System and method for linking current and previous images based on anatomy

• US 20070127795A1
• Filed: 11/23/2005
• Published: 06/07/2007
• Est. Priority Date: 11/23/2005
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Yeluri, Vijaykalyan, Gentles, Thomas, Herfkens, Robert, Lau, Denny, Napel, Sandy, Samara, Yaseen, Paik, David
• Granted Patent: US 7,747,050 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/30 Determination of transform parameters for the alignment of images, i.e. image registration
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS

Abstract

Certain embodiments of the present invention provide systems and methods for correlating an acquired image with an historical image. Certain embodiments include registering an acquired image and at least one historical image according to a coordinate system, applying a metric to the acquired image and each of the historical image(s), and identifying a correlation between the acquired image and one of the historical image(s) based on the metric. Certain embodiments further include storing the correlation between the acquired image and an historical image for automatic linking of the acquired image and the historical image upon display. In certain embodiments, the acquired image and the historical image may be displayed based on the correlation. In certain embodiments, the acquired image and the historical image may be automatically linked based on the correlation. In certain embodiments, the metric analyzes the acquired image and at least one historical image based on anatomy.

Claims

1. An image registration system for correlating a current image with a previous image, said system comprising:

an image processing subsystem configured to compare at least one current image and at least one previous image using a metric, wherein said image processing subsystem identifies a corresponding previous image for a current image based on said metric; and

a matching table identifying said current image and said corresponding previous image, wherein said matching table is used to automatically retrieve said corresponding previous image when said current image is displayed.

2. The system of claim 1, wherein said metric generates a metric value representing a degree of similarity between said at least one current image and said at least one previous image, and wherein said image processing subsystem identifies a corresponding previous image for a current image based on said metric value.

3. The system of claim 1, wherein said image processing subsystem registers said at least one current image and said at least one previous image according to a coordinate system.

4. The system of claim 1, further comprising a display subsystem capable of displaying said current image in conjunction with said corresponding previous image.

5. The system of claim 4, wherein said display subsystem is capable of displaying clinical data in conjunction with said current image and said corresponding previous image.

6. The system of claim 1, further comprising an image/data storage subsystem configured to store at least one of said at least one current image, said at least one previous image, and clinical data.

7. The system of claim 1, wherein said image processing subsystem automatically identifies a corresponding previous image for a current image upon receipt of said current image.

8. The system of claim 1, wherein said metric includes at least one of a mean square image to image metric and a mutual information metric.

9. A method for correlating anatomy in an acquired image with an historical image, said method comprising:

registering an acquired image and at least one historical image according to a coordinate system;

applying a metric to said acquired image and each of said at least one historical image; and

identifying a correlation between said acquired image and one of said at least one historical image based on said metric.

10. The method of claim 9, further comprising storing said correlation between said acquired image and one of said at least one historical image for automatic linking of said acquired image and one of said at least one historical image upon display.

11. The method of claim 9, further comprising displaying said acquired image and one of said at least one historical image based on said correlation.

12. The method of claim 9, further comprising automatically linking said acquired image and one of said at least one historical image based on said correlation.

13. The method of claim 9, wherein said metric is based on anatomy.

14. A computer-readable storage medium including a set of instructions for execution on a processor, the set of instructions comprising:

an image registration routine configured to register an acquired image with respect to at least one historical image; and

an image mapping routine configured to map said acquired image with one of said at least one historical image based on anatomy, wherein said image mapping routine identifies one of said at least one historical image similar to said acquired image based on a metric.

15. The set of instructions of claim 14, further comprising a display routine for displaying said acquired image and said one of said at least one historical image.

16. The set of instructions of claim 15, wherein said display routine automatically displays said acquired image and said one of said at least one historical image based on a mapping of said acquired image with said one of said at least one historical image.

17. The set of instructions of claim 14, wherein said image mapping routine further identifies clinical information relevant to at least one of said acquired image and said one of said at least one historical image.

18. The set of instructions of claim 14, further comprising a mapping data structure, wherein said mapping data structure stores a mapping between said acquired image and said one of said at least one historical image.

19. The set of instructions of claim 14, wherein said image mapping routine automatically links said acquired image and said one of said at least one historical image for display.

20. The set of instructions of claim 14, wherein said image mapping routine automatically identifies a mapping between said acquired image and said one of said at least one historical image upon receipt of said acquired image.