CLASSIFICATION OF SKIN DISEASES USING DEEP CONVOLUTION NEURAL NETWORK

CLASSIFICATION OF SKIN DISEASES USING DEEP CONVOLUTION NEURAL NETWORK
Author(s):
Dr. P. Ammireddy, Tejaswi Kambhampati, Sahithi Konka, Murali Priya Komaragiri, Prasanna Jonnalagadda
Keywords:
CNN, Dermotoscopic images, Data augmentation, RadomOverSampler.
Abstract
Skin diseases are one of the major issues in the medical sector. Skin diseases include cancer type or non-cancer type. Skin cancer occurs based on serval parameters like a decrease in the quantity of melanin in our body. Small types like lesions and allergies affect our body's skin sometimes these small things come under the noncancer type skin specialists face multiple problems while detecting these diseases because of their color and other many factors. so it is necessary to find the diseases in the early stages to give better treatment as early as possible. For this, we approach deep learning like Convolutional Neural Networks. The proposed algorithm extracts features of images by applying different extra layers to the existing model of CNN to classify the skin diseases into seven diseases actinic keratoses, basal cell carcinoma, benign keratosis-like lesions, dermatofibroma, melanoma, melanocytic nevi, and vascular lesions. This algorithm shows decent results with an accuracy of 98.74% and a precision of 98.85%.
Article Details
Unique Paper ID: 162742 Publication Volume & Issue: Volume 10, Issue 10 Page(s): 913 - 916
Article Preview & Download

Share This Article

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org