SYSTEM, METHOD AND DEVICE FOR AUTOMATIC NONINVASIVE SCREENING FOR DIABETES AND PRE-DIABETES

• US 20140228668A1
• Filed: 02/11/2014
• Published: 08/14/2014
• Est. Priority Date: 02/11/2013
• Status: Active Grant

• Current Assignee: Lifelens LLC
• Original Assignee: Lifelens LLC
• Inventors: Wakizaka, Jason, To, Wilson, Souaiaia, Tade
• Granted Patent: US 9,364,147 B2
• Time in Patent Office: Days
• US Class Current: 600/407
• CPC Class Codes: A61B 3/12 for looking at the eye fundus, e.g. ophthalmoscopes A61B3/13 takes precedence
• CPC Class Codes: A61B 3/14 Arrangements specially adapted for eye photography apparatus or arrangements for taking photographs per se G03B
• CPC Class Codes: A61B 5/02007 Evaluating blood vessel condition, e.g. elasticity, compliance
• CPC Class Codes: A61B 5/0261 using optical means, e.g. infrared light
• CPC Class Codes: A61B 5/489 Blood vessels
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/10 Segmentation; Edge detection motion-based segmentation G06T7/215
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A system for an automatic noninvasive screening for diabetes and pre-diabetes using a device to take at least one image of a patient'"'"'s eye, executing non-transitory instructions executable on a processor for analyzing the image and displaying an indication if the patient has diabetes.

Claims

1. A system for an automatic noninvasive screening for diabetes and pre-diabetes using at least one image, the system comprising:

a) an imaging device for taking at least one image of a patient'"'"'s eye;

b) a processor, operably connected to the imaging device, comprising non-transitory instructions executable on the processor for analyzing the image; and

c) an indicator operably connected to the imaging device and the processor for displaying an indication if the patient has diabetes.

2. The system of claim 1, where the imaging device and the processor are a self contained unit.

3. The system of claim 1, where the imaging device and the processor are separate units communicatively coupled to each other.

4. The system of claim 1, where the non-transitory instructions executable on the processor comprise instructions for screening the at least one image for diabetes and pre-diabetes.

5. The system of claim 4 further comprising non-transitory instructions executable on a processor to perform image processing algorithms to detect the presence, and measure when appropriate, abnormalities in the microcirculation of the patient.

6. The system of claim 5, where the algorithms to analyze the at least one image for abnormalities, where the abnormalities can be assigned three levels of importance.

7. The system of claim 6, where abnormalities in a highest importance level are selected from the group consisting of abnormal vessel diameter, vessel tortuosity, uneven vessel thickness, damaged vessel, and microaneurysms.

8. The system of claim 6, where abnormalities in a second importance level are selected from the group consisting of abnormal vessel distribution, blood flow sludging, ischemic sites, abnormal Arteriole, Venule ratio, hemosiderin deposits, and abnormal blood flow velocity.

9. The system of claim 6, where abnormalities in a third importance level are selected from the group consisting of abnormal morphology, distended vessel, “

boxcar”

blood flow phenomena (trickled flow), and comma sign.

10. A method for an automatic noninvasive screening for diabetes and pre-diabetes using at least one image, the method comprising the steps of:

a) taking at least one image of a patient'"'"'s eye using the imaging device of claim 1;

b) storing the at least one image in a storage for processing;

c) determining if more than one image is to be processed;

d) analyzing the at least one image;

e) calculating a risk profile for the patient based upon the at least one image; and

f) determining if the patient has diabetes.

11. The method of claim 10 further comprising the step of registering a plurality of images to form a single image if the determination is made that there is more than one image.

12. The method of claim 10, where the calculated risk profile can determine if the patient is pre-diabetic.

13. The method of claim 10, where the step of analyzing the at least one image further comprises the steps of:

a) detecting hemosiderin deposits;

b) detecting venuoles;

c) determining an arteriole to venuole ratio;

d) determining venuole midpoints;

e) determining the venuole midpoint diameters and angles;

f) detecting venuole paths by clustering the venuole midpoints;

g) detecting abnormalities;

h) detecting boxcar flow in the blood vessels;

i) detecting ischemic sites; and

j) detecting abnormal blood vessel distribution.

14. The method of claim 13, where the abnormalities detected can comprise tortuosity, uneven thickness, damaged vessels, microaneurysms, distended vessels, and sickle vessels.

15. The method of claim 13, where venuole diameters and angles are calculated using the steps of:

a) loading pixel values into a matrix;

b) subdividing the image of the venuole diameters and angles into subsets;

c) making microangiopathy priority groupings for each subsection analyzed; and

d) determining a risk factor for the patient based on one or more of the priority groupings alone or in combination.

16. The method of claim 13, where detection of venuoles comprises the steps of:

1) creating a binary matrix with the same dimensions as the original image

2) determining for each pixel in the image, if the pixel is in the appropriate blood vessel color range and exceeds a darkness intensity threshold, a color intensity threshold or both a darkness and a color intensity threshold;

3) setting the corresponding bit in the matrix to true, otherwise set it to false if the threshold of step

     2) is true;

4) storing in a storage a position of the pixel corresponding to the true bit position in the matrix as an identified venuole; and

5) creating an image mask from the matrix and the stored pixel information to isolate the venuoles identified in steps

     1)-4).

17. A device useful for a system for automatic noninvasive screening for diabetes and pre-diabetes, the device comprising:

a) an eyepiece;

b) a tube having a proximal and distal end and an exterior and interior portion, where the eyepiece is attached to the distal end;

c) a light source affixed to the interior portion of the tube;

d) a magnifying lens affixed to the interior portion near the proximal end of the tube; and

e) a camera body affixed to the proximal end of the tube.

18. The device of claim 17, where the camera body comprises an interior and exterior portion.

19. The device of claim 18, where a touchscreen is affixed to the camera body opposite to the tube.

20. The device of claim 19, where the interior portion of camera body comprises:

a) a camera sensor;

b) a microprocessor connected to the camera sensor; and

c) a storage for storing images connected to the microprocessor.

21. The device of claim 20 further comprising a hardware communications port, a wireless transmitter, or both a hardware communications port and a wireless transmitter for downloading the images from the storage in the device to an external storage, an archival repository or both an external storage and an archival repository.

22. The device of claim 20 further comprising a wired trigger, a wireless trigger, or both a wired and wireless trigger for activating the device to take an image of a patient'"'"'s eye to analyze the risk factors for diabetes or pre-diabetes.

23. A device useful for a system for automatic noninvasive screening for diabetes and pre-diabetes, the device comprising:

a) a handheld computer;

b) a camera body coupled to the handheld computer; and

c) a lens with a light source wrapped around the lens coupled to the camera body, where the light source can direct light to the eye in a uniform, diffuse manner, as well as minimize reflected glare.

24. The device of claim 23, where the light source can be composed of a silicon tube with LED lights placed inside of the tube.

25. The device of claim 24, where the LED'"'"'s can be directed radially out, away from the lens.

26. The device of claim 23 further comprising a fiber optic fixation light mounted on a post rotatable around the lens.

27. A method for an automatic noninvasive screening for diabetes and pre-diabetes using at least one image, the method comprising the steps of:

a) capturing a color image of a patient'"'"'s eye;

b) storing the image in a storage for processing;

c) converting the color image to a grayscale image;

d) applying a box blur filter to the grayscale image;

e) applying a noise reduction filter the box blur image;

f) normalizing the noise reduced image;

g) increasing the range between white (conjunctiva) and black (blood vessel) pixels on the normalized image;

h) applying a Gaussian Matched filter to the range increased image;

i) scoring each pixel of the Gaussian Matched image on a likelihood of being in a blood vessel;

j) calculating, for each of the scored pixels, the best orthogonal angle;

k) rank segmenting the results;

i) identifying the best identified blood vessel candidates from the segmented rankings using a threshold;

j) calculating a midpoint for each segment;

k) calculating midpoints for the rank segmented pixels;

m) calculating blood vessel diameters associated with each midpoint;

n) chaining each identified midpoint to the other identified midpoints;

o) calculating a line that connects and traverses the blood vessel through the chained midpoints creating a line; and

p) performing feature analysis on the blood vessel using statistics and the blood vessel chains to identify and measure features in the micro circulation to identified diabetic conditions.

28. The method of claim 27, where only the light intensity of each pixel is stored, rather than color data for the step of converting the color image to grayscale.

29. The method of claim 28, where calculating the light intensity of each pixel is done using the formula:

Gray Value=0.114B+0.587G+0.299R, where;

B=blue channel;

G=green channel;

R=red channel.

30. The method of claim 27, the image noise is reduced by applying a box blur filter.

31. The method of claim 30, where the box blur filter comprises the steps of:

a) creating a new image, where each pixel in the new image is equal to the average value of the neighboring pixels in the original image;

b) defining neighboring pixels as a box with length k centered on the pixel; and

c) repeating step b) for a number of iterations.

32. The method of claim 31, where the length k is in the range of 1 pixel to the number of pixels in the image.

33. The method of claim 31, where the length k is five pixels.

34. The method of claim 27, where the step of normalization increases the dynamic range of the image, exaggerating the difference in pixel intensity between the pixels in a blood vessel and pixels not in a blood vessel.

35. The method of claim 27, where normalization comprises the steps of:

a) analyzing each pixel for a white value and a black value;

b) setting the whitest pixel to white, and the darkest pixel to black; and

c) scaling all other pixels accordingly.

36. The method of claim 35, where the step of scaling uses the formula pixel(x,y)=[(pixel(x,y)−

min)/(max−

min)]×

255, where pixel(x,y)=an individual pixel.

37. The method of claim 36, where min is the smallest (minimum pixel intensity) and max is the largest pixel value, respectively, in the entire image.

38. The method of claim 36, where the image is split into smaller bins, and where min is the smallest (minimum pixel intensity) and max is the largest pixel value, respectively, in the local bin.

39. The method of claim 27, where enhancing the image using a Gaussian Matched Filter comprises the steps of:

a) analyzing, for every point P(x,y), in the image a line of pixels of some length centered on P(x,y);

b) scoring how closely the pixel intensities match a Gaussian curve, with P(x,y) acting as the mean;

c) repeating the scoring for a number of equidistant radials, centered on P(x,y); and

d) storing the highest score and an angle that produced the high score for every point in the image.

40. The method of claim 38, where the score is calculated using twelve radials.

41. The method of claim 27, where the midpoint chaining uses the O'"'"'Brien Midpoint Chaining algorithm to chain adjacent midpoints together to create a line that traverses the center of a blood vessel.

42. The method of claim 27, where the feature analysis, the method comprising the steps of:

a) identifying vessel tortuosity;

b) calculating an average, maximum, minimum, and variance of diameter for each chain to determine abnormal vessel diameter and uneven vessel thickness;

c) analyzing chains that terminate at a point not near the edge of the image;

d) identifying terminated chains as damaged blood vessels;

e) analyzing the chains identified as damaged vessels for a significant increase in diameter, a circular shape or both an increase in diameter and a circular shape at the end of the chain;

f) identifying the chains of damaged vessels as a microaneurysm;

g) analyzing chains identified as a damaged vessel for distended blood vessel, where the chains have a significant decrease in diameter at the end of the chain;

h) identifying the distended blood vessels;

i) dividing the image into a number of equal size sections;

j) analyzing the divided image for abnormal vessel distribution;

k) analyzing the divided image for ischemic sites;

analyzing the image for “

Boxcar”

blood flow phenomena.

43. The method of claim 42, where the circular shape is detected with a Hough transform.

44. The method of claim 42, where an average diameter and variance over all chains will be calculate.

45. The method of claim 42 further comprising the step of analyzing the original color image for significant areas of yellow-brown color indicating hemosiderin deposits.

46. The method of claim 42 further comprises the step of calculating vessel tortuosity.

47. The method of claim 46, where blood vessel tortuosity is calculated as being equal to the curvature of the chain divided by the length of the chain

48. The method of claim 46, where blood vessel tortuosity is calculated as being equal to the sum of the dot products over the sum of the lengths.

49. The method of claim 46, where blood vessel tortuosity is calculated using the formula: