Identifying the Porous Bones in CT Scan Dataset Bone using Enhanced Residual Network over Traditional Convolutional Neural Network

Abstract

Aim: The aim of this study is to identify the porous bones by using the proposed Enhanced Residual Network over Traditional CNN Algorithm. Materials and Methods: Sample groups that are considered in this project is CT Scan dataset that can be classified into two, one for Enhanced Residual Network and other for Traditional CNN, Dataset are tested using 233.9s for Gpower to determine the sample size and for train set analysis.Nearly 215 CT Scan images have been used in each group for testing of cancer. Results: Enhanced Residual Network has better efficiency(79%) when compared to Traditional CNN algorithm efficiency(70%). Statistical significance difference (two-sided) is 0.01 (p<0.05). Conclusion: Enhanced Residual Network algorithm performed significantly better than the Traditional CNN algorithm.