A total variation-undecimated wavelet approach to chest radiograph image enhancement

Matilda Wilson,James B H Acquah,Anthony Y Aidoo

doi:10.12928/telkomnika.v17i4.11911

Abstract

Most often medical images such as X-Rays have a low dynamic range and many of their targeted features are difficult to identify. Intensity transformations that improve image quality usually rely onwavelet denoising and enhancement typically use the technique of thresholding to obtain better quality medical images. A disadvantage of wavelet thresholding is that even though it adequately removes noise in an image, it introduces unwanted artifacts into the image near discontinuities. We utilize a total variation method and an undecimated wavelet image enhancing algorithm for improving the image quality of chest radiographs. Our approach achieves a high level chest radiograph image deniosing in lung nodules detection while preserving the important features. Moreover, our method results in a high image sensitivity that reduces the average number of false positives on a test set of medical data.

Highlights

Frequency and transform domain techniques [1] such as the discrete wavelet transform (DWT) are able to achieve appreciable results in improving the quality of medical images
The objective of this paper is to develop a denoising and enhancement technique that can be used to reduce anatomical and other noises in chest radiographs for better detection sensitivity and specificity of any computer-aided detection and diagnosis (CADD) scheme [3,4,5,6,7]
The chest radiograph (CR) were extracted and classified with the WEKA tool, and the Support Vector Machine (SVM) was used and 80% of all the nodules and normal cases of 247 CRs were used in the training set and 20% as the testing set which yielded an average of 71.9% in sensitivity

Summary

Introduction

Frequency and transform domain techniques [1] such as the discrete wavelet transform (DWT) are able to achieve appreciable results in improving the quality of medical images. A small shift in the input signal is magnified in the form of a major variation in energy distribution in the wavelet coefficients at various scales. Another disadvantage is that wavelets lead to directional selectivity of diagonal features of an image since wavelet filters are separable. In our previous work [1], we implemented an algorithm for total variation (TV) denoising and deblurring of two-dimensional chest radiograph (CR) images.

Objectives

Methods

Results

Conclusion