Requesting a demo code for calculating second-order statistics (contrast, correlation, energy, homogeneity, and entropy) for medical images.

2 views (last 30 days)
I want to calculate second-order statistics (contrast, correlation, energy, homogeneity, and entropy) for medical images (CT/MRI images). Do you have a demo code that I can use as an example when writing my own code?

Answers (2)

Walter Roberson
Walter Roberson on 28 May 2023
Split the code up into two parts:
  1. read the medical images into memory arrays
  2. code that calculates second-order statistics on memory arrays
That is, no calculation of those statistics you list cares even a little whether the arrays are from medical images, or from stock images of happy people and hot air ballons used to sell picture frames, or screen captures from VCR tapes of music videos recorded off of MTV. So go ahead and program the statistics based on receiving 2D arrays (or general arrays), and call those functions passing in the contents of the images you read in.
  1 Comment
Zeynep Fatma
Zeynep Fatma on 28 May 2023
I have performed semantic segmentation on CT images, classifying them as cancerous and non-cancerous. Then, I calculated the first-order statistics (minimum, maximum, mean, standard deviation, and percentiles 25-50-75) of these regions. Now, I need to calculate the second-order statistics, but I am unsure of how to write the code. Therefore, I requested a demo code from you as an example.

Sign in to comment.


Image Analyst
Image Analyst on 28 May 2023
Try graycoprops. I'm also attaching a related GLCM demo and image moments demo. Good luck.
help graycoprops
GRAYCOPROPS Properties of gray-level co-occurrence matrix. STATS = GRAYCOPROPS(GLCM,PROPERTIES) normalizes the gray-level co-occurrence matrix (GLCM) so that the sum of its elements is one. Each element in the normalized GLCM, (r,c), is the joint probability occurrence of pixel pairs with a defined spatial relationship having gray level values r and c in the image. GRAYCOPROPS uses the normalized GLCM to calculate PROPERTIES. GLCM can be an m x n x p array of valid gray-level co-occurrence matrices. Each gray-level co-occurrence matrix is normalized so that its sum is one. PROPERTIES can be a comma-separated list of strings or char vectors, a cell array containing strings or char vectors, the string "all", char vector 'all', or a space separated string or char vector. They can be abbreviated, and case does not matter. Properties include: 'Contrast' the intensity contrast between a pixel and its neighbor over the whole image. Range = [0 (size(GLCM,1)-1)^2]. Contrast is 0 for a constant image. 'Correlation' statistical measure of how correlated a pixel is to its neighbor over the whole image. Range = [-1 1]. Correlation is 1 or -1 for a perfectly positively or negatively correlated image. Correlation is NaN for a constant image. 'Energy' summation of squared elements in the GLCM. Range = [0 1]. Energy is 1 for a constant image. 'Homogeneity' closeness of the distribution of elements in the GLCM to the GLCM diagonal. Range = [0 1]. Homogeneity is 1 for a diagonal GLCM. If PROPERTIES is the string "all" or char vector 'all', then all of the above properties are calculated. This is the default behavior. Please refer to the Documentation for more information on these properties. STATS is a structure with fields that are specified by PROPERTIES. Each field contains a 1 x p array, where p is the number of gray-level co-occurrence matrices in GLCM. For example, if GLCM is an 8 x 8 x 3 array and PROPERTIES is 'Energy', then STATS is a structure containing the field 'Energy'. This field contains a 1 x 3 array. Notes ----- Energy is also known as uniformity, uniformity of energy, and angular second moment. Contrast is also known as variance and inertia. Class Support ------------- GLCM can be logical or numeric, and it must contain real, non-negative, finite, integers. STATS is a structure. Examples -------- GLCM = [0 1 2 3;1 1 2 3;1 0 2 0;0 0 0 3]; stats = graycoprops(GLCM) I = imread('circuit.tif'); GLCM2 = graycomatrix(I,'Offset',[2 0;0 2]); stats = graycoprops(GLCM2,{'contrast','homogeneity'}) See also GRAYCOMATRIX. Documentation for graycoprops doc graycoprops

Categories

Find more on Biomedical Imaging in Help Center and File Exchange

Products


Release

R2022b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!