Title :
Intravascular ultrasound image interpretation
Author :
Nailon, William H. ; McLaughlin, Stephen ; Spencer, Timothy ; Ramo, M. Pauliina
Author_Institution :
Dept. of Electr. Eng., Edinburgh Univ., UK
Abstract :
In this study, statistical and fractal texture analysis was used to assess the ability of 30 MHz intravascular ultrasound (IVUS) data, in raw and scan-converted form, to characterise atherosclerotic plaque. Data from 3 different plaque groups was assessed in the study: 1) loose fibrotic tissue; 2) dense fibrotic tissue; and 3) calcium. The composition of each group was verified from histo-pathological analysis, providing a Gold Standard from which results were verified. Scan-converted images were used to locate 33 regions of interest (ROI) within areas of known tissue composition. Fractal and statistical textural features were computed on ROI data in raw and scan-converted form. The results show the ability of the method to discriminate between groups, in particular they highlight the advantage of using the raw data over the scan-converted data to assess coronary artery disease
Keywords :
biomedical ultrasonics; feature extraction; fractals; image texture; medical image processing; statistical analysis; ultrasonic imaging; atherosclerotic plaque; calcium; coronary artery disease; fibrotic tissue; fractal texture analysis; histo-pathological analysis; intravascular ultrasound image; medical image processing; scan-converted images; statistical textural features; tissue composition; Calcium; Cardiac disease; Cardiovascular diseases; Fractals; Image analysis; Image resolution; Image segmentation; Image texture analysis; Spatial resolution; Ultrasonic imaging;
Conference_Titel :
Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-8186-7282-X
DOI :
10.1109/ICPR.1996.546998