Method and system for fractal-based analysis of medical image texture
AssigneeThe University of Chicago
InventorsMaryellen L. Giger, Hui Li
Life of this patent
Estimating the term…
Abstract
A computerized method, system and computer program for the computerized fractal-based analysis of a structure as presented in a pattern on a medical image. Image data is generated from the medical image and a region of interest is selected. The image data is digitized and analyzed to reveal fractal-based computer-generated features of a texture of the image data. Then a qualifier is applied to the computer-generated features to obtain fractal characteristics of the image data. A multi-fractal nature is observed for the texture of the region of interest. A marker for assessing a risk of a disease is yielded based on the multi-fractal nature of the texture.
Claims18
A method implemented by a computer programmed as an image processing device that analyzes a mammogram in digital form of a breast of a patient, comprising:
- extracting from a selected region of interest in the mammogram, plural surface area values or plural volume values calculated at corresponding plural scales associated with a texture of a parenchyma of the breast;
- applying, by the image processing device, said plural surface area values or said plural volume values directly as inputs to at least one of a linear discriminant classifier and an artificial neural network classifier;
- and
- generating a risk marker indicative of a breast disease risk for said patient based on an output of the at least one of a linear discriminant classifier and an artificial neural network classifier.
A system for computerized analysis of a mammogram in digital form of a breast of a patient, comprising:
- a memory storing the mammogram in digital form;
- a feature extraction mechanism that extracts, from a selected region of interest in the mammogram, plural surface area values or plural volume values calculated at corresponding plural scales associated with a texture of a parenchyma of the breast;
- a classifier mechanism including at least one of a linear discriminant classifier and an artificial neural network to which the plural surface area values or said plural volume values are directly applied as inputs;
- and
- a risk marker generator that generates a risk marker indicative of a breast disease risk for said patient based on an output of the classifier mechanism.
A non-transitory computer readable medium storing instructions for execution on a computer system, which when executed by the computer system, causes the computer system to perform a method for a computerized analysis of a mammogram in digital form of a breast of a patient, comprising the steps of:
- extracting from a selected region of interest in the mammogram, plural surface area values or plural volume values calculated at corresponding plural scales associated with a texture of a parenchyma of the breast;
- applying said plural surface area value or said plural volume values directly as inputs to at least one of a linear discriminant classifier and an artificial neural network classifier;
- and
- generating a risk marker indicative of a breast disease risk for said patient based on an output of the at least one of a linear discriminant classifier and an artificial neural network classifier.
Dependencies are inferred from the claim text.