Title :
Liver Fibrosis Identification Based on Ultrasound Images
Author :
Cao, Guitao ; Shi, Pengfei ; Hu, Bing
Author_Institution :
Inst. of Image Process. & Pattern Recognition, Shanghai Jiao Tong Univ.
Abstract :
Diagnostic ultrasound is one of useful and noninvasive tools for clinical medicine. However, due to its qualitative, subjective and experience-based nature, ultrasound images can be influenced by image conditions such as scanning frequency and machine settings. In this paper, a novel method is proposed to extract the liver features using the joint features of fractal dimension and the entropies of texture edge co-occurrence matrix based on ultrasound images, which is not sensitive to changes in emission frequency and gain. Then, Fisher linear classifier and support vector machine are employed to test on a group of 99 liver fibrosis images from 18 patients, as well as other 273 healthy liver images from 18 specimens
Keywords :
biomedical ultrasonics; entropy; feature extraction; fractals; image classification; image texture; liver; medical image processing; support vector machines; Fisher linear classifier; clinical medicine; diagnostic ultrasound images; entropy; feature extraction; fractal dimension; liver fibrosis identification; machine settings; scanning frequency; support vector machine; texture edge cooccurrence matrix; Biomedical imaging; Entropy; Feature extraction; Fractals; Frequency; Liver; Medical diagnostic imaging; Support vector machine classification; Support vector machines; Ultrasonic imaging; Fisher classifier; Fractal; Liver fibrosis; edge co-occurrence matrix; support vector machine;
Conference_Titel :
Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the
Conference_Location :
Shanghai
Print_ISBN :
0-7803-8741-4
DOI :
10.1109/IEMBS.2005.1615942
