Computer-aided diagnosis method and system

• US 6,574,357 B2
• Filed: 09/05/2001
• Issued: 06/03/2003
• Est. Priority Date: 09/29/1993
• Status: Expired due to Fees

• Current Assignee: Shih-Ping Wang
• Original Assignee: Shih-Ping Wang
• Inventors: Wang, Shih-Ping
• Primary Examiner(s): Patel, Jayanti K.
• Assistant Examiner(s): AZARIAN, SEYED H
• Application Number:
  US09/946,209
• Publication Number:
  US 20020076091A1
• Time in Patent Office: 636 Days
• Field of Search: 382/131, 382/132, 382/128, 382/171, 378/166, 378/37, 378/143, 378/98.9, 424/144.1, 424/154.1, 424/188.1, 424/208.1, 435/7.1, 435/6, 435/69.3, 435/262
• US Class Current: 382/132
• CPC Class Codes: A61B 6/465 adapted to display user selection data, e.g. graphical user interface, icons or menus
• CPC Class Codes: G06F 2203/04805 Virtual magnifying lens, i.e. window or frame movable on top of displayed information to enlarge it for better reading or selection
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06F 3/04855 Interaction with scrollbars
• CPC Class Codes: G06T 15/08 Volume rendering
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/30068 Mammography; Breast
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: H05G 1/60 Circuit arrangements for obtaining a series of X-ray photographs or for X-ray cinematography

Abstract

A computer-aided diagnostic (CAD) method and system provide image annotation information that can include an assessment of the probability, likelihood or predictive value of the CAD-detected suspected abnormalities as an additional aid to the radiologist. More specifically, probability values, in numerical form and/or analog form, are added to the locational markers of the CAD-detected suspected abnormalities. The task of a physician using a CAD system is believed to be made easier by displaying two different markers representing different probability thresholds. An additional threshold can be used to display “extra view markers” as an additional aid or guide to the radiologic technician to take extra views of a patient before the patient is released or discharged. A control device is added to allow the user to select and vary the probability threshold for the display of locational markers.

Claims

1. A method comprising:

processing a medical x-ray image in digital form to detect suspected abnormalities;

creating an annotated map of suspected abnormalities detected in said processing;

wherein said map shows both locations of suspected abnormalities and values related to confidence levels that suspected abnormalities are true abnormalities;

said confidence levels being user selectable; and

displaying both the x-ray image and the annotation map to a user.

2. A method as in claim 1 comprising supplying said x-ray image on film and digitizing the film to thereby generate the x-ray image in digital form that is processed in said processing.

3. A method as in claim 1 in which said processing includes converting said digital x-ray image from one digital format to another digital format.

4. A method as in claim 1 including selecting a first threshold of said confidence level and using a first notation to show suspected abnormalities in said map detected in accordance with the first threshold.

5. A method as in claim 4 including selecting an additional, second threshold of said confidence levels, different from the first threshold, and using a second notation, different from said first notation, to show suspected abnormalities detected in accordance with the second threshold.

6. A method as in claim 5 including selecting a third threshold, different from said first and second thresholds, and using a third notation, different from said first and second notations, to show suspected abnormalities detected in accordance with the third threshold.

7. A method as in claim 1 in which said map shows said values related to confidence levels as numerical values.

8. A method as in claim 1 in which said map shows said values related to confidence levels as different colors for different ranges of values.

9. A method as in claim 1 in which said map shows said values related to confidence levels as location markers that are differently sized in accordance with said values.

10. A method as in claim 1 in which said displaying comprises displaying said x-ray image on film at a lightbox and displaying an annotated map corresponding thereto at a monitor below and adjacent the displayed film.

11. A method as in claim 10 in which said displaying comprises displaying a reduced size version of the x-ray image superimposed and registered with said map at said monitor.

12. A method as in claim 1 in which said displaying comprises displaying said x-ray image in digital form at a monitor and displaying said annotated map on the same monitor, at a location spaced from at least a selected portion of the displayed x-ray image.

13. A method as in claim 1 including printing a film version of said x-ray image in digital form and of said annotated map, wherein said displaying comprises displaying said film version at a lightbox, with said annotated map spaced from a display of at least a selected portion of the displayed x-ray image.

14. A method as in claim 1 in which said x-ray image in digital form is a mammogram.

15. A method as in claim 14 including taking a film mammogram and generating said x-ray image in digital form therefrom.

17. A system as in claim 14 in which said display comprises a first area displaying said x-ray image and a second area, spaced at least from a selected part of said first area and displaying said annotation map.

16. A system comprising:

a source of a medical x-ray image in digital form;

a processor processing said x-ray image digitally to detect suspected abnormalities therein;

said processor creating as a result of said processing an annotated map showing both locations of suspected abnormalities and values related to a likelihood that the abnormalities are true abnormalities;

a display coupled with said processor to display both the x-ray image and said annotation map.

18. A system as in claim 16 in which said source of a medical x-ray image in digital form comprises a mammography imager.

19. A system as in claim 18 in which said mammography imager comprises a film mammograph and a digitizer converting film images therefrom into digital form.

20. A system as in claim 16 in which said processor creates an annotated map that uses a first notation to show suspected abnormalities having a first threshold of likelihood that they are true abnormalities.

21. A system as in claim 20 in which said processor creates an annotated map that further uses a second notation to show suspected abnormalities having a second threshold of likelihood that they are true abnormalities.

22. A system as in claim 21 in which said processor creates an annotated map that further uses a third notation to show suspected abnormalities having a third threshold of likelihood that they are true abnormalities.

23. A system as in claim 22 in which said notations are differently sized in accordance with said thresholds.

24. A system as in claim 22 in which said notations are differently colored in accordance with said thresholds.

25. A system as in claim 22 in which said notations are differently shaped in accordance with said thresholds.