Paper Key : IRJ************869
Author: Reddybattula Nandan Reddy
Date Published: 04 Mar 2024
Abstract
Due to the limited availability of resources, skin cancer is one of the most quickly spreading diseases in the globe. Identification of skin cancer through an accurate diagnosis is essential for a preventative approach in general. Dermatologists struggle to detect skin cancer at an early stage, and in recent years, both supervised and unsupervised learning tasks have made extensive use of deep learning. One of these models, Convolutional Neural Networks (CNN), has surpassed all others in object detection and classification tests. The dataset is screened from MNIST: HAM10000 which consists of seven different types of skin lesions with the sample size of 10015 is used for the experimentation. The data pre-processing techniques like sampling, dull razor and segmentation using autoencoder and decoder is employed. To enhance the model's performance, transfer learning is employed by leveraging pre-trained neural network weights on a large-scale image dataset. Fine-tuning is performed to adapt the network to the specific characteristics of dermatoscopic images. The model is trained and validated on a comprehensive dataset, and its performance is evaluated using various metrics such as sensitivity, specificity, and accuracy.Results demonstrate the efficacy of the proposed deep learning model in accurately classifying skin lesions. The system exhibits a high level of sensitivity and specificity, outperforming traditional methods and showcasing its potential as a valuable tool for dermatologists and healthcare professionals in the early diagnosis of skin cancer. Furthermore, the model's interpretability is explored through attention mechanisms, providing insights into the regions of interest contributing to the classification decision. Because of the lack of resources, skin cancer is one of the diseases that is spreading the fastest in the world. Accurate diagnosis of skin cancer identification is essential for early detection in order to implement preventive measures more broadly. Dermatologists find it difficult to identify skin cancer in its early stages, and deep learning has been used extensively in both supervised and unsupervised learning tasks in recent years. In tests of object detection and classification, Convolutional Neural Networks (CNN), one of these models, has outperformed the others.