Article: Efficient de-noising brain MRI images using various filtering techniques Journal: International Journal of Intelligent Engineering Informatics (IJIEI) 2023 Vol.11 No.2 pp.176 - 190 Abstract: Brain cancer affects millions today. MRI images must be separated, identified, and extracted to locate a brain tumour. This process is complicated and error prone. In order to minimise the limitations, segmentation and categorisation are currently done utilising automatic and semiautomatic techniques. The initial step of image processing is de-noising. The image may become hazy if the noise-reduction technique is not carefully followed. The image may become hazy if the noise-reduction technique is not carefully followed by salt and pepper sounds. Gaussian and speckle noise alter the MRI image. Therefore, getting exact photographs of the brain is a tough undertaking. Different de-noising techniques are performed on MRI scans; each has unique properties. The noise from the provided images is removed in this research effort using a variety of filters, including mean filter (MF), Gaussian filter (GF), Kalman filter (KF) and alpha-trimmed mean filter (ATMF). The outcomes of these techniques are evaluated based on various criteria, including peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) and mean square error (MSE). The outcomes demonstrate how the suggested alpha-trimmed mean filter (ATMF) works better and used for MATLAB execution. Inderscience Publishers - linking academia, business and industry through research

Title: Efficient de-noising brain MRI images using various filtering techniques

Authors: A. Anand Selvakumar; P. Thangaraju

Addresses: PG & Research Department of Computer Science, Bishop Heber College (Autonomous), Tiruchirappalli, Tamil Nadu, India; Affiliated to: Bharathidasan University, India ' PG & Research Department of Computer Science, Bishop Heber College (Autonomous), Tiruchirappalli, Tamil Nadu, India; Affiliated to: Bharathidasan University, India

Abstract: Brain cancer affects millions today. MRI images must be separated, identified, and extracted to locate a brain tumour. This process is complicated and error prone. In order to minimise the limitations, segmentation and categorisation are currently done utilising automatic and semiautomatic techniques. The initial step of image processing is de-noising. The image may become hazy if the noise-reduction technique is not carefully followed. The image may become hazy if the noise-reduction technique is not carefully followed by salt and pepper sounds. Gaussian and speckle noise alter the MRI image. Therefore, getting exact photographs of the brain is a tough undertaking. Different de-noising techniques are performed on MRI scans; each has unique properties. The noise from the provided images is removed in this research effort using a variety of filters, including mean filter (MF), Gaussian filter (GF), Kalman filter (KF) and alpha-trimmed mean filter (ATMF). The outcomes of these techniques are evaluated based on various criteria, including peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) and mean square error (MSE). The outcomes demonstrate how the suggested alpha-trimmed mean filter (ATMF) works better and used for MATLAB execution.

Keywords: de-noising; MRI brain images; segmentation; filter; mean filter; Gaussian filter; Kalman filter; alpha-trimmed mean filter; ATMF.

DOI: 10.1504/IJIEI.2023.132703

International Journal of Intelligent Engineering Informatics, 2023 Vol.11 No.2, pp.176 - 190

Received: 16 Feb 2023
Accepted: 11 Apr 2023
Published online: 08 Aug 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Efficient de-noising brain MRI images using various filtering techniques

Keep up-to-date