Detection of Malignant and Benign skin lesions using residual neural network 152 V2 and compare the accuracy with convolutional neural network

The aim of this1research work is to detect Malignant and Benign skin lesions using Residual Neural Network- 152 V2 and compare the accuracy with Convolutional Neural Network. This study investigates the ability of two machine learning algorithms, a new approach called Novel Residual Neural Network-1...

Full description

Saved in:
Bibliographic Details
Main Authors: Nivyashree, T., Pramila, P. V., Kumar, K. S. Sathish, Durumutla, V.
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Algorithms
Artificial neural networks
Cancer
Datasets
Lesions
Machine learning
Medical screening
Neural networks
Skin cancer
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The aim of this1research work is to detect Malignant and Benign skin lesions using Residual Neural Network- 152 V2 and compare the accuracy with Convolutional Neural Network. This study investigates the ability of two machine learning algorithms, a new approach called Novel Residual Neural Network-152 and a more established method called Convolutional Neural Network, to distinguish between malignant and benign skin lesions detected by a cancer screening system. The researchers evaluated a total of N=10 samples. The training dataset includes 1440 benign and 1197 malignant samples, while the test dataset contains 300 images each of benign and malignant. The G power values are 0.8 with 95% confidence interval. The Novel Residual Neural Network-152 V2 accuracy for predicting skin cancer is 84.2%, and the Convolutional Neural Networks accuracy is 76.3%. The statistically significant value for the T test between the two groups is p
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0229255