Filtering methods in speckle noise reduction in biomedical images

2022

Full text Open access: Green Metadata (CSL-JSON)
DOI 10.1117/12.2664480
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

A review of the methods of filtering ultrasound images on the example of hip dysplasia images is presented, their advantages and disadvantages are shown. Demonstrated ways of computer diagnostics of Hip dysplasia development. The method of filtration of the speckle noise of ultrasonic images of the hip dysplasia was proposed. The proposed method focuses on Gaussian blur effects. The idea of the method is that performs a logical AND operation between the original input image and two another images processed Gaussian filtering. The algorithm was tested on the tested images, as well as on real ultrasound images of hip dysplasia.