Method and device for retinal image analysis
AssigneeThe Chinese University of Hong Kong
InventorsBenny Chung-Ying ZEE, Jack Jock-Wai LEE, Esther Qing LI
Life of this patent
Estimating the term…
Abstract
The present application provides methods and devices for diagnosing and/or predicting the presence, progression and/or treatment effect of a disease characterized by retinal pathological changes in a subject.
Claims44
A method for diagnosing and/or predicting the presence, progression and/or treatment effect of a disease characterized by retinal pathological changes in a subject, comprising the steps of:
- (a) obtaining a retinal fundus image from the subject;
- (b) converting the image to a gray level image and/or extracting vessels from the image to obtain the gray level image and/or the vessel image;
- (c) performing one or at least two or more analyses on the gray level image and/or the vessel image, and generating one or more factors, wherein the one or at least two or more analyses are selected from the group consisting of
- fractal analysis,
- statistical texture analysis,
- high order spectra analysis,
- abnormal pattern analysis,
- and any combination thereof;
- and
- (d) comparing the one or more factors obtained from step (c) with those of a control, a change of the factors is an indication of the presence, progression and/or treatment effect of the disease in the subject.
A method for generating one or more factors associated with retinal pathological changes in a disease of a subject, comprising the steps of:
- (a) obtaining a retinal fundus image from the subject;
- (b) converting the image to a gray level image and/or extracting vessels from the image to obtain the gray level image and/or the vessel image;
- and
- (c) performing one or more analyses on the gray level image and/or the vessel image, and generating one or more factors, wherein the one or at least two or more analyses are selected from the group consisting of
- fractal analysis,
- statistical texture analysis,
- high order spectra analysis,
- abnormal pattern analysis,
- and any combination thereof.
A device for diagnosing and/or predicting the presence, progression and/or treatment effect of a disease characterized by retinal pathological changes in a subject, comprising:
- an image-capturing module for obtaining a retinal fundus image from the subject;
- a conversion module for converting the image to a gray level image and/or extracting vessels from the image to obtain said gray level image and/or vessel image;
- an analysis module comprising one or at least two or more submodules for performing analysis on the gray level image and/or vessel image and generating one or more factors, wherein the one or at least two or more submodules are selected from the group consisting of
- a fractal analysis submodule,
- a statistical texture analysis submodule,
- a high order spectra analysis submodule,
- an abnormal pattern analysis submodule,
- and any combination thereof;
- and
- optionally a comparison module for comparing the factors obtained from the analysis module with those of a control.
A method for screening or grading diabetic retinopathy in a subject, the method comprising the steps of
- a) capturing retina images from the subject;
- b) preprocessing the images to enhance the image contrast using mathematical morphological operations and wavelet transform;
- c) locating optic disc and macula in the preprocessed images by morphological analysis;
- d) detecting and analyzing abnormal patterns related to diabetic retinopathy in the preprocessed image, wherein the abnormal patterns are analyzed using wavelet algorithm;
- and
- e) integrating the detection results and grading the severity of diabetic retinopathy based on the integrated results.
A system for screening or grading diabetic retinopathy in a subject, comprising
- a) a first module for capturing retina images from the subject;
- b) a second module for receiving and preprocessing the images to enhance the image contrast using mathematical morphological operations and wavelet transform;
- c) a third module for locating optic disc and macula in the preprocessed images by morphological analysis;
- d) a fourth module for detecting and analyzing abnormal patterns related to the retinopathy in the preprocessed image, which optionally comprises multiple units to detect different abnormal patterns, wherein the abnormal patterns are analyzed using wavelet algorithm;
- and
- e) a fifth module for integrating the analyzed results and grading the retinopathy based on the integrated results.
Dependencies are inferred from the claim text.