Analysis and Comparison of Kidney Stone Detection using Minimum Distance to Mean Classifier and Bayesian Classifier with Improved Classification Accuracy

Aim: The goal of this research is to use minimum distance to mean classifier and bayesian classifiers to predict and detect kidney stones. Materials and Methods: This investigation made use of a collection of data from Kaggle website. Samples were collected (N=10) for normal kidney images and (N=10) for kidney with stone images. Total sample size was calculated using clinical.com. As a result the total number of samples 20 was considered for analysis. Using Matlab software and a standard data set collected from Kaggle website, the classification accuracy was obtained. Pretest G power taken as 85 in sample size calculation can be done through clinical.com. Results: The accuracy (%) of both classification techniques are compared using SPSS software by independent sample t-tests. There is a statistical significant difference between minimum distance to mean classifier and Bayesian classifier.Comparison results show that innovative minimum distance to mean classifier give better classification with an accuracy of (78.85%) than bayesian classifiers (71.1314%).There is a statistical significant difference between minimum distance to mean classifier and bayesian classifiers. The Minimum Distance to Mean classifier with p=0.708, p>0.05 insignificant and showed better results in comparison to Bayesian classifiers. Conclusion: The Minimum Distance to Mean Classifier appears to give better accuracy than the Bayesian Classifiers.