| publication name | Automated Multi-Class Skin Cancer Classification through Concatenated Deep Learning Models |
|---|---|
| Authors | Rana Hassan Bedeir, Rasha Orban Mahmoud, Hala H. Zayed |
| year | 2022 |
| keywords | Classification, Deep learning, HAM10000, ResNet50, Skin cancer |
| journal | IAES International Journal of Artificial Intelligence (IJ-AI). |
| volume | 11 |
| issue | 2 |
| pages | 764-772 |
| publisher | Not Available |
| Local/International | International |
| Paper Link | https://ijai.iaescore.com/index.php/IJAI/article/view/21359#:~:text=This%20paper%20tries%20to%20get%20the%20most%20accurate,of%20these%20two%20techniques%20through%20the%20concatenate%20function. |
| Full paper | download |
| Supplementary materials | Not Available |
Abstract
Skin cancer is the most annoying type of cancer diagnosis according to its fast spread to various body areas, so it was necessary to establish computer-assisted diagnostic support systems. State-of-the-art classifiers based on convolutional neural networks (CNNs) are used to classify images of skin cancer. This paper tries to get the most accurate model to classify and detect skin cancer types from seven different classes using deep learning techniques; ResNet-50, VGG-16, and the merged model of these two techniques through the concatenate function. The performance of the proposed model was evaluated through a set of experiments on the HAM10000 database. The proposed system has succeeded in achieving a recognition accuracy of up to 94.14%.