DocumentCode :
2979447
Title :
Liver fatty change classification using 25 MHz high frequency ultrasound
Author :
Yeh, Wen-Chun ; Jeng, Yung-Ming ; Li, Cheng-Han ; Lee, Po-Huang ; Li, Pai-Chi
Author_Institution :
Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Volume :
3
fYear :
2004
fDate :
23-27 Aug. 2004
Firstpage :
2169
Abstract :
Liver fatty change (steatosis), the accumulation of fat within liver cells, is a common histological finding in liver biopsies. The histological changes of steatosis, such as the distribution of fatty droplets, cannot be resolved by conventional ultrasound. High frequency ultrasound (≥20 MHz), on the other hand, has the potential to reveal more detail of steatosis. B-mode HF ultrasound images of 19 fresh human liver samples were obtained to evaluate ultrasound´s ability to determine the steatosis grade. The images were acquired by a mechanically controlled 25 MHz single crystal probe. Image features derived from gray level concurrence and non-separable wavelet transform were extracted to classify steatosis grade using a support vector machine classifier. Each liver sample subsequently underwent histological examination and liver steatosis was graded and classified according to the number of hepatocytes affected. It is found that, compared with the results acquired from conventional ultrasound at 7 MHz, classification accuracy is clearly better at 25 MHz. Thus, liver steatosis can be more accurately characterized using high frequency B-mode ultrasound. Limitations and potential solutions of liver steatosis using high frequency ultrasound are also discussed.
Keywords :
acoustic signal processing; biomedical ultrasonics; feature extraction; image classification; liver; medical image processing; support vector machines; wavelet transforms; 25 MHz; 7 MHz; fatty droplets; gray level concurrence; hepatocytes; high frequency ultrasound; image feature extraction; liver fatty change classification; liver steatosis classification; nonseparable wavelet transform; single crystal probe; support vector machine classifier; Biopsy; Frequency; Hafnium; Humans; Liver; Probes; Support vector machine classification; Support vector machines; Ultrasonic imaging; Wavelet transforms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Ultrasonics Symposium, 2004 IEEE
ISSN :
1051-0117
Print_ISBN :
0-7803-8412-1
Type :
conf
DOI :
10.1109/ULTSYM.2004.1418268
Filename :
1418268
Link To Document :
بازگشت