Detecting Osteoporosis using Novel Multitask Cascaded Convolutional Neural Network over Traditional CNN Algorithm

Abstract

Aim: The aim of this study is to detect bone cancer by using the proposed Novel Multitask Cascaded Convolutional Neural 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 Novel Multitask Cascaded CNN and other for Traditional CNN, Dataset are tested for G-power 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: Novel Multitask Cascaded Convolutional Neural Network algorithm has better efficiency (86%) when compared to Traditional CNN algorithm efficiency (75%). Statistical significance difference (two-sided) is 0.01 (p<0.05). Conclusion: Novel Multitask Cascaded Convolutional Neural Network algorithm performed significantly better than the Traditional CNN algorithm.