Automatic detection of red lesions in digital color fundus photographs
First Claim
Patent Images
1. A method of identifying a subject with a disease of the retina comprising automatically detecting in a digital color fundus photograph of the subject abnormal objects in an ImageORG, comprising:
- a. reducing intensity variation in the ImageORG producing a shade-corrected image, ImageSC and a background image, ImageBG;
b. automatically detecting candidate objects in the ImageSC; and
c. automatically classifying the candidate objects as abnormal or normal, wherein classification of an object as abnormal identifies a subject with a disease of the retina, wherein step b comprises,removing bright lesions in the ImageSC to produce an ImagePP,training a classifier with a supervised procedure using example pixels extracted from a labeled reference standard training set,obtaining pixel feature vectors from the ImagePP comprising applying filters for determining pixel intensities or other characteristics of pixels at each pixel location or pixel region in the ImagePP,automatically classifying each of a plurality of the ImagePP pixels as foreground or background pixels,assigning a posterior probability of being a foreground pixel to each Image PP pixel according to the equation p=n/k, producing an ImagePROB,removing the ImagePROB pixels where the posterior probability is less than a probability threshold, producing an ImageBIN-PC,removing any object in the ImageBIN-PC with a size that is above a size threshold, generating a plurality of one or more seed coordinates,applying a region-growing procedure using the plurality of one or more seed coordinates to the ImageSC to grow a set of candidate objects, andfilling empty pixels within the grown objects of the set of candidate objects.
4 Assignments
0 Petitions
Accused Products
Abstract
Disclosed is an automated method which can detect images containing red lesions. First, each image is preprocessed; next, candidate objects that may represent red-lesions are extracted; and in the final stage the probability for each candidate to represent a red-lesion is estimated using a classifier and a large set of specifically designed features.
90 Citations
30 Claims
-
1. A method of identifying a subject with a disease of the retina comprising automatically detecting in a digital color fundus photograph of the subject abnormal objects in an ImageORG, comprising:
-
a. reducing intensity variation in the ImageORG producing a shade-corrected image, ImageSC and a background image, ImageBG; b. automatically detecting candidate objects in the ImageSC; and c. automatically classifying the candidate objects as abnormal or normal, wherein classification of an object as abnormal identifies a subject with a disease of the retina, wherein step b comprises, removing bright lesions in the ImageSC to produce an ImagePP, training a classifier with a supervised procedure using example pixels extracted from a labeled reference standard training set, obtaining pixel feature vectors from the ImagePP comprising applying filters for determining pixel intensities or other characteristics of pixels at each pixel location or pixel region in the ImagePP, automatically classifying each of a plurality of the ImagePP pixels as foreground or background pixels, assigning a posterior probability of being a foreground pixel to each Image PP pixel according to the equation p=n/k, producing an ImagePROB, removing the ImagePROB pixels where the posterior probability is less than a probability threshold, producing an ImageBIN-PC, removing any object in the ImageBIN-PC with a size that is above a size threshold, generating a plurality of one or more seed coordinates, applying a region-growing procedure using the plurality of one or more seed coordinates to the ImageSC to grow a set of candidate objects, and filling empty pixels within the grown objects of the set of candidate objects. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 21, 22, 23, 24)
-
-
10. A method of identifying a subject with a disease of the retina comprising automatically detecting in a digital color fundus photograph of the subject abnormal objects in an ImageORG, comprising:
-
a. reducing intensity variation in the ImageORG producing a shade-corrected image, ImageSC and a background image, ImageBG; b. automatically detecting candidate objects in the ImageSC; and c. automatically classifying the candidate objects as abnormal or normal, wherein classification of an object as abnormal identifies a subject with a disease of the retina, wherein step b comprises, applying mathematical morphology based candidate object detection to produce a first set of candidate objects, applying a supervised pixel classification based candidate object detection to produce a second set of candidate objects, combining the first set of candidate objects and the second set of candidate objects to form a third set of candidate objects, identifying in the third set of candidate objects a plurality of pairs of overlapping objects, and removing one object from each pair of overlapping objects in the third set of candidate objects.
-
-
11. A method of identifying a subject with a disease of the retina comprising automatically detecting in a digital color fundus photograph of the subject abnormal objects in an ImageORG, comprising:
-
a. reducing intensity variation in the ImageORG producing a shade-corrected image, ImageSC and a background image, ImageBG; b. automatically detecting candidate objects in the ImageSC; and c. automatically classifying the candidate objects as abnormal or normal, wherein classification of an object as abnormal identifies a subject with a disease of the retina, wherein step b comprises, applying a morphological transformation to the ImageSC to discriminate circular from elongated regions producing a vasculature map; subtracting the vasculature map from the ImageSC to produce an ImageLESION; applying a matched filter to the ImageLESION to enhance the contrast between background regions and abnormal regions producing an ImageMATCH; applying a brightness threshold to the ImageMATCH to produce a binary digital fundus photograph, ImageBIN-MM, wherein the threshold is above the modal value of the ImageMATCH, generating a first plurality of one or more seed coordinates; applying a region-growing procedure using the first plurality of one or more seed coordinates to the ImageSC to grow a first set of candidate objects; removing bright lesions in the ImageSC to produce an ImagePP; training a classifier with a supervised procedure using example pixels extracted from a labeled reference standard training set; obtaining pixel feature vectors from the ImagePP comprising applying filters for determining pixel intensities or other characteristics of pixels at each pixel location or pixel region in the ImagePP; automatically classifying each of a plurality of the ImagePP pixels as foreground or background pixels; assigning a posterior probability of being a foreground pixel to each ImagePP pixel according to the equation p=n/k, producing an ImagePROB; removing the ImagePROB pixels where the posterior probability is less than a probability threshold, producing an ImageBIN-PC; removing any object in the ImageBIN-PC with a size that is above a size threshold, generating a second plurality of one or more seed coordinates; applying a region-growing procedure using the second plurality of one or more seed coordinates to the ImageSC to grow a second set of candidate objects; filling empty pixels in the grown objects of the second set of candidate objects; combining the first set of candidate objects and the second set of candidate objects to form a third set of candidate objects; identifying in the third set of candidate objects a plurality of pairs of overlapping objects; and removing one object from each pair of overlapping objects in the third set of candidate objects. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19, 20)
-
-
25. A system that identifies a subject with a disease of the retina by detecting in a digital color fundus photograph of the subject abnormal objects in an ImageORG, comprising:
-
a processor; and a computer readable medium coupled to said processor for storing a computer program comprising, computer code that reduces intensity variation in the ImageORG producing a shade-corrected image, ImageSC and a background image, ImageBG, computer code that automatically detects candidate objects in the ImageSC, and computer code that automatically classifies the candidate objects as abnormal or normal, wherein classification of an object as abnormal identifies a subject with a disease of the retina, wherein computer code that automatically detects candidate objects in the ImageSC comprises, removing bright lesions in the ImageSC to produce an ImagePP, training a classifier with a supervised procedure using example pixels extracted from a labeled reference standard training set, obtaining pixel feature vectors from the ImagePP comprising applying filters for determining pixel intensities or other characteristics of pixels at each pixel location or pixel region in the ImagePP, automatically classifying each of a plurality of the ImagePP pixels as foreground or background pixels, assigning a posterior probability of being a foreground pixel to each ImagePP pixel according to the equation p=n/k, producing an ImagePROB, removing the ImagePROB pixels where the posterior probability is less than a probability threshold, producing an ImageBIN-PC, removing any object in the ImageBIN-PC with a size that is above a size threshold, generating a plurality of one or more seed coordinates, applying a region-growing procedure using the plurality of one or more seed coordinates to the ImageSC to grow a set of candidate objects, and filling empty pixels within the grown objects of the set of candidate objects. - View Dependent Claims (26)
-
-
27. A system that identifies a subject with a disease of the retina by detecting in a digital color fundus photograph of the subject abnormal objects in an ImageORG, comprising.
a storage device for storing digital fundus image data; - and
a processor operably coupled to the storage device for performing the steps of; reducing intensity variation in the ImageORG producing a shade-corrected image, ImageSC and a background image, ImageBG, automatically detecting candidate objects in the ImageSC, and automatically classifying the candidate objects as abnormal or normal, wherein classification of an object as abnormal identifies a subject with a disease of the retina, wherein automatically detecting candidate objects in the ImageSC comprises, applying mathematical morphology based candidate object detection to produce a first set of candidate objects, applying a supervised pixel classification based candidate object detection to produce a second set of candidate objects, combining the first set of candidate objects and the second set of candidate objects to form a third set of candidate objects, identifying in the third set of candidate objects a plurality of pairs of overlapping objects, and removing one object from each pair of overlapping objects in the third set of candidate objects. - View Dependent Claims (28)
- and
-
29. A computer readable storage medium having computer executable instructions embodied thereon for performing a method of identifying a subject with a disease of the retina comprising automatically detecting in a digital color fundus photograph of the subject abnormal objects in an ImageORG, comprising:
-
a. reducing intensity variation in the ImageORG producing a shade-corrected image, ImageSC and a background image, ImageBG; b. automatically detecting candidate objects in the ImageSC; and c. automatically classifying the candidate objects as abnormal or normal, wherein classification of an object as abnormal identifies a subject with a disease of the retina, wherein step b comprises, removing bright lesions in the ImageSC to produce an ImagePP, training a classifier with a supervised procedure using example pixels extracted from a labeled reference standard training set, obtaining pixel feature vectors from the ImagePP comprising applying filters for determining pixel intensities or other characteristics of pixels at each pixel location or pixel region in the ImagePP, automatically classifying each of a plurality of the ImagePP pixels as foreground or background pixels, assigning a posterior probability of being a foreground pixel to each ImagePP pixel according to the equation p=n/k, producing an ImagePROB, removing the ImagePROB pixels where the posterior probability is less than a probability threshold, producing an ImageBIN-PC, removing any object in the ImageBIN-PC with a size that is above a size threshold, generating a plurality of one or more seed coordinates, applying a region-growing procedure using the plurality of one or more seed coordinates to the ImageSC to grow a set of candidate objects, and filling empty pixels within the grown objects of the set of candidate objects.
-
-
30. A computer readable storage medium having computer executable instructions embodied thereon for performing a method of identifying a subject with a disease of the retina comprising automatically detecting in a digital color fundus photograph of the subject abnormal objects in an ImageORG, comprising
a. reducing intensity variation in the ImageORG producing a shade-corrected image, ImageSC and a background image, ImageBG; -
b. automatically detecting candidate objects in the ImageSC; and c. automatically classifying the candidate objects as abnormal or normal, wherein classification of an object as abnormal identifies a subject with a disease of the retina, wherein step b comprises, applying mathematical morphology based candidate object detection to produce a first set of candidate objects, applying a supervised pixel classification based candidate object detection to produce a second set of candidate objects, combining the first set of candidate objects and the second set of candidate objects to form a third set of candidate objects, identifying in the third set of candidate objects a plurality of pairs of overlapping objects, and removing one object from each pair of overlapping objects in the third set of candidate objects.
-
Specification