Please use this identifier to cite or link to this item: https://gnanaganga.inflibnet.ac.in:8443/jspui/handle/123456789/1107
Title: Classification of Skin Cancer Images Using Convolutional Neural Networks
Authors: Tismeet Singh, Kartikeya Agarwal
Keywords: Computer Vision,
Confusion Matrix
Benign
Convolutional Neural Network
Deep Learning
Gradient Class Activation Maps
Machine Learning
Malignant
Skin Cancer
Transfer Learning
Issue Date: 2022
Publisher: Indian Journal of Computer Science
Abstract: Skin cancer is the most common human malignancy according to American Cancer Society. It is primarily diagnosed visually, starting with an initial clinical screening and followed potentially by der moscopic (related to skin) analysis, a biopsy and histopathological examination. Skin cancer occurs when errors (mutations) occur in the DNA of skin cells. The mutations cause cells to grow out of control and form a mass of cancer cells. The aim of this study was to try to classify images of skin lesions with the help of Convolutional Neural Networks. Deep neural networks show humongous potential for image classification while taking into account the large variability exhibited by the environment. Here, we trained images on the basis of pixel values and classified them on the basis of disease labels. The dataset was acquired from an Open Source Kaggle Repository (Kaggle Dataset) which itself was acquired from ISIC (International Skin Imaging Collaboration) archive. The training was performed on multiple models accompanied with Transfer Learning. The highest model accuracy achieved was over 86.65%. The dataset used is publicly available to ensure credibility and reproducibility of the aforementioned result.
URI: http://gnanaganga.inflibnet.ac.in:8080/jspui/handle/123456789/1107
Appears in Collections:Article Archives

Files in This Item:
File Description SizeFormat 
Classification of Skin Cancer Images Using Convolutional.pdf
  Restricted Access
Classification of Skin Cancer Images Using665.62 kBAdobe PDFView/Open Request a copy


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.