Title :
Automatic evaluation of steatosis by ultrasound image analysis
Author :
Mihailescu, Dan Mihai ; Gui, Vasile ; Toma, Corneliu Ioan ; Popescu, Adrian ; Sporea, Ioan
Author_Institution :
Dept. of Telecommun., Politeh. Univ. in Timisoara, Timişoara, Romania
Abstract :
This paper presents a new method for computer based diagnosis in liver steatosis diagnosis. The effectiveness of several image features extracted by robust estimation in conjunction with a random forests classifier for steatosis stage assessment is proved. We found that a successive dichotomy approach using random forests leads to better diagnosis than simultaneous classification with random forests.
Keywords :
biomedical ultrasonics; image classification; medical image processing; patient diagnosis; automatic evaluation; computer based diagnosis; feature extraction; liver steatosis diagnosis; random forests classifier; robust estimation; simultaneous classification; steatosis stage assessment; successive dichotomy approach; ultrasound image analysis; Attenuation; Computer vision; Diseases; Feature extraction; Liver; Robustness; Ultrasonic imaging; computer aided design; noninvasive; robust methods; steatosis; ultrasonography;
Conference_Titel :
Electronics and Telecommunications (ISETC), 2012 10th International Symposium on
Conference_Location :
Timisoara
Print_ISBN :
978-1-4673-1177-9
DOI :
10.1109/ISETC.2012.6408111
