Table 1 Texture features
From: The relationship between HbA1c and ultrasound plaque textures in atherosclerotic patients
Histogram (1) mean, (2) variance, (3) skewness, (4) kurtosis and (5) percentiles 1, 10, 50, 90 and 99 % |
Absolute gradient (1) mean, (2) variance, (3) skewness, (4) kurtosis and (5) percentage of pixels with nonzero gradient |
Run-length matrix (1) run-length nonuniformity, (2) grey-level nonuniformity, (3) long-run emphasis, (4) short run emphasis and (5) fraction of image in runs. Parameters computed for horizontal, 45° vertical and 135° orientation |
Co-occurrence matrix (1) angular second moment, (2) contrast, (3) correlation, (4)sum of squares, (5) inverse difference moment, (6) sum average, (7) sum variance, (8) sum entropy, (9) entropy, (10) difference variance and (11) difference entropy. Parameters are computed for 4 orientations: (a, 0), (0, a), (a, a), (a, −a) and 5 distances: a = 1, 2, 3, 4, 5; between image pixels |
Autoregressive model (1) model parameter vector includes 4 parameters and (2) standard deviation of the driving noise |
Wavelet (1) Energy of wavelet coefficients in low-frequency subbands, (2) horizontal high-frequency subbands, (3) vertical high-frequency subbands and (4) diagonal high-frequency subbands at successive scales |