# US 8,787,623 B2 · Methods, systems and computer program products for diagnosing conditions using unique codes generated from a multidimensional image of a sample

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 8,787,623 B2
- Document ID: US8787623B2
- Status: Granted
- Kind: B2
- Application number: 12/953,868
- Filed: 2010-11-24
- Published: 2011-06-30
- Granted: 2014-07-22
- Earliest claimed: 2008-11-26
- Assignees: Bioptigen, Inc.
- Applicants: Bradley A. Bower; Eric L. Buckland
- Inventors: Bradley A. Bower; Eric L. Buckland
- Web page: https://patentgrep.com/patent/US8787623B2

## CPC

- G06V 40/19: Sensors therefor
- A61B 5/0062: {Arrangements for scanning}
- A61B 5/117: Identification of persons (methods or arrangements for recognising patterns, e.g. fingerprints, G06F18/00, G06V40/00; identification of persons by analysing their voice or speech G10L17/00)
- A61B 5/1171: based on the shapes or appearances of their bodies or parts thereof
- A61B 5/6821: {Eye}
- A61B 5/6826: {Finger}
- G06K 7/1413: {1D bar codes}
- G06K 7/1417: {2D bar codes}
- G06K 7/1447: {extracting optical codes from image or text carrying said optical code}
- G06T 12/20: Inverse problem, i.e. transformations from projection space into object space
- G06V 40/1312: {direct reading, e.g. contactless acquisition}
- G06V 40/1359: {Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop}
- G06V 40/70: Multimodal biometrics, e.g. combining information from different biometric modalities
- A61B 5/0066: {Optical coherence imaging}
- A61B 5/0068: {Confocal scanning}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06K: GRAPHICAL DATA READING (image or video recognition or understanding G06V); PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Methods of providing a diagnosis using a digital code associated with an image are provided including collecting a multidimensional image, the multidimensional image having at least two dimensions; extracting a two dimensional subset of the multidimensional image; reducing the multidimensional image to a first code that is unique to the multidimensional image based on the extracted two dimensional image; comparing the first unique code associated with the subject to a library of reference codes, each of the reference codes in the library of reference codes being indicative of a class of objects; determining if the subject associated with the first unique code falls into at least one of the classes of objects associated with the reference codes based on a result of the comparison; and formulating a diagnostic decision based on the whether the first unique code associated with the subject falls into at least one of the classes associated with the reference code. Related systems and computer program products are also provided herein.

## Claims

### Claim 1

A method of providing a diagnosis using a digital code associated with an image, the method comprising:
collecting a multidimensional image of a subject using optical coherence tomography (OCT), the multidimensional image having at least two dimensions;
extracting a two dimensional subset of the multidimensional image;
reducing the multidimensional image to a first code that is unique to the multidimensional image of the subject based on the extracted two dimensional image;
comparing the first unique code associated with the subject to a library of reference codes, each of the reference codes in the library of reference codes being indicative of a class of objects;
determining if the subject associated with the first unique code falls into at least one of the classes of objects associated with the reference codes based on a result of the comparison; and
formulating a diagnostic decision based on the whether the first unique code associated with the subject falls into at least one of the classes associated with the reference code,
wherein determining if the subject associated with the first unique code falls into at least one of the classes further includes determining if the subject associated with the first unique code has changed classes over time; and
wherein formulating the diagnostic decision comprises formulating the diagnostic decision based on the change of class over time.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining if the subject associated with the first unique code falls into at least one of the classes of objects comprises determining that the subject associated with the first unique code falls into at least two of the classes, the method further comprising:
applying additional processing to determine which of the at least two classes more accurately identifies the subject associated with the first unique code.

### Claim 3 (depends on 1)

The method of claim 1, wherein the classes associated with the reference code identify at least one of a physical state and a physical object.

### Claim 4 (depends on 3)

The method of claim 3, wherein the subject comprises at least one of a fingernail bed, a fingerprint, an iris, a cornea, a retina, retinal vessels, any human tissue and physical object.

### Claim 5 (depends on 1)

The method of claim 1, wherein reducing further comprises reducing the two dimensional subset to the first unique code based on a defined set of structural or functional information contained with the image, the method further comprising:
storing the first unique code; and
comparing the first unique code to a second unique code to establish a degree of equivalence of the first and second codes.

### Claim 6 (depends on 1)

The method of claim 1, wherein the multidimensional image comprises at least one of a volumetric image representative of slowly time-variant information in a sample and time variant structural or functional information in a sample.

### Claim 7 (depends on 5)

The method of claim 5, where reducing the two dimensional subset to the first unique code comprises:
manipulating the multidimensional data to extract a region of interest;
extracting the structural or the functional information using a filter;
translating the filtered information into the first unique code representative of the information content contained in the multidimensional data;
manipulating the first unique code to be compared to other codes; and
comparing two or more codes to assess a degree of equivalents between the codes.

### Claim 8 (depends on 7)

The method of claim 7, wherein extracting comprises extracting using a filter configured to extract the structural or functional information.

### Claim 9 (depends on 8)

The method of claim 8, wherein the filter comprises at least one of a Gabor filter, a complex filter that consists of real and imaginary parts, a complex filter that consists of a spatial frequency component and a Gaussian window component and a complex filter that has at least three unique degrees of freedom including amplitude, at least one spatial frequency, and at least one Gaussian window standard deviation.

### Claim 10 (depends on 8)

The method of claim 8, wherein the filter is configured to operate on a two dimensional subset using at least one of a convolution in the native domain or a multiplication of the Fourier Transforms of the filter and two dimensional subset and multiple filter scales in which one or more filter degrees of freedom are changed before combination with the image subset.

### Claim 11 (depends on 8)

The method of claim 8, wherein the unique code is obtained from complex data comprising at least one of a complex representation of the filter combined with the image subset in which the complex result is treated as a vector in the complex plane and a method in which the angle of the vector in the complex plane is determined and a code representative of the quadrant in the complex plane containing the vector angle is generated.

### Claim 12 (depends on 1)

The method of claim 1, wherein the unique code is binary such that each pixel of information is represented by one of two states.

### Claim 13 (depends on 1)

The method of claim 1, wherein the unique code has a base greater than 2.

### Claim 14 (depends on 1)

The method of claim 1, wherein the unique code is represented as a one or two dimensional barcode configured to be read by a generic commercial barcode reading technology.

### Claim 15 (depends on 5)

The method of claim 5, wherein comparing comprises comparing two or more unique codes using cross-correlation or other relational comparison.

### Claim 16 (depends on 15)

The method of claim 15, wherein the relational comparison comprises an XOR operation.

### Claim 17 (depends on 15)

The method of claim 15, wherein the comparison result is applied to find a Hamming distance.

### Claim 18 (depends on 17)

The method of claim 17, wherein the Hamming distance is used to validate a strength of the comparison against a database of other codes.

### Claim 19 (depends on 7)

The method of claim 7, further comprising:
repeating extracting, translating, manipulating, comparing and assigning to construct a database of codes; and
defining a unique identifier threshold based on sensitivity analysis of the codes in the database.

### Claim 20 (depends on 19)

The method of claim 19, further comprising determining if a calculated code is unique or present in the database by comparing the unique identifier threshold to the Hamming distance between the calculated code and the codes in the database.

### Claim 21 (depends on 8)

The method of claim 8, wherein the filter comprises any image processing system in which information content is emphasized or extracted from a depth-dependent image.

### Claim 22 (depends on 21)

The method of claim 21, wherein the filter comprises at least one of a speckle tracking algorithm and a texture-based image analysis algorithm.

### Claim 23 (depends on 1)

The method of claim 1, wherein the method is performed using an optical coherence tomography (OCT) imaging system.

### Claim 24 (depends on 1)

A computer program product for providing a digital code associated with an image, the computer program product comprising a non-transitory computer readable storage medium having computer readable program code embodied in said medium, the computer readable program code comprising computer readable program code configured to carry out the method of claim 1.

### Claim 25

A method for providing a diagnosis using a digital code in an optical coherence tomography (OCT) imaging system, the method comprising:
acquiring interferometric cross-correlation data representative of multidimensional information unique to a sample, the multidimensional information including at least one of one or more spatial dimensions and one or two time dimensions;
processing the multidimensional interferometric cross-correlation data into one or more images to represent one or more of slowly time variant information about the sample, time variant structural and functional information about the sample;
selecting a subset of the multidimensional data;
reducing the selected subset of data to a two dimensional subset of data;
performing one or more spatial or temporal frequency transforms of the two dimensional subsets to derive a unique representation of the sample;
reducing the transform into a unique digital code associated with the sample;
comparing the unique digital code associated with the sample to a library of reference codes, each of the reference codes in the library of reference codes being indicative of a class of objects;
determining if the sample associated with the unique digital code falls into at least one of the classes of objects associated with the reference codes based on a result of the comparison; and
formulating a diagnostic decision based on the whether the unique digital code associated with the sample falls into at least one of the classes associated with the reference code,
wherein determining if the sample associated with the unique digital code falls into at least one of the classes of objections further comprises determining if the sample associated with the unique digital code has changed classes over time; and
wherein formulating the diagnostic decision comprises formulating the diagnostic decision based on the change of class over time.

### Claim 26 (depends on 25)

The method of claim 25, wherein the optical coherence tomography system comprises:
an optical source;
an optical splitter configured to separate a reference optical signal from a sample optical signal; and
an optical detector configured to detect an interferometric cross-correlation between the reference optical signal and the sample optical signal.

### Claim 27 (depends on 26)

The method of claim 26, wherein the unique digital code comprises a first unique digital code, the method further comprising:
storing the digital code;
comparing the first unique digital code to a second unique digital code of the sample acquired from a second position within the sample, of the same sample acquired at a different time and/or of a different sample; and
establishing a degree of equivalence between the first and second unique digital codes.

### Claim 28 (depends on 25)

The method of claim 25, wherein the method is performed using an optical coherence tomography (OCT) imaging system.

### Claim 29 (depends on 25)

A computer program product for providing a digital code associated with an image, the computer program product comprising a non-transitory computer readable storage medium having computer readable program code embodied in said medium, the computer readable program code comprising computer readable program code configured to carry out the method of claim 25.

### Claim 30

A method of providing a diagnosis using a digital code using a Fourier domain optical coherence tomography imaging system, the method comprising:
acquiring frequency-dependent interferometric cross-correlation data representative of multidimensional information unique to a sample, the multidimensional information including at least two of at least one frequency dimensions, one or more spatial dimensions and one or two time dimensions;
processing the multidimensional interferometric cross-correlation data into one or more images to represent one or more of slowly time variant information about the sample and time variant structural or functional information about the sample;
selecting a subset of the multidimensional data;
reducing the subset of data to a two dimensional subset of data;
performing one or more spatial or temporal frequency transforms of the two dimensional subsets to derive a unique representation of the sample;
reducing the transform into a unique digital code that provides a unique signature of the multidimensional data;
comparing the unique digital code associated with the sample to a library of reference codes, each of the reference codes in the library of reference codes being indicative of a class of objects;
determining if the sample associated with the unique digital code falls into at least one of the classes of objects associated with the reference codes based on a result of the comparison; and
formulating a diagnostic decision based on the whether the unique digital code associated with the sample falls into at least one of the classes associated with the reference code,
wherein determining if the sample associated with the unique digital code falls into at least one of the classes of objections further comprises determining if the sample associated with the unique digital code has changed classes over time; and
wherein formulating the diagnostic decision comprises formulating the diagnostic decision based on the change of class over time.

### Claim 31 (depends on 30)

The method of claim 30, wherein the Fourier domain optical coherence tomography imaging system comprises:
an optical source;
an optical splitter configured to separate a reference optical signal from a sample optical signal; and
an optical detector configured to detect a frequency-dependent interferometric cross-correlation between the reference signal and the sample signal.

### Claim 32 (depends on 31)

The method of claim 31, wherein the unique digital code comprises a first unique digital code, the method further comprising:
storing the unique digital code;
comparing the unique digital code to a second unique digital code of the same sample acquired from a separate position within the sample, of the sample acquired at a separate time, of a different sample; and
establishing a degree of equivalence between the first and second unique digital codes.

### Claim 33 (depends on 32)

The method of claim 32, wherein processing of frequency-dependent interferometric cross-correlation data comprises obtaining a Fourier transformation of the frequency-dependent dimension to provide a spatial dimension.

### Claim 34 (depends on 30)

The method of claim 30:
wherein the image is a volumetric image of a fingernail of a subject;
wherein the volumetric image includes a series of one-dimensional lines that provide information on scattering from the fingernail and fingernail bed as a function of depth;
wherein a series of lines optically contiguous are arrayed in a two-dimensional frame that represents a cross section of the fingernail perpendicular to an axis of the finger, and
wherein the method further comprises acquiring a series of frames to produce a volume.

### Claim 35 (depends on 34)

The method of claim 34, further comprising:
segmenting a nailbed from within the volumetric image of the fingernail using an automated or manual segmentation technique; and
averaging one or more frames in order to produce an average-valued image of multiple cross-sectional locations of the nailbed or to improve the signal-to-noise ratio of the nailbed image along one cross-section.

### Claim 36 (depends on 35)

The method of claim 35, further comprising processing a digital code from the cross-sectional image of segmented nailbed region of at least one frame.

### Claim 37 (depends on 36)

The method of claim 36, wherein processing the multidimensional interferometric cross-correlation data comprises processing an intensity projection from two or more frames of the segmented nailbed, the method further comprising processing a digital code from the intensity projection.

### Claim 38 (depends on 30)

The method of claim 30, wherein the image is a volumetric image of an iris of an eye of a subject, wherein the volumetric image includes a series of one-dimensional lines that provide information on scattering from the iris as a function of depth, wherein a series of lines optically contiguous are arrayed in a two-dimensional frame that represents a cross section of the iris perpendicular to an axis of the eye, the method further comprising acquiring a series of frames to produce a volume.

### Claim 39 (depends on 38)

The method of claim 38, further comprising constructing the volumetric image from a series of concentric circular scans approximately centered on a pupil of the eye.

### Claim 40 (depends on 38)

The method of claim 38, further comprising:
segmenting one or more layers of the iris from within the volumetric image of the iris using an automated or manual segmentation technique; and
averaging one or more frames in order to produce an average-valued image of multiple cross-sectional locations of the iris or to improve the signal-to-noise ratio of the iris image at cross section.

### Claim 41 (depends on 40)

The method of claim 40, further comprising processing a digital code from the cross-sectional image of segmented iris region of at least one frame.

### Claim 42 (depends on 38)

The method of claim 38, further comprising:
processing an intensity projection from two or more frames of the segmented iris; and
processing a digital code from the intensity projection.

### Claim 43 (depends on 30)

The method of claim 30, wherein the method is performed using an optical coherence tomography (OCT) imaging system.

### Claim 44 (depends on 30)

A computer program of providing a digital code associated with an image, the computer program product comprising a non-transitory computer readable storage medium having computer readable program code embodied in said medium, the computer readable program code comprising computer readable program code configured to carry out the method of claim 30.

### Claim 45

An optical coherence tomography imaging system comprising:
means for acquiring interferometric cross-correlation data representative of multidimensional information unique to a sample, the multidimensional information including at least one of one or more spatial dimensions and one or two time dimensions;
means for processing the multidimensional interferometric cross-correlation data into one or more images to represent one or more of, slowly time variant information about the sample, time variant structural and functional information about the sample;
means for selecting a subset of the multidimensional data;
means for reducing the selected subset of data to a two dimensional subset of data;
means for performing one or more spatial or temporal frequency transforms of the two dimensional subsets to derive a unique representation of the sample;
means for reducing the transform into a unique digital code associated with the sample;
means for comparing the unique digital code associated with the sample to a library of reference codes, each of the reference codes in the library of reference codes being indicative of a class of objects;
means for determining if the sample associated with the unique digital code falls into at least one of the classes of objects associated with the reference codes based on a result of the comparison; and
means for formulating a diagnostic decision based on the whether the unique digital code associated with the sample falls into at least one of the classes associated with the reference code,
wherein the means for determining if the sample associated with the unique digital code falls into at least one of the classes of objections further comprise means for determining if the sample associated with the unique digital code has changed classes over time; and
wherein the means for formulating the diagnostic decision comprises means for formulating the diagnostic decision based on the change of class over time.

### Claim 46 (depends on 45)

The system of claim 45, further comprising:
an optical source;
an optical splitter configured to separate a reference optical signal from a sample optical signal; and
an optical detector configured to detect an interferometric cross-correlation between the reference optical signal and the sample optical signal.

### Claim 47 (depends on 46)

The system of claim 46, wherein the unique digital code comprises a first unique digital code, the system further comprising:
means for storing the digital code;
means for comparing the first unique digital code to a second unique digital code of the sample acquired from a second position within the sample, of the same sample acquired at a different time and/or of a different sample; and
means for establishing a degree of equivalence between the first and second unique digital codes.

### Claim 48

A Fourier domain optical coherence tomography imaging system comprising:
means for acquiring frequency-dependent interferometric cross-correlation data representative of multidimensional information unique to a sample, the multidimensional information including one or more of one frequency dimensions; one or more spatial dimensions; and one or two time dimensions;
means for processing the multidimensional interferometric cross-correlation data into one or more images to represent one or more of, slowly time variant information about the sample and time variant structural or functional information about the sample;
means for selecting a subset of the multidimensional data;
means for reducing the subset of data to a two dimensional subset of data;
means for performing one or more spatial or temporal frequency transforms of the two dimensional subsets to derive a unique representation of the sample;
means for reducing the transform into a unique digital code that provides a unique signature of the multidimensional data;
means for comparing the unique digital code associated with the sample to a library of reference codes, each of the reference codes in the library of reference codes being indicative of a class of objects;
means for determining if the sample associated with the unique digital code falls into at least one of the classes of objects associated with the reference codes based on a result of the comparison; and
means for formulating a diagnostic decision based on the whether the unique digital code associated with the sample falls into at least one of the classes associated with the reference code;
wherein the means for determining if the sample associated with the unique digital code falls into at least one of the classes of objections further comprise means for determining if the sample associated with the unique digital code has changed classes over time; and
wherein the means for formulating the diagnostic decision comprises means for formulating the diagnostic decision based on the change of class over time.

### Claim 49 (depends on 48)

The system of claim 48, further comprising:
an optical source;
an optical splitter configured to separate a reference optical signal from a sample optical signal; and
an optical detector configured to detect a frequency-dependent interferometric cross-correlation between the reference signal and the sample signal.

### Claim 50 (depends on 48)

The system of claim 48, wherein the unique digital code comprises a first unique digital code, the system further comprising:
means for storing the unique digital code;
means for comparing the unique digital code to a second unique digital code of the same sample acquired from a separate position within the sample, of the sample acquired at a separate time, of a different sample; and
a means for establishing a degree of equivalence between the first and second unique digital codes.