Intensity texture based classification system and method
AssigneeNeuromedical Systems, Inc.
InventorJoel M. Recht
Life of this patent
Estimating the term…
Abstract
A method for classifying objects within a specimen as likely to be premalignant or malignant cells includes the steps of forming an intensity image of a specimen, calculating and storing the maximum and minimum grey scale values at a plural number of distances from a pixel in the intensity image, finding the difference between the maximum and minimum grey scale values at like distances from the pixel, determining the slope of the log of the differences as a function of the log of the distances, storing the slope at the pixel location in a resultant image, and identifying objects in the intensity image as likely to be malignant or premalignant based on the value of the slope.
Claims12
A method for classifying objects within a specimen as likely to be premalignant or malignant cells, comprising the steps of:
- a) forming an intensity image of at least part of a specimen using a microscope;
- b) using a processing element to find and store the maximum and minimum grey scale values at plural distances from a pixel in said intensity image;
- c) finding the difference between the maximum and minimum grey scale values at the respective distances from said pixel using an algorithmic logic unit;
- d) determining the slope of the log of said differences as a function of the log of said distances to provide a measure of intensity texture;
- and
- e) classifying objects in said intensity image as likely to be malignant or premalignant based on the value of said slope.
A method for classifying objects based on surface texture, comprising the steps of:
- a) forming an intensity image of at least part of the surface of the object using a camera;
- b) using a hardware ranker to find the maximum and minimum grey scale values at plural distances from each pixel in said intensity image;
- c) subtracting the minimum grey scale values from the maximum grey scale values at the respective distances from each said pixel using an algorithmic logic unit;
- d) looking up the slope of the log of said differences as a function of the log of said distances in a look up table for each said pixel to provide a measure of intensity texture;
- and
- e) classifying objects in said intensity image as likely to have a certain characteristic based on the values of said slopes.
A system for classifying objects based on surface texture, comprising:
- a camera which obtains an intensity image of at least part of the surface of the object;
- a ranker which finds the maximum and minimum grey scale values at plural distances from each pixel in said intensity image;
- an arithmetic logic unit which subtracts the minimum grey scale values from the maximum grey scale values at the respective distances from each said pixel;
- a lookup table containing the slope of the log of said differences as a function of the log of said distances, the slope for providing a measure of intensity texture;
- and
- a classifier for classifying objects in said intensity image as likely to have a certain characteristic based on the values of said slopes.
Dependencies are inferred from the claim text.