Title: A novel optimised method for speckle reduction in medical ultrasound images

Authors: V.B. Shereena; G. Raju

Addresses: Department of Computer Applications, MES College, Marampally, Kochi, India ' Department of Data Science, CHRIST (Deemed to be University), Lavasa Campus, Pune, India

Abstract: The advancement of medical imaging techniques evolving from X-ray to PET images and the medical image analysis helped medical experts to detect, diagnose and offer treatments for complex disorders and deadly diseases in the human body. Among the various modalities used, Ultrasound imaging is the most widely accepted modality because of its affordability, non-invasive nature and various other features. But the presence of speckle noise in ultrasound image lowers the image quality and reduces diagnostic value. This article states an improved hybrid speckle noise reduction method, a combined application of Kuan and non-local means filters. In this method, Kuan filter is used to sharpen the edges and thereafter the speckle noise elimination is done by using the non-local means. In addition, the performance of the proposed hybrid filter and its design parameters are optimised by using a meta-heuristic called grey wolf optimiser. The performance of hybrid method is evaluated by analysing a chosen set of well-known post filtering methods used for speckle reduction with given ultrasound B-mode images. The comparison of test results using remarkable performance metrics and computation time demonstrate that the hybrid method can be used as the efficient speckle reduction method for image analysis.

Keywords: ultrasound image; speckle noise; multiplicative noise; performance metrics; spatial filter; transform domain filter; Kuan filter; non-local means filter; grey wolf optimisation; hybrid filter.

DOI: 10.1504/IJAAC.2022.121123

International Journal of Automation and Control, 2022 Vol.16 No.2, pp.137 - 163

Received: 09 Oct 2019
Accepted: 10 May 2020
Published online: 28 Feb 2022 *

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