OBJECT BASED IMAGE RETRIEVAL

• US 20080037876A1
• Filed: 08/20/2007
• Published: 02/14/2008
• Est. Priority Date: 08/09/1999
• Status: Active Application

• Current Assignee: Almen Laboratories Co.
• Original Assignee: Almen Laboratories Co.
• Inventors: Galperin, Michael
• Granted Patent: US 8,775,451 B2
• Time in Patent Office: Days
• US Class Current: 382/203
• 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 of analyzing a medical image, comprising:

providing a digital image;

characterizing at least one feature of the digital image;

comparing the at least one feature to corresponding features from images in an image repository having known diagnoses;

selecting image data from images in the image repository having at least one similar feature to the at least one feature characterized in the characterizing step;

displaying the provided image and at least one selected image data, wherein selected image data having a particular diagnosis provides an indication that the probability of the same diagnosis for the provided image is high.

3. The method of claim 1, further comprising displaying the provided digital image with at least one parameter used in the comparison step.

5. The method of claim 1, wherein the characterizing step comprises characterizing at least one of a perimeter, an area, and an intensity.

6. The method of Claim 1, wherein the characterizing step comprises characterizing at least one of a form factor, an aspect ratio, relief, and homogeneity.

7. The method of claim 1, wherein the characterizing step comprises characterizing density.

9. The method of claim 1, wherein the repository stores a plurality of images comprising objects previously characterized as malignant or benign abnormalities with or without associated biomedical and/or diagnostic descriptors.

10. The method of claim 1, wherein the at least one object parameter comprises at least two object parameters, and the at least two object parameters are weighted, such that the comparing step comprises a weighted comparison.

28. The method of claim 1, wherein the image is a 2D image.

29. The method of claim 1, wherein the image is a 3D image.

30. The method of claim 29, wherein the 3D image is rendered into 3D out of 2D representations.

2. (canceled)

4. The method of claim 2, wherein the user input comprises a selection of the at least one object parameter for use in the characterizing step.

8. (canceled)

11. A method for search of an identified image database for interpretation of biomedical images, comprising:

providing a biomedical image;

characterizing at least one feature of the biomedical image;

comparing the at least one feature to corresponding features from biomedical images in the identified image database having known diagnoses;

displaying at least part of a biomedical image from the identified image database based on said comparison results; and

alerting a user to disease likelihood for the subject in the provided biomedical image.

12. (canceled)

13. (canceled)

14. A method for facilitating diagnosis or suspicion of a condition related to an image, comprising:

displaying a first image comprising an object related to the condition;

selecting a plurality of identified images from a database based on similarity to said object with respect to at least one characterized feature;

displaying said plurality of identified images near the first image, wherein the plurality of identified images having a particular diagnosis provides an indication that the probability of the same diagnosis or suspected condition for the first image is high.

15. The method of claim 14, wherein the displayed first image is larger than the displayed plurality of identified images and wherein the displayed first image is displayed simultaneously to the displayed plurality of identified images.

16. The method of claim 14, wherein the at least one characterized feature comprises a parameter selected from perimeter, area, and intensity.

17. The method of claim 14, further comprising spatially arranging said plurality of identified images according to the similarity.

18. The method of claim 14, wherein the object is detected using both a computer system and user input.

19. (canceled)

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

processing user input to detect or define an object in a first display image;

displaying the object in a first display; and

displaying a plurality of images from an identified database near the first display, wherein each of the plurality of images is identified based on a similarity measure between objects of the plurality of images and at least one object of the first image.

21. The method of claim 20, wherein each of the plurality of images is smaller than the first image and wherein the first image is displayed simultaneously to the plurality of identified images.

22. The method of claim 20, wherein the similarity measure relates to at least one object parameter.

23. The method of claim 22, wherein the at least one characterized object parameter comprises a parameter selected from perimeter, area, and intensity.

24. The method of claim 20, further comprising spatially arranging said plurality of identified images according to the similarity measure.

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

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

displaying a plurality of images from an image repository near the first image, wherein each of the plurality of images is identified based on a similarity measure between objects of the plurality of images and at least one object of the first image; and

each of the plurality of images corresponds to a known diagnosis,

wherein the plurality of images are spatially arranging according to the similarity measure.

26. The method of claim 25, wherein the similarity measure relates to an object parameter comprising a parameter selected from perimeter, area, and intensity.

27. The method of claim 25, wherein each of the plurality of images is smaller than the first image and wherein the first image is displayed simultaneously to the plurality of identified images.