| Issue |
ITM Web Conf.
Volume 74, 2025
International Conference on Contemporary Pervasive Computational Intelligence (ICCPCI-2024)
|
|
|---|---|---|
| Article Number | 01001 | |
| Number of page(s) | 13 | |
| Section | Artificial Intelligence and Machine Learning Applications | |
| DOI | https://doi.org/10.1051/itmconf/20257401001 | |
| Published online | 20 February 2025 | |
Assessing Skin Cancer Awareness: A Survey on Detection Methods
1 Department of CSE, Vignan’s Foundation for Science, Technology, and Research, Vadlamudi 522213, Andhra Pradesh, India
2 Department of CSE, Vignan’s Foundation for Science, Technology, and Research, Vadlamudi, Andhra Pradesh, India
billavaishnavi350@gmail.com
nithayapasupuleti2005@gmail.com
shaikhaseena0908@gmail.com
sajidashaik550@gmail.com
Skin cancer is considered one of the most aggressive cancer types and can be difficult to treat once it spreads to other parts of the body.Early diagnosis of this disease is very crucial, as once skin cancer has metastasized, it cannot be effectively treated. Automated systems for the recognition of skin lesions can thereby help in early diagnosis and thus improve the treatment outcome. The work proposed here concerns the image preprocessing techniques such as resizing and normalization followed by grayscale conversion and Canny edge detection of dermatology images for the preprocessing of data for the CNN classification model. Important features include asymmetry, border irregularity, diameter, color, and texture. The CNN looks for initial features such as edges and textures in the convolutional layers that are then max pooled to downsample and reduce computation. Finally, after several rounds of convolution and pooling, the feature maps are flattened and passed into the dense layers to learn high-level complex patterns. It helps prevent overfitting by generalizing a model to predict data which was never seen before.
Key words: ISICdataset / Deeplearning / CNN / Accuracy / Precision / Recall / F1score
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.