Computerized medical diagnostic system

• US 5,878,746 A
• Filed: 06/06/1995
• Issued: 03/09/1999
• Est. Priority Date: 08/25/1993
• Status: Expired due to Term

• Current Assignee: Jerome H. Lemelson, Parker J. Kevin
• Original Assignee: Jerome H. Lemelson, Parker J. Kevin
• Inventors: Parker, J. Kevin, Lemelson, Jerome H.
• Primary Examiner(s): Getzow, Scott M.
• Assistant Examiner(s): SHAW, SHAWNA JEANNINE
• Application Number:
  US08/465,954
• Time in Patent Office: 1,372 Days
• Field of Search: 128/653.1, 364/413.02, 364/413.13, 364/413.22, 382/108, 382/189, 382/190, 382/195, 382/203, 395/10, 395/52, 395/924
• US Class Current: 600/407
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• 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: G16H 70/60 relating to pathologies
• CPC Class Codes: Y10S 128/92 Computer assisted medical diagnostics
• CPC Class Codes: Y10S 128/922 including image analysis
• CPC Class Codes: Y10S 706/924 Medical

Abstract

A computerized system is disclosed for performing various medical diagnostic tests and evaluating the results thereof. In one form, image data generated from an imaging device, such as a CAT, PET, or MRI scanner, is analyzed by computer and compared with coded information defining past images of the same patient and/or standard images in order to assess the patient'"'"'s condition. The system may incorporate various types of both imaging and non-imaging modalities for providing data inputs which are stored in a database for analysis. In one particular embodiment, a computer automatically controls the performance of certain tests in accordance with its evaluation of the current input data.

Claims

1. A method for diagnosing and evaluating disease in a patient, comprising the steps of:

generating a present image of a selected anatomical region of the patient'"'"'s body and inputting digital signals corresponding to said image into a computer;

extracting features relating to particular disease states from said image signals with a pattern recognition program and storing feature signals corresponding to said extracted features in a fact database accessible by said computer;

comparing said extracted feature signals with similar feature signals corresponding to features extracted from a second image of the same anatomical region which is stored in said fact database, producing a comparison code relating to each such comparison, and storing said comparison codes in said fact database;

operating on a plurality of production rules contained in a rule database stored within said computer and relating said comparison codes to certain disease states by an inference program to generate and intelligibly indicate a diagnostic assessment of the patient'"'"'s condition based on differences between the present and second images.

2. The method as set forth in claim 1 wherein said inference program forward-chains production rules in order to generate said diagnostic assessment.

3. The method as set forth in claim 1 wherein said second image is a previously generated image of the patient'"'"'s body, and said comparison codes represent changes in the patient'"'"'s condition over time.

4. The method as set forth in claim 1 wherein said second image is a standard image of the anatomical region being examined.

5. The method as set forth in claim 1 wherein said diagnostic assessment includes intelligible recommendations for further diagnostic tests.

6. The method as set forth in claim 1 wherein said extracted features include sizes of regions segmented from an input image.

7. The method as set forth in claim 1 wherein said extracted features include shapes of select regions of an image field segmented from the input image.

8. The method as set forth in claim 1 wherein said extracted features include textures of regions segmented from an input image.

9. The method as set forth in claim 1 wherein said inference program operates on said production rules by backward-chaining a plurality of production rules in order to test a hypothetical assessment of the patient'"'"'s condition.

10. The method as set forth in claim 1 wherein said fact database includes signal recordings defining non-image features representing clinical parameters and further wherein said production rules relate said non-image features to particular disease states.

11. The method as set forth in claim 10 further comprising the step of automatically performing a diagnostic test in response to a command generated by the inference program.

12. A system for diagnosing and evaluating disease in a patient comprising:

an imaging apparatus for generating signals defining a digitized first image of a selected anatomical region of the patient'"'"'s body and inputting said image signals into a computer;

means for extracting features relating to particular disease states from said image signals with a pattern recognition program and storing the extracted features in a fact database;

wherein said fact database further includes a digitized second image of the same anatomical region as the first image;

means for comparing signals defining said extracted features with signals defining similar features extracted from a second image of the same anatomical region which are stored in said fact database, producing a comparison code relating to each such comparison, and storing said comparison codes in said fact database;

means for generating inferences by operating on a plurality of production rules relating comparison codes to certain disease states in order to generate a diagnostic assessment of the patient'"'"'s condition based on differences detected between the present and standard images.

13. The system as set forth in claim 12 wherein said inference generating means is operable to forward-chain production rules in order to generate said diagnostic assessment.

14. The system as set forth in claim 12 wherein said second image is a previously generated image of the patient'"'"'s body, said comparison codes representing changes in the patient'"'"'s condition over time.

15. The system as set forth in claim 12 wherein said second image defines a standard image of the anatomical region being examined.

16. The system as set forth in claim 12 wherein said diagnostic assessment includes recommendations for further diagnostic tests.

17. The system as set forth in claim 12 wherein said means for extracting features operates to extract features including the size of regions segmented from the input image.

18. The system as set forth in claim 12 wherein said means for extracting features operates to extract features including the shape of regions segmented from the input image.

19. The system as set forth in claim 12 wherein said means for extracting features operates to extract features including the texture of regions segmented from the input image.

20. The system as set forth in claim 12 wherein said inference generating means operates on said production rules by backward-chaining a plurality of production rules in order to test a hypothetical assessment of the patient'"'"'s condition.

21. The system as set forth in claim 12 wherein said fact database contains information defining non-image data representing clinical parameters and further wherein said production rules relate said non-image data to particular disease states.

22. The system as set forth in claim 12 further comprising:

an input device for generating digitized non-image data from a diagnostic testing device under the control of said computer;

a non-image feature extractor for extracting features relating to particular disease states from said non-image data and storing the extracted features in said fact database;

wherein said comparison module is operable to compare extracted features with similar features extracted from non-image data previously stored in said fact database, produces a comparison code relating to each such comparison, and stores said comparison codes in said fact database; and

,

wherein said inference program operates on a plurality of production rules relating comparison codes to certain disease states to generate a diagnostic assessment of the patient'"'"'s condition based on said comparison codes.

23. The system as set forth in claim 22 wherein a diagnostic test is automatically performed in response to a command generated by said inference program.