A Novel Medical Image Enhancement Method Based on Wavelet Multi-Resolution Analysis and Image Processing Techniques

Abstract

Aim- The aim of this paper is multi resolution analysis for medical image segmentation with Watershed transform method in comparison with Wavelet transforms to enhance the efficiency of the system. Materials and methods- The data set in this paper utilizes the Kaggle data set, which contains sample size 100 (Group 1=50 and Group 2 =50) to determine the resolution. Multi resolution analysis for medical image segmentation for improving accuracy is performed by Watershed transformand Wavelet transformstechniques. Result- The accuracy rate of Wavelet transforms is 92.122% whereas results of Watershed transform method accuracy rate are 87.1223%. The sensitivity rate is 93.67%for the Wavelet transformswhereas the results of Watershed transform method sensitivity rate are 88.823%. The specificity rate is 92.122% for Wavelet transforms whereas results of Watershed transform method specificity rate are 88.1223%. There is a significant difference in accuracy rate (P=0.0376). Conclusion – Wavelet transforms provides the better performance in finding the accuracy, sensitivity and specificity for multi resolution analysis in medical image segmentation when compared to Watershed transform method.