Back to Search Start Over

An adaptive optimum weighted mean filter and bilateral filter for noise removal in cardiac MRI images

Authors :
R. Radhika
Rashima Mahajan
Source :
Measurement: Sensors, Vol 29, Iss , Pp 100880- (2023)
Publication Year :
2023
Publisher :
Elsevier, 2023.

Abstract

Medical diagnosis greatly benefits from the use of MRI images. There have been many MRI image enhancement algorithms proposed over the years to aid doctors in disease diagnosis. Conventional image enhancing methods, nevertheless, may also boost the noise that was already there in the captured picture, which might cause distortion, which is unfavourable for the disease diagnosis. Therefore, an appropriate technique for noise suppression is necessary. An attempt has been made to incorporate a two-step filtering based algorithm for noise removal in cardiac MRI images while maintaining the images crucial compositional elements, such as their borders and textures. A combination of adaptive optimum weighted mean filter (AOWMF) and bilateral filter (BF) has been implemented to reduce impulsive noise and Gaussian noise that are both present as mixed noise. The fundamental idea of the AOWMF approach includes the detection of noise pixels using Crow Optimization Algorithm (COA), and replacing them with an optimum weighted mean value depending on a criterion of maximization fitness function. Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) have been used to assess the effectiveness of the employed noise reduction technique. The result analysis are experimented in MATLB which reveals that proposed method is able to achieve high PSNR and SSIM and further, this method has the potential to enhance more detail structures of the input cardiac MRI images than existing methods.

Details

Language :
English
ISSN :
26659174
Volume :
29
Issue :
100880-
Database :
Directory of Open Access Journals
Journal :
Measurement: Sensors
Publication Type :
Academic Journal
Accession number :
edsdoj.781dc935805f4816a68d64e60fa5d299
Document Type :
article
Full Text :
https://doi.org/10.1016/j.measen.2023.100880