# US 8,787,645 B2 · Method and system for analyzing optical coherence tomography (OCT) results using color reflectivity discretization analysis > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,787,645 B2 - Document ID: US8787645B2 - Status: Granted - Kind: B2 - Application number: 13/188,193 - Filed: 2011-07-21 - Published: 2012-01-26 - Granted: 2014-07-22 - Earliest claimed: 2010-07-21 - Assignees: Diopsys, Inc. - Applicants: Peter Derr; Alberto Gonzalez; Laurie Cox - Inventors: Peter Derr; Alberto Gonzalez; Laurie Cox - Web page: https://patentgrep.com/patent/US8787645B2 ## CPC - G06T 7/0012: {Biomedical image inspection} - G06F 18/2433: Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection - G06T 7/136: involving thresholding - A61B 3/102: {for optical coherence tomography [OCT]} - G06T 2207/10024: Color image - G06T 2207/10101: Optical tomography; Optical coherence tomography [OCT] - G06T 2207/30041: Eye; Retina; Ophthalmic - G06T 2207/30242: Counting objects in image - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) ## Abstract A method of analyzing an OCT image. An OCT image has many differently colored dots. The system detects the number of differently colored dots, quantifies them and performs statistical analysis to determine a likelihood of disease. The different colored dots correspond to different retina cell types and structures. ## Claims ### Claim 1 A method of analyzing an OCT image to detect abnormalities, comprising the steps of: obtaining an OCT image and storing said OCT image in digital memory, said OCT image comprising at least an upper reflective layer and a lower reflective layer, said OCT image further comprising dots; isolating at least a portion of said upper reflective of said OCT image as an area for dot analysis; performing a discretization operation, said discretization operation determining different ranges of pixel values, each of said ranges corresponding to a different color; assigning a color to dots in said upper reflective layer of said OCT image, said assignment of color based on a determined range of pixel values; and counting said dots which were assigned a color. ### Claim 2 (depends on 1) The method of claim 1, wherein said step of isolating at least a portion of said upper reflective layer comprises the steps of: converting said OCT image to a grayscale image; binarizing said grayscale image; defining a midpoint in said grayscale image; and isolating a region above said midpoint. ### Claim 3 (depends on 1) The method of claim 1, wherein said step of isolating at least a portion of said upper reflective layer comprises the steps of: performing a blob extraction operation on said OCT image to yield a set of blobs; selecting a largest blob from said set of blobs; mapping the region of said largest blob; and performing dot analysis in a region of said upper reflective layer based on the mapping of said region of said largest blob. ### Claim 4 (depends on 1) The method of claim 1, comprising the step of determining four different ranges of pixels values, each of said different ranges corresponding to a different color. ### Claim 5 (depends on 4) The method of claim 4, whereby said different colors are red, yellow, green and blue. ### Claim 6 (depends on 5) The method of claim 5, further comprising the step counting said dots to yield an absolute number of each of said four different colored dots. ### Claim 7 (depends on 6) The method of claim 6, further comprising the step of comparing said absolute numbers of dots to an absolute number of dots determined for a normal OCT image, said absolute number of dots determined for a normal OCT image being stored in a database. ### Claim 8 (depends on 7) The method of claim 7, further comprising the step of generating a result said result comprising a likelihood of abnormality based on said comparison. ### Claim 9 (depends on 5) The method of claim 5, further comprising the steps of: grouping said red and yellow dots into a first group and grouping said green and blue dotes into a second group; counting the number of red and yellow in said first group and counting the number of green and blue dots in said second group; and determining a ratio of dots in said first group to dots in said second group. ### Claim 10 (depends on 9) The method of the method of claim 9, further comprising the step of generating an index based on said ratio of dots in said first group to dots in said second group. ### Claim 11 (depends on 7) The method of claim 7, whereby said upper reflective layer is divided into a plurality of sectors and said step of comparing absolute numbers of dots is performed on a sector-by-sector basis. ### Claim 12 (depends on 11) The method of claim 11, whereby a number of dots in a first of said plurality of sectors is compared to a number of dots in a second of said plurality of sectors. ### Claim 13 (depends on 9) The method of claim 9, whereby said upper reflective layer is divided into a plurality of sectors and said step of determining ratios is performed on said plurality of sectors. ### Claim 14 A method of analyzing an optic disc to detect abnormalities, comprising the steps of: obtaining an OCT image of an optic disc and storing said OCT image in digital memory, said OCT image comprising at least an upper reflective layer and a lower reflective layer, said OCT image further comprising dots; dividing said OCT image of said optic disc into a plurality of slices; performing a discretization operation, said discretization operation determining different ranges of pixel values, each of said ranges corresponding to a different color; assigning a color to dots in said upper reflective layer of said OCT image, said assignment of color based on a determined range of pixel values; and counting said dots which were assigned a color. ### Claim 15 (depends on 14) The method of claim 14 further comprising the steps of determining four different ranges of pixels values, each of said different ranges corresponding to a different color. ### Claim 16 (depends on 15) The method of claim 15, whereby said different colors are red, yellow, green and blue. ### Claim 17 (depends on 16) The method of claim 16, further comprising the steps of: grouping said red and yellow dots into a first group and grouping said green and blue dotes into a second group; counting the number of red and yellow in said first group and counting the number of green and blue dots in said second group; and determining a ratio of dots in said first group to dots in said second group.