Object based image retrieval

• US 8,775,451 B2
• Filed: 08/20/2007
• Issued: 07/08/2014
• Est. Priority Date: 08/09/1999
• Status: Expired due to Fees

• Current Assignee: Almen Laboratories Co.
• Original Assignee: Almen Laboratories, Inc.
• Inventors: Galperin, Michael
• Primary Examiner(s): Vy, Hung T
• Application Number:
  US11/841,888
• Publication Number:
  US 20080037876A1
• Time in Patent Office: 2,514 Days
• Field of Search: 600/407, 600/481, 600/437, 382/132, 382/128, 382/203, 382/209, 382/260, 382/294, 382/217, 382/118, 707/758, 707/600, 345/635, 345/555, 345/156
• US Class Current: 707/758
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 18/21 Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 10/70 using pattern recognition or machine learning optical pattern recognition or electronic computations therefor G06V10/88
• 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: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A computer-aided image comparison, evaluation and retrieval system compares objects and object clusters, or images. User controlled or automatic filtering to enhance object features may be performed prior to object definition/detection. The query image may be substantially continuously displayed during the image filtering and object definition processes. Scoring to suspected biological, medical, chemical, physical or clinical condition may be performed based on retrieved objects or images and their relative similarities to the unknown.

Claims

1. A method for facilitating diagnosis or suspicion of a condition related to an X-ray, MRI, mammography, or ultrasound, comprising:

processing user input to identify or define an object of interest in a first display image, the object of interest being located within the first display image and representing a candidate condition or indication for diagnosis or suspicion of the condition;

displaying the object of interest in a first display;

determining at least one imaging parameter based on at least one measurement of the object of interest;

displaying, near the first display, a plurality of additional images from an identified database, wherein each of the plurality of additional images comprises one or more objects and each of the plurality of additional images is identified based on mathematically generating a value which characterizes a similarity measurement between the at least one imaging parameter of the objects of interest and the at least one stored parameter of an object within the corresponding additional images;

spatially arranging the plurality of additional images according to the similarity measurement and

selecting, by a user, at least one of a plurality of image sharpening options with checkboxes;

outputting a first result for a first analysis of the user input based on pixel location;

outputting a second result for a second analysis of the user input based on the first result of the first analysis; and

outputting a numeric score that indicates the likelihood that a disease is associated with the user input, wherein the similarity measurement is based on the first result and the second result, and the similarity measurement is calculated with a modified Voronin formula.

2. The method of claim 1, wherein each of the plurality of additional images is smaller than the first display image and wherein the first display image is displayed simultaneously to the plurality of additional images.

3. The method of claim 2, wherein each of the plurality of additional images is a portion of a full representation of an original referenced images.

4. The method of claim 1, wherein the mathematical generation of a value which characterizes the similarity measurement fails to refer to the meaning associated with the at least one imaging parameter.

5. The method of claim 4, wherein the at least one imaging parameter comprises a parameter that is a numeric representation of at least one of geometry, texture and density of the first display image.

6. The method of claim 1, wherein:

the object of interest comprises multiple components, and

a multi-object template is used to determine the similarity measure based on at least a spatial relationship between one or more objects of the multi-object template to other objects in the multi-object template.

7. The method of claim 1, wherein the identified database is a reference library of cases with known or confirmed diagnosis or condition.

8. The method of claim 1, further comprising selecting the imaging parameters based on a pixel analysis.

9. The method of claim 8, wherein the pixel analysis is a pixel location analysis.

10. The method of claim 8, wherein the pixel analysis is an image geometry, image texture, or image density analysis.

11. The method of claim 1, further comprising determining at least one secondary parameter as a function of the at least one imaging parameter, wherein each the plurality of additional images is identified based on both the at least one imaging parameter and the at least one secondary parameter.

12. The method of claim 11, wherein the at least one secondary parameter is a risk factor, an age of a patient, or a disease history of a patient.

13. The method of claim 1, wherein the similarity measurement between the at least one imaging parameter of the objects of interest and the at least one stored parameter of an object is measured by Mikowski line metrics or measured by Hamming distance.

14. A method for facilitating diagnosis or suspicion of a condition related to an X-ray, MRI, mammography, or ultrasound, comprising:

displaying a first image comprising an object to a user; and

displaying, near the first image, a plurality of additional images from an image repository, wherein;

each of the plurality of additional images comprises one or more objects,

each of the plurality of additional images is identified based on a mathematically generating of a value which characterizes a similarity measurement between the at least one stored parameter of an object within the corresponding additional image and the at least one imaging parameter of an object of interest of the first image,

each of the plurality of additional images corresponds to a known diagnosis, the plurality of additional images are spatially arranged according to the similarity measurement and

selecting, by a user, at least one of a plurality of image sharpening options with checkboxes;

outputting a first result for a first analysis of the user input based on pixel location;

outputting a second result for a second analysis of the user input based on the first result of the first analysis; and

outputting a numeric score that indicates the likelihood that a disease is associated with the user input, wherein the similarity measurement is based on the first result and the second result, and the similarity measurement is calculated with a modified Voronin formula.

15. The method of claim 14, wherein the at least one imaging parameter comprising a parameter selected from a group consisting of a numeric representation of geometry, texture and density.

16. The method of claim 14, wherein each of the plurality of additional images is smaller than the first image and wherein the first image is displayed simultaneously to the plurality of additional images.

17. The method of claim 14, wherein each of the plurality of additional images is a portion of a full representation of an original referenced image with known or confirmed diagnosis or condition.