IP Library › Granted Patent US 10,127,664
Granted Patent B2
US 10,127,664 · App. 15/356,890 · Granted Nov 13, 2018

Ovarian image processing for diagnosis of a subject

Inventors: Anita Govindjee (Ithaca, NY); Lakshminarayanan Krishnamurthy (Round Rock, TX); Niyati Parameswaran (Santa Clara, CA); Shanker Parameswaran (Mumbai, IN)
Assignee: International Business Machines Corporation
G06T7/0014A61B3/0025A61B5/4325A61B5/7282A61B6/5217A61B8/5223G06T2207/10088G06T2207/10101G06T2207/10104G06T2207/10108G06T2207/10116
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,127,664
App. No.
15/356,890
Granted
Nov 13, 2018
Kind
B2
Abstract

Embodiments relate to digital image processing for diagnosis of a subject. More specifically, the embodiments relate to automation of diagnoses through data interpretation. An image is acquired from the subject. Elements are recognized within the image based on morphological features. The image is compared to learned data. Based on the comparison, a probability of a potential diagnosis(es) is calculated. A diagnosis of the subject is determined based on the potential diagnosis(es) and the calculated probability. The diagnosis may be changed based on a new image acquired from the subject.

Claims (86)

1. A computer system comprising:

a processing unit in communication with a memory;

a functional unit in communication with the processing unit having an image diagnostic tool to determine a diagnosis, the image diagnostic tool to:

capture a first image of a first ovary;

recognize a first follicle utilizing a morphological feature of the first follicle including determine on a pixel basis each morphological feature utilizing a template set having an instruction for determination of one or more morphological features;

perform a first comparison including compare the first follicle, on a pixel basis, to a previously recognized follicle of at least one ovary;

determine a first probability based on the performed first comparison;

create a first diagnosis based on the performed first comparison and determined first probability; and

convert the first captured image to a first diagnostic image, the conversion utilizing the recognized first follicle, created first diagnosis and determined first probability, and the first diagnostic image being a visual representation of the created first diagnosis.

2. The system of claim 1 , further comprising the image diagnostic tool to:

capture a second image of the first ovary;

recognize a second follicle within the second captured image utilizing the morphological feature of the second follicle within the second captured image including determine on a pixel basis each morphological feature utilizing the template set;

perform a second comparison including compare the second follicle of the second captured image, on a pixel basis, to at least one previously recognized follicle of at least one ovary;

determine a second probability based on the performed second comparison;

create a second diagnosis based on the performed first and second comparisons and the determined first and second probabilities; and

convert the first and second captured images to a second diagnostic image, the conversion utilizing the recognized second follicle, created second diagnosis, and determined second probability, and the second diagnostic image being a visual representation of the created second diagnosis.

3. The system of claim 2 , further comprising the image diagnostic tool to:

determine a change between the recognized first and second follicle;

perform a third comparison including compare the determined change to a previously determined change of at least one follicle of at least one ovary;

determine a third probability based on the performed third comparison; and

create a third diagnosis based on the performed third comparison and determined third probability;

wherein the conversion of the first and second captured images includes utilizing the created third diagnosis and determined third probability.

4. The system of claim 2 , further comprising the image diagnostic tool to:

recalculate the determined first probability based on the created second diagnosis;

create a polyline based on the first and second captured images, and recalculated first and determined second probabilities; and

create a polyline diagnosis based on the polyline.

5. The system of claim 1 , further comprising the image diagnostic tool to:

determine one or more parameters of a first subject; and

wherein the performed first comparison includes compare the first follicle to a previously recognized follicle of at least one previous subject having one or more similar parameters to the first subject.

6. The system of claim 1 , wherein the morphological feature is selected from the group consisting of: edge, size, shape, and color.

7. A computer program product for determining a diagnosis, the computer program product comprising a computer readable storage device having program code embodied therewith, the program code executable by a processor to:

capture a first image of a first ovary;

recognize a first follicle utilizing a morphological feature of the first follicle including determine on a pixel basis each morphological feature utilizing a template set having an instruction for determination of one or more morphological features;

perform a first comparison including compare the first follicle, on a pixel basis, to a previously recognized follicle of at least one ovary;

determine a first probability based on the performed first comparison;

create a first diagnosis based on the performed first comparison and determined first probability; and

convert the first captured image to a first diagnostic image, the conversion utilizing the recognized first follicle, created first diagnosis and determined first probability, and the first diagnostic image being a visual representation of the created first diagnosis.

8. The computer program product of claim 7 , further comprising program code to:

capture a second image of the first ovary;

recognize a second follicle within the second captured image utilizing the morphological feature of the second follicle within the second captured image including determine on a pixel basis each morphological feature utilizing the template set;

perform a second comparison including compare the second follicle of the second captured image, on a pixel basis, to at least one previously recognized follicle of at least one ovary;

determine a second probability based on the performed second comparison;

create a second diagnosis based on the performed first and second comparisons and the determined first and second probabilities; and

convert the first and second captured images to a second diagnostic image, the conversion utilizing the recognized second follicle, created second diagnosis, and determined second probability, and the second diagnostic image being a visual representation of the created second diagnosis.

9. The computer program product of 8 , further comprising program code to:

determine a change between the recognized first and second follicle;

perform a third comparison including compare the determined change to a previously determined change of at least one follicle of at least one ovary;

determine a third probability based on the performed third comparison; and

create a third diagnosis based on the performed third comparison and determined third probability;

wherein the conversion of the first and second captured images includes utilizing the created third diagnosis and determined third probability.

10. The computer program product of claim 8 , further comprising program code to:

recalculate the determined first probability based on the created second diagnosis;

create a polyline based on the first and second captured images, and recalculated first and determined second probabilities; and

create a polyline diagnosis based on the polyline.

11. The computer program product of claim 7 , further comprising program code to:

determine one or more parameters of a first subject; and

wherein the performed first comparison includes compare the first follicle to a previously recognized follicle of at least one previous subject having one or more similar parameters to the first subject.

12. The computer program product of claim 7 , wherein the morphological feature is selected from the group consisting of: edge, size, shape, and color.

13. A method for determining a diagnosis comprising:

capturing a first image of a first ovary;

recognizing a first follicle utilizing a morphological feature of the first follicle including determining on a pixel basis each morphological feature utilizing a template set having an instruction for determination of one or more morphological features;

performing a first comparison including comparing the first follicle, on a pixel basis, to a previously recognized follicle of at least one ovary;

determining a first probability based on the performed first comparison;

creating a first diagnosis based on the performed first comparison and determined first probability; and

converting the first captured image to a first diagnostic image, the converting utilizing the recognized first follicle, created first diagnosis and determined first probability, and the first diagnostic image being a visual representation of the created first diagnosis.

14. The method of claim 13 , further comprising:

capturing a second image of the first ovary;

recognizing a second follicle within the second captured image utilizing the morphological feature of the second follicle within the second captured image including determining on a pixel basis each morphological feature utilizing the template set;

performing a second comparison including comparing the second follicle of the second captured image, on a pixel basis, to at least one previously recognized follicle of at least one ovary;

determining a second probability based on the performed second comparison;

creating a second diagnosis based on the performed first and second comparisons and the determined first and second probabilities; and

converting the first and second captured images to a second diagnostic image, the converting utilizing the recognized second follicle, created second diagnosis, and determined second probability, and the second diagnostic image being a visual representation of the created second diagnosis.

15. The method of 14 , further comprising:

determining a change between the recognized first and second follicle;

performing a third comparison including comparing the determined change to a previously determined change of at least one follicle of at least one ovary;

determining a third probability based on the performed third comparison; and

creating a third diagnosis based on the performed third comparison and determined third probability;

wherein the converting the first and second captured images includes utilizing the created third diagnosis and determined third probability.

16. The method of claim 14 , further comprising:

recalculating the determined first probability based on the created second diagnosis;

creating a polyline based on the first and second captured images, and recalculated first and determined second probabilities; and

creating a polyline diagnosis based on the polyline.

17. The method of claim 13 , further comprising:

determining one or more parameters of a first subject; and

wherein the performed first comparison includes comparing the first follicle to a previously recognized follicle of at least one previous subject having one or more similar parameters to the first subject.

18. The method of claim 13 , wherein the morphological feature is selected from the group consisting of: edge, size, shape, and color.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 21, 2016
From: GOVINDJEE, ANITA; KRISHNAMURTHY, LAKSHMINARAYANAN; PARAMESWARAN, NIYATI; PARAMESWARAN, SHANKER
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 040391/0434 →
Continuity (1)
Related Publication 20180144471A1 · May 24, 2018
Cited By (1)
US 12,465,325