Abstract: The present invention provides quantification and imaging methods and a system of the echo-texture feature, comprising: obtaining an ultrasonic image; calculating all the pixel values in a selected ROI of the ultrasonic image to obtain a regional standard deviation; excluding pixels with a pixel value smaller than a multiple of the regional standard deviation in the selected ROI; counting a set of pixels centered around a Nth pixel to gather a Nth local mean, a Nth local variance and a Nth local coefficient of variance corresponding the set of pixel values, wherein N is from 1 to the number of the pixels remaining in the selected ROI; and obtaining an echo-texture index according to the local means, the local variances, or the local coefficient of variances. The imaging of echo texture which shows the echo texture distribution of the selected ROI with a color scale changing continuously from red to blue is also included. A parameter is provided to adjust the visualization enhancement of the echo texture.

Abstract: A quantification method and an imaging method are disclosed, capable of quantifying the margin feature, the cysts feature, the calcifications feature, the echoic feature and the heterogenesis feature of a tumor, and capable of imaging the margin feature, the cysts feature, the calcifications feature and the heterogenesis feature of a tumor. The quantification method and the imaging method calculate the moving variance of the gray scale of each of the pixel points based on the gradient value of the gray scale of these pixel points. Then, depending on the purpose of the quantification method or the imaging method, the maximum value, the minimum value, the mean value, and the standard deviation of the moving variance of the gray scale of these pixel points are calculated, respectively. At final, with the definition of the threshold value and the imaging rule, the above features of the tumor are quantified or imaged.

Abstract: The present invention relates to a method for multi-layer classifier applying on a computer readable medium for classifying multiple image samples. The method at least comprising the following steps: (a) receiving a plurality of samples; (b) providing a plurality of attributes, and evaluating a significance of the attributes by a selection criterion; (c) selecting at least one cut-point to establish a discriminant analysis model; (d) proceeding a step of evaluating a performance of the discriminant analysis model by adding the attributes to the discriminant analysis model; and (e) providing a stop criterion. The present invention also provides a computer readable medium for classifying multiple image samples by using the method for multi-layer classifier.

Abstract: The present invention related to a method for retrieving a tumor contour of an image processing system that includes a memory storing a grayscale image and a processor, comprising: receiving an input tumor contour of the grayscale image; defining a tumor contour annular region and a plurality of reference segments of the grayscale image, wherein the input tumor contour is in the tumor contour annular region, and each of the plurality of reference segments is across the tumor contour annular region and includes a plurality of measured points; retrieving a tumor contour suggestion point on each of the plurality of reference segments; and linking all the tumor contour suggestion points on all of the reference segments, for forming the tumor contour. Accordingly, by applying the method of the present invention, a doctor can rapidly and accurately identify the contour of a tumor in a grayscale image.

Abstract: The present invention related to a method for retrieving a tumor contour of an image processing system that includes a memory storing a grayscale image and a processor, comprising: receiving an input tumor contour of the grayscale image; defining a tumor contour annular region and a plurality of reference segments of the grayscale image, wherein the input tumor contour is in the tumor contour annular region, and each of the plurality of reference segments is across the tumor contour annular region and includes a plurality of measured points; retrieving a tumor contour suggestion point on each of the plurality of reference segments; and linking all the tumor contour suggestion points on all of the reference segments, for forming the tumor contour. Accordingly, by applying the method of the present invention, a doctor can rapidly and accurately identify the contour of a tumor in a grayscale image.

Abstract: The present invention relates to a method for multi-layer classifier applying on a computer readable medium for classifying multiple image samples. The method at least comprising the following steps: (a) receiving a plurality of samples; (b) providing a plurality of attributes, and evaluating a significance of the attributes by a selection criterion; (c) selecting at least one cut-point to establish a discriminant analysis model; (d) proceeding a step of evaluating a performance of the discriminant analysis model by adding the attributes to the discriminant analysis model; and (e) providing a stop criterion. The present invention also provides a computer readable medium for classifying multiple image samples by using the method for multi-layer classifier.

Abstract: A quantification method and an imaging method are disclosed, capable of quantifying the margin feature, the cysts feature, the calcifications feature, the echoic feature and the heterogenesis feature of a tumor, and capable of imaging the margin feature, the cysts feature, the calcifications feature and the heterogenesis feature of a tumor. The quantification method and the imaging method calculate the moving variance of the gray scale of each of the pixel points based on the gradient value of the gray scale of these pixel points. Then, depending on the purpose of the quantification method or the imaging method, the maximum value, the minimum value, the mean value, and the standard deviation of the moving variance of the gray scale of these pixel points are calculated, respectively. At final, with the definition of the threshold value and the imaging rule, the above features of the tumor are quantified or imaged.