the skin. It can have significant effects on an individual’s health and well-being. It starts as lesions on the skin when early detection is not done or timely medical attention is not taken then it leads to skin cancer. Melanoma, squamous cell carcinoma (SCC), and basal cell carcinoma (BCC) are the three primary varieties of skin cancer. This framework focuses on the detection of skin cancer at an early stage based on the skin imaging data and the dataset used in this paper is collected from Kaggle.com namely Melanomia. From the data, both spatial and sequential patterns are analyzed and also the features are extracted to forecast the occurrence of skin cancer. The dataset used for this paper comprises 3033 images with two different classes. A deep learning-based convolutional neural network is used to perform cancer prediction. Additionally, the activation functions SoftMax and Sigmoid and optimization techniques like Adam, RMSprop, and Nadam are applied to improve the model to make accurate predictions. CNN is used due to its ability to extract information from dermatological photos and also perform better classification by avoiding errors in the dataset. According to the analysis of the experiment results, CNN-RMSprop with a sigmoid activation function outperforms other CNN optimizers with 89.30% accuracy. Therefore, quick action would help minimize losses in skin disease, and the proposed work would be a significant step towards improving the lives of patients in the field of dermatology.

Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
Series
Advances in Computer Science Research
Publication Date
30 July 2024
ISBN
978-94-6463-471-6
ISSN
2352-538X
DOI
10.2991/978-94-6463-471-6_10How to use a DOI?
Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Smita Rani Sahu
AU  - Vaddi Bhargavi
AU  - Kunchala Keerthi
AU  - Itrajula Sai Kumar
AU  - Gara Srikanth
PY  - 2024
DA  - 2024/07/30
TI  - A CNN-Based Approach For The Detectıon Of Skın Cancer
BT  - Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
PB  - Atlantis Press
SP  - 98
EP  - 108
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-471-6_10
DO  - 10.2991/978-94-6463-471-6_10
ID  - Sahu2024
ER  -