Pupil distortion measurement and psychiatric diagnosis method

• US 10,182,755 B2
• Filed: 12/25/2017
• Issued: 01/22/2019
• Est. Priority Date: 01/06/2017
• Status: Active Grant

• Current Assignee: Jacques Ohayon
• Original Assignee: Jacques Ohayon
• Inventors: Ohayon, Jacques
• Primary Examiner(s): Mistry, Oneal R
• Application Number:
  US15/853,899
• Publication Number:
  US 20180132775A1
• Time in Patent Office: 393 Days
• CPC Class Codes: A61B 2576/02 specially adapted for a particular organ or body part
• CPC Class Codes: A61B 5/163 by tracking eye movement, gaze, or pupil change
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30041 Eye; Retina; Ophthalmic
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 7/0014 using an image reference approach
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 40/19 Sensors therefor
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/197 Matching; Classification
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing

Abstract

A prediction, diagnosis, or suggesting of a diagnosis of a psychiatric disorder is made based in embodiments of the disclosed technology by determining a shape of one or both pupils in an image of a patient. Such a diagnosis can be made in real-time by diagnosing the patient, or by viewing a digitized version of the patient'"'"'s face as part of post-processing. By finding a pupil which is ovoid or irregular shape (non-circular) and/or comparing the shape to that of shapes of people with known psychiatric disorders, a diagnosis can be suggested.

Claims

1. A method of diagnosing a patient, comprising:

obtaining, using a high-resolution digital camera comprising greater than 5-megapixel resolution, a digitized representation at a given instant of a face of the patient;

determining, using a networked processing device, a relative position of a pupil of at least one eye of the patient by using a color or intensity change line between the pupil and an iris associated with the pupil of the patient in the digitized representation;

creating, using the networked processing device, an ovoid shape, the ovoid shape following as close a path as possible to the color or intensity change line between the pupil and the iris associated with the pupil;

inscribing, using the networked processing device, the pupil and ovoid shape in a square;

uniformly, using the networked processing device, scattering pixels over the square, the uniformly scattered pixels being uniformly sized;

determining, using the networked processing device, a ratio of a quantity of pixels disposed inside the ovoid shape to a quantity of pixels disposed inside the square;

determining, using the networked processing device, a deviation of the ovoid shape from a circle based on a deviation of the ratio from pi/4; and

comparing the deviation to a threshold of distortion, and in response to the deviation exceeding the threshold of distortion, outputting a suggestion that the patient is experiencing a medical condition.

2. The method of claim 1, wherein the ovoid shape is a perfect circle, within a pre-defined threshold, the method further comprising:

outputting the suggested medical condition.

3. The method of claim 1, further comprising smoothing the ovoid shape to be closer to an oval prior to comparing the smoothed ovoid shape to the shapes of pupils associated with people having known medical condition.

4. The method of claim 3, further comprising:

overlaying a circle over the pupil; and

adjusting the circle to become the ovoid shape and capture pixels determined represent the pupil.

5. The method of claim 4, further comprising determining the suggested medical condition based on a difference between a quantity of pixels associated with the circle and a quantity of pixels associated with the ovoid shape.

6. The method of claim 5, further comprising:

receiving an indication of whether the pupil in the digitized representation of the face is abnormal; and

during the comparison, using the indication to determine if said ovoid shape represents the known psychiatric disorder.

7. The method of claim 6, further comprising determining the indication by comparing the pupil in the digitized representation of the face to a plurality of different circles, each of the plurality of different circles being offset at a different angle with respect to each other and being representative of a healthy patient.

8. The method of claim 1, further comprising determining the known medical condition to associated with specific shapes of pupils based on images of people who have committed violent crimes.

9. The method of claim 1, further comprising determining the known medical condition associated with specific shapes of pupils based on images of people with non-circular pupils who take anti-depressant medication.

10. The method of claim 7, further comprising:

receiving an indication of a brightest region of the pupil; and

determining a threshold of the color or intensity change using the brightest region of the pupil to locate the pupil.

11. The method of claim 1, further comprising determining the suggested medical condition based on medical history of said the patient and medication history comprising a selective serotonin re-uptake inhibitors.

12. The method of claim 4, further comprising, prior to overlaying the circle, magnifying the digitized representation such that the ovoid shape is accurate to a pixel level of resolution.

13. A devise for diagnosing a patient, comprising:

a high-resolution digital camera comprising greater than 5-megapixel resolution, the high-resolution digital camera obtaining providing a digitized representation at a given instant of a face of the patient; and

a networked processing device, the networked processing device determining a relative position of a pupil of at least one eye of the patient by using a color or intensity change line between the pupil and an iris associated with the pupil of the patient in the digitized representation, the networked processing device creating an ovoid shape,

the ovoid shape following as close a path as possible to the color or intensity change line between the pupil and the iris associated with the pupil,

the networked processing device inscribing, using the networked processing device, the pupil and ovoid shape in a square;

the networked processing device uniformly, using the networked processing device, scattering pixels over the square, the uniformly scattered pixels being uniformly sized;

the networked processing device determining, using the networked processing device, a ratio of a quantity of pixels disposed inside the ovoid shape to a quantity of pixels disposed inside the square;

the networked processing device determining, using the networked processing device, a deviation of the ovoid shape from a circle based on a deviation of the ratio from pi/4; and

the networked processing device comparing the deviation to a threshold of distortion, and in response to the deviation exceeding the threshold of distortion, outputting a suggestion that the patient is experiencing a medical condition.