KMID : 1151820150090040227
|
|
Journal of the Korean Society of Radiology 2015 Volume.9 No. 4 p.227 ~ p.234
|
|
Image Analysis of Diffuse Liver Disease using Computer-Adided Diagnosis in the Liver US Image
|
|
Lee Jin-Soo
Kim Chang-Soo
|
|
Abstract
|
|
|
In this paper, we studied possibility about application for CAD on diffuse liver disease through pixel texture analysis parameters(average gray level, skewness, entropy) which based statistical property brightness histogram and image analysis using brightness difference liver and kidney parenchyma. The experiment was set by ROI (50x50 pixels) on liver ultrasound images.(non specific, fatty liver, liver cirrhosis) then, evaluated disease recognition rates using 4 types pixel texture analysis parameters and brightness gap liver and kidney parenchyma. As a results, disease recognition rates which contained average brightness, skewness, uniformity, entropy was scored 100%¡96%, they were high. In brightness gap between liver and kidney parenchyma, non specific was -1.129¡¾12.410 fatty liver was 33.182¡¾11.826, these were shown significantly difference, but liver cirrhosis was -1.668¡¾10.081, that was somewhat small difference with non specific case. Consequently, pixel texture analysis parameter which scored high disease recognition rates and CAD which used brightness difference of parenchyma are very useful for detecting diffuse liver disease as well as these are possible to use clinical technique and minimize reading miss. Also, it helps to suggest correct diagnose and treatment.
|
|
KEYWORD
|
|
Liver us image, Pixel texture analysis parameters, Brightness gap, Diffuse liver disease
|
|
FullTexts / Linksout information
|
|
|
|
Listed journal information
|
|
|
|