Method, system and computer readable medium for an intelligent search workstation for computer assisted interpretation of medical images

• US 7,184,582 B2
• Filed: 03/08/2004
• Issued: 02/27/2007
• Est. Priority Date: 02/04/2000
• Status: Expired due to Term

• Current Assignee: ARCH Development Corporation (University of Chicago)
• Original Assignee: ARCH Development Corporation (University of Chicago)
• Inventors: Giger, Maryellen L., Lan, Li, Vyborny, Carl J., Huo, Zhimin
• Primary Examiner(s): Bella; Matthew C.
• Assistant Examiner(s): AZARIAN, SEYED H
• Application Number:
  US10/793,799
• Publication Number:
  US 20040247166A1
• Time in Patent Office: 1,086 Days
• Field of Search: 382128-133, 382/156, 382/162, 382/165, 382/168, 382/169, 382/199, 382/203, 382/219, 382/237, 382/254, 382/266, 382/274, 382/285, 382/316, 382/321, 250/455, 600/408, 600/443, 600/425, 356/39, 377/10, 378/21, 378/28, 378/37, 345/418, 345/604, 348/77, 348/180, 707/104.1
• US Class Current: 382/128
• CPC Class Codes: A61B 6/502 for diagnosis of breast, i.e. mammography
• CPC Class Codes: G06T 2207/30068 Mammography; Breast
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• 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 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A method, system and computer readable medium for an intelligent search display into which an automated computerized image analysis has been incorporated. Upon viewing an unknown mammographic case, the display shows both the computer classification output as well as images of lesions with known diagnoses (e.g., malignant vs. benign) and similar computer-extracted features. The similarity index used in the search can be chosen by the radiologist to be based on a single feature, multiple features, or on the computer estimate of the likelihood of malignancy. Specifically the system includes the calculation of features of images in a known database, calculation of features of an unknown case, calculation of a similarity index, display of the known cases along the probability distribution curves at which the unknown case exists. Techniques include novel developments and implementations of computer-extracted features for similarity calculation and novel methods for the display of the unknown case amongst known cases with and without the computer-determined diagnoses.

Claims

1. In a user interface of a computer-aided detection (CAD) system, a method for facilitating user diagnosis of a detected lesion in an x-ray mammogram, comprising:

displaying a first image of the detected lesion to the user;

selecting a plurality of reference images from a reference lesion database based on similarity to said detected lesion with respect to at least one computed feature characteristic; and

displaying said plurality of reference images near the first image, each reference image comprising a lesion with a known diagnosis and being visibly marked according to said known diagnosis.

2. The method of claim 1, comprising:

displaying said reference images sized smaller than said first image and simultaneously with display of said first image.

3. The method of claim 2, wherein said at least one computed feature characteristic comprises:

a likelihood-of-malignancy metric computed by the CAD system.

4. The method of claim 2, wherein said at least one computed feature characteristic is selected from the group consisting of:

a margin sharpness metric;

a spiculation metric;

a mass density metric; and

a likelihood-of-malignancy metric computed by the CAD system.

5. The method of claim 2, comprising:

spatially ordering said reference images on said user interface according to said computed feature characteristic.

6. The method of claim 1, wherein the detected lesion is a CAD-detected lesion selected by the user from a CAD-annotated x-ray mammogram display.

7. In a user interface of a computer-aided detection (CAD) system, a method for facilitating user diagnosis of a detected lesion in an x-ray mammogram, comprising:

receiving a selection of the detected lesion on a first display;

displaying a first image of the detected lesion on a second display; and

displaying a plurality of reference images on the second display near the first image, each reference image based on a similarity to said detected lesion with respect to at least one computed feature characteristic and comprising a lesion with a known diagnosis and being visibly marked according to said known diagnosis, including displaying said reference images sized smaller than said first image and simultaneously with display of said first image on said second display.

8. The method of claim 7, comprising:

selecting said plurality of reference images from a reference lesion database based on similarity to said detected lesion with respect to at least one computed feature characteristic.

9. The method of claim 8, wherein said at least one computed feature characteristic comprises:

a likelihood-of-malignancy metric computed by the CAD system.

10. The method of claim 8, wherein said at least one computed feature characteristic is selected from the group consisting of a margin sharpness metric, a spiculation metric, a mass density metric, and a likelihood-of-malignancy metric computed by the CAD system.

11. The method of claim 8, comprising:

spatially ordering said reference images on said user interface according to said computed feature characteristic.

12. In a user interface of a computer-aided detection (CAD) system, a method for facilitating user diagnosis of a detected lesion in an x-ray mammogram, comprising:

displaying a first image of the detected lesion to the user;

displaying a plurality of reference images near the first image, each reference image based on a similarity to said detected lesion with respect to at least one computed feature characteristic and comprising a lesion with a known diagnosis and being visibly marked according to said known diagnosis, including spatially ordering said reference images on said user interface according to a degree of similarity with said detected lesion with respect to at least one computed feature characteristic.

13. The method of claim 12, wherein said at least one computed feature characteristic comprises:

a likelihood-of-malignancy metric computed by the CAD system.

14. The method of claim 12, wherein said at least one computed feature characteristic is selected from the group consisting of a margin sharpness metric, a spiculation metric, a mass density metric, and a likelihood-of-malignancy metric computed by the CAD system.

15. The method of claim 12, comprising displaying said reference images sized smaller than said first image and simultaneously with display of said first image.