Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

TISSUE CHARACTERIZATION BY ULTRASOUND SPECKLE

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  Paper number  033052,  2003 ASAE Annual Meeting . (doi: 10.13031/2013.15001) @2003
Authors:   Zhanqi Cheng, Jinglu Tan, Jeannie Kozak, Moses Hdeib
Keywords:   speckle analysis, ultrasound images, texture descriptor, tissue characterization, segmentation, mutifractal, run length, morphological operation

Ultrasound speckle, which is caused by the interference of the backscattered ultrasound signal, is considered to degrade image quality and is therefore unwanted in images. A variety of research involving the statistical analysis of speckle has been performed and methods have thus been developed to suppress or remove ultrasound speckle from images. Recent evidence has however shown that speckle contains useful information and is part of the signal. Research is therefore currently needed to use speckle to assist recognition of formerly unrecognizable objects.

It is often difficult to differentiate various soft tissues in ultrasound images due to the similarities in their physical (elastic) properties. Since speckle texture in ultrasound images is believed to contain information about internal tissue structures, local area texture analysis was performed on speckle images. Pixel-based features were obtained from multi-scale resolution analysis and pixel value run length analysis. The features were analyzed for their ability to discriminate tissues. After feature selection, multivariate classification techniques were used to differentiate beef muscle from pork muscle in animal ultrasound images. Morphological operations were applied to produce better segmentation. The neural network algorithm classified 84.3% of pixels into the correct class, while using only the ultrasound signal in a similar algorithm correctly classified a mere 71.7%. These results indicate that the developed algorithms can be used in soft tissue differentiation and can be potentially used in medical ultrasound image to help with diagnosis.

(Download PDF)    (Export to EndNotes)