| A Comparative Study for Skin Cancer Optimization Based on Deep Learning Techniques |
| Paper ID : 1071-ICEEM2023 (R1) |
| Authors: |
|
Talaat Abdelhamid *1, Ahmed A. Mageed2, Samah Abdel Aziz3, Ayman E. EL-SAYED4 1Physics and Mathematical Engineering Department, Faculty of Electronic Engineering, Menoufiya University, Menouf 32952, Egypt. 2Computer Science and Engineering, Faculty of Electronic Engineering, Menoufiya University, Egypt. 3Faculty of Science, Zagazig University, Zagazig, 44519, Egypt 4Menoufia University |
| Abstract: |
| Skin cancer is a significant public health concern, necessitating accurate and timely detection for effective treatment. Deep learning models have emerged as promising tools for skin cancer classification, demonstrating remarkable accuracy in various studies. However, the performance of deep learning models heavily relies on the choice of the optimizer, which affects the training process and convergence speed. This paper investigates the accuracy variance between optimizers in deep-learning models for skin cancer classification. Different deep learning architectures, such as convolutional neural networks (CNNs) are implemented on HAM 10000 (Human Against Machine) dataset to train the skin cancer classification models. The obtained results compare different optimizers such as Root Mean Square Propagation (RMSProp), Nadam, AdaDelta, Stochastic Gradient Descent (SGD), Adamax, Adagrad, Adam, and Adam-M, in terms of the model accuracy. As a future direction, we recommend hybrid techniques and modifications of Adam technique. |
| Keywords: |
| Skin cancer, Deep learning, Medical image classification, Dermoscopy |
| Status : Paper Accepted |
