Real and Complex Valued Ripplet-I Transform for Medical Image Denoising and Analysis of Thresholding Constants and Scales Effects
Journal Title: Journal of Biomedical Engineering and Medical Imaging - Year 2017, Vol 4, Issue 2
Abstract
Medical image processing is an important diagnostic tool in the field of medical. Medical images might be affected by the noises that manipulate the resolution negatively during screening or transmission. These images need to be eliminated so as not to affect the diagnosis success negatively. In medical image denoising studies, using the multi-resolution analysis coefficients is a widely appreciated method. This study tested the success rate of real and complex valued ripplet-I transform for medical image denoising. Thanks to this study, the complex version of the newly suggested ripplet-I transform whose real version was used formerly in various studies was used in a medical image denoising application the first time. In the study tested with 40 liver images, 40 retinal images and 322 mammographic images, peak signal-to-noise ratio (PSNR), mean structural similarity index (MSSIM) and feature similarity index (FSIM) were utilized to compare the successes of image denoising. In the wake of study, it was seen that the complex valued ripplet-I (CVR-I) transform gave better results than the real valued ripplet-I (RVR-I) transform when used in the same image denoising algorithm. This study also examined the effects that the changes in scale and thresholding constant values have on the medical image denoising results, thus making this study appear as a guideline.
Authors and Affiliations
Hüseyin Yaşar
Keywords
Related Articles
- EP ID EP296518
- DOI 10.14738/jbemi. 42.2830
- Views 85
- Downloads 0
Hybrid Algorithm Edge Detected DICOM Image Enhancement and Analysis based on Genetic Algorithm for Evolution and Best Fit Value
The segmentation of a DICOM standard medical image is a necessary technique which is essential for feature extraction, object edge detection and classification of the segments of the image. The DICOM image is partitioned...
Mobile Three Gas Extractor Using Pressure Swing Adsorption Method
This paper deals with a simple approach of producing three gases that are oxygen, nitrogen and pressurized air by using a mobile three gas extractor. Indeed, the proposed medical device integrates the following modules d...
Computational Analysis of Histological Images of Tissue Engineered Cartilage for Evaluation of Scaffold Cell Migration
Human chondrocytes were seeded on porcine collagen scaffolds and cultivated for up to six weeks in a cartilage bioreactor. To evaluate the influence of cultivation parameters on the proliferation and migration of the cel...
Comparative Study of Medical Image Contrast Enhancement using Discrete Wavelet Transform and Dual Tree Complex Wavelet Transform
Image Enhancement is one of the most important preprocessing technique in image processing technology that leads to improvement of contrast and visual appearance of an image to make the original image more appropriate fo...
Semiautomatic Determination of Arterial Input Function in DCE-MRI of the Abdomen
The goal of this study was to develop a semiautomatic segmentation technique of the abdominal aorta to determine the arterial input function (AIF). A total of 24 patients having therapy naïve abdominal cancers were image...