Mammography statistical diagnostic profiler and prediction system

• US 8,687,860 B2
• Filed: 11/25/2009
• Issued: 04/01/2014
• Est. Priority Date: 11/24/2009
• Status: Active Grant

• Current Assignee: Penrad Technologies Incorporated (Intelerad Medical Systems Incorporated)
• Original Assignee: Penrad Technologies Incorporated (Intelerad Medical Systems Incorporated)
• Inventors: Gustafson, Greg
• Primary Examiner(s): Gilligan, Luke
• Application Number:
  US12/625,910
• Publication Number:
  US 20110123073A1
• Time in Patent Office: 1,588 Days
• Field of Search: 382/128, 382/190, 600/300, 600/437
• US Class Current: 382/128
• CPC Class Codes: G06F 3/04817 using icons graphical or visual programming using iconic symbols G06F8/34
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 2207/30068 Mammography; Breast
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/41 based on statistical description of texture
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• 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: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A method and system for analyzing and retrieving breast tissue abnormality tracking data, providing a tool for a radiologist that includes a report summarizing the statistical frequency of diagnosed patients, both locally and nationally, with mammogram region-of-interest classifications similar to the mammogram images taken of the anatomy of an individual patient. In one embodiment, a computer aided diagnostic program can be tested or verified against the mammography images and the region-of-interest classifications that have been validated by definitive patient diagnosis. Another embodiment allows the efficient collection of all of the mammogram abnormalities for a given medical facility in order to provide trending data or radiologist performance analysis. In yet another embodiment, the region-of-interest abnormalities in a single location in a patient'"'"'s tissue are correlated across a variety of imaging modalities including X-rays, mammogram, CT, ultrasound, MRI, or other imaging technologies.

Claims

1. A method comprising:

providing a first database of existing categorizations of existing abnormalities within a first medical facility, each existing categorization comprising at least one characteristic identified for each existing abnormality;

providing a second database of existing categorizations of existing abnormalities within a plurality of medical facilities, each existing categorization comprising at least one characteristic identified for each existing abnormality;

defining a region of interest in a breast-tissue image, wherein the region of interest contains a breast-tissue abnormality;

obtaining a categorization of the abnormality by identifying at least one characteristic of the abnormality contained in the region of interest;

identifying, by a computer system, all existing categorizations in the first database matching the categorization of the abnormality;

identifying, by the computer system, all existing categorizations in the second database matching the categorization of the abnormality;

presenting, by the computer system, an adjacent display of;

a total quantity of the indentified existing categorizations in the first database matching the categorization of the abnormality,

a quantity of the identified existing categorizations in the first database matching the categorization of the abnormality that are benign,

a quantity of the identified existing categorizations in the first database matching the categorization of the abnormality that are malignant,

a total quantity of the indentified existing categorizations in the second database matching the categorization of the abnormality,

a quantity of the identified existing categorizations in the first second database matching the categorization of the abnormality that are benign, and

a quantity of the indentified existing categorizations in the second database matching the categorization of the abnormality that are malignant.

2. The method of claim 1, wherein identifying at least one characteristic comprises manually identifying at least one characteristic of the abnormality.

3. The method of claim 1, wherein identifying at least one characteristic comprises utilizing a computer assisted diagnostic tool to identify at least one characteristic of an abnormality contained in the region of interest.

4. The method of claim 1, wherein identifying at least one characteristic comprises selecting the at least one characteristic from a lexicon of abnormality characteristics.

5. The method of claim 4, further comprising synthesizing, by the computer system, the lexicon of abnormality characteristics with a lexicon of the existing categorizations.

6. The method of claim 1, wherein obtaining a categorization comprises:

obtaining a manual categorization of a region of interest;

obtaining a computer assisted diagnostic system categorization of the region of interest; and

comparing the manual categorization and the computer assisted diagnostic system categorization.

7. The method of claim 1, further comprising providing, by the computer system, an image of a breast tissue abnormality having an existing categorization that matches the categorization of the region of interest.

8. The method of claim 1, wherein the first and second databases of existing categorizations of regions of interest each includes a first sub-set of the regions of interest that are known to be malignant and a second sub-set of the regions of interest that are known to be benign.

9. The method of claim 1, further comprising:

presenting, by the computer system, one or more exam pathology findings for the current categorization, each of the one or more exam pathology findings including;

a benign or malignant outcome,

a quantity corresponding to the individual pathology finding, and

a description of the finding.

10. The method of claim 9, further comprising:

receiving a selected pathology finding from the one or more exam pathology findings;

presenting, by the computer system, one or more examinations for the selected pathology finding corresponding to at least one historical patient having the same selected pathology finding, the one or more examinations each including a patient identifier;

receiving a selected patient identifier corresponding to a selected historical patient having the same selected pathology finding; and

presenting, by the computer system, an historical examination report for the selected historical patient.

11. A medical breast image profiler comprising:

a first database of existing categorizations of existing abnormalities in regions of interest in breast images within a first medical facility, each existing categorization comprising at least one characteristic identified for each existing abnormality;

a second database of existing categorizations of existing abnormalities in regions of interest in breast images within a plurality of medical facilities, each existing categorization comprising at least one characteristic identified for each existing abnormality;

a graphical user interface configured to present a plurality of possible characteristics according to which a current categorization of a region of interest in a breast image can be defined; and

a processor configured to identify all existing categorizations in the first database that match the current categorization, identify all existing categorization in the second database that match the current categorization, and to present information related to the identification in the graphical user interface,

wherein the graphical user interface comprises a profiler display portion, and wherein the information related to the identification is presented in the profiler display portion by an adjacent display of;

a total quantity of the identified existing categorizations in the first database matching the current categorization,

a quantity of the identified existing categorizations in the first database matching the current categorization that are benign,

a quantity of the identified existing categorizations in the first database matching the current categorization that are malignant,

a total quantity of the identified existing categorizations in the second database matching the current categorization,

a quantity of the identified existing categorizations in the second database matching the current categorization that are benign, and

a quantity of the identified existing categorizations in the second database matching the current categorization that are malignant.

12. The profiler of claim 11, wherein the graphical user interface is presented in a web browser.

13. The profiler of claim 11, wherein the processor is configured to dynamically update the information related to the identification presented in the graphical user interface if selected ones of the plurality of possible characteristics are changed.

14. The profiler of claim 11, wherein the graphical user interface is further configured to present one or more exam pathology findings for the current categorization, each of the one or more exam pathology findings including;

a benign or malignant outcome,

a quantity corresponding to the individual pathology finding, and

a description of the finding.

15. The profiler of claim 14, wherein the processor is further configured to receive a selected pathology finding from the one or more exam pathology findings, and the graphical user interface is further configured to present one or more examinations for the selected pathology finding corresponding to at least one historical patient having the same selected pathology finding, the one or more examinations each including a patient identifier.

16. The profiler of claim 15, wherein the processor is further configured to receive a selected patient identifier corresponding to a selected historical patient having the same selected pathology finding, and the graphical user interface is further configured to present an historical examination report for the selected historical patient.

17. A breast image profiler comprising:

a first database of existing categorizations of existing abnormalities in regions of interest in breast tissue images within a first medical facility, each existing categorization comprising at least one characteristic identified for each existing abnormality;

a second database of existing categorizations of existing abnormalities in regions of interest in the breast images within a plurality of medical facilities, each existing categorization comprising at least one characteristic identified for each existing abnormality;

a graphical user interface presented in a web browser and configured to present a plurality of possible characteristics according to which a region of interest in a breast tissue image can be characterized; and

a processor configured

to identify all existing categorizations in the first database that match selected ones of the plurality of possible characteristics,

to identify all existing categorizations in the second database that match selected ones of the plurality of possible characteristics, and

to calculate a rate of at least one of malignancy or benignity for the selected ones of the plurality of possible characteristics based on a comparison with the existing categorizations for each of the first and second databases, and

to present information related to the identification in the graphical user interface by an adjacent display of;

a total quantity of the identified existing categorizations in the first database matching the selected ones of the plurality of possible characteristics,

a quantity of the identified existing categorizations in the first database matching the selected ones of the plurality of possible characteristics that are benign,

a quantity of the identified existing categorizations in the first database matching the selected ones of the plurality of possible characteristics that are malignant,

a total quantity of the identified existing categorizations in the second database matching the selected ones of the plurality of possible characteristics,

a quantity of the identified existing categorizations in the second database matching the selected ones of the plurality of possible characteristics that are benign, and

a quantity of the identified existing categorizations in the second database matching the selected ones of the plurality of possible characteristics that are malignant.

18. The breast image profiler of claim 17, wherein the graphical user interface is configured to update a display of statistical report rate of at least one of malignancy or benignity based on the selection of one of the plurality of possible characteristics.

19. A multiple modality tissue image profiler comprising:

a first database of existing pathological findings for a plurality of tissue abnormalities within a first medical facility, each tissue abnormality located in a region of interest of one of a plurality of tissue images, each existing pathological finding comprising at least one characteristic identified for each tissue abnormality;

a second database of existing pathological findings for a plurality of tissue abnormalities within a plurality of medical facilities, each tissue abnormality located in a region of interest of one of a plurality of tissue images, each existing pathological finding comprising at least one characteristic identified for each tissue abnormality;

a graphical user interface configured to present a plurality of possible characteristics according to which a tissue abnormality can be characterized; and

a processor configured

to identify all existing categorizations in the first database that match selected ones of the plurality of possible characteristics,

to identify all existing categorizations in the second database that match selected ones of the plurality of possible characteristics,

to present information related to the matching selected ones of the plurality of possible characteristics by an adjacent display of;

a total quantity of the identified existing categorizations in the first database matching the selected ones of the plurality of possible characteristics,

a quantity of the identified existing categorization in the first database matching the selected ones of the plurality of possible characteristics that are benign,

a quantity of the identified existing categorizations in the first database matching the selected ones of the plurality of possible characteristics that are malignant,

a total quantity of the identified existing categorizations in the second database matching the selected ones of the plurality of possible characteristics,

a quantity of the identified existing categorizations in the second database matching the selected ones of the plurality of possible characteristics that are benign, and

a quantity of the identified existing categorizations in the second database matching the selected ones of the plurality of the possible characteristics that are malignant,

to retrieve at least one image having at least one of the selected ones of the plurality of possible characteristics based on a comparison with the existing categorizations, and

to present the at least one image depicting the characterized tissue abnormality in the graphical user interface;

wherein the plurality of images depicting the characterized tissue abnormality include a plurality of different imaging modalities.

20. The profiler of claim 19, wherein the plurality of different imaging modalities are selected from the group consisting of an X-ray, MRI image, an ultrasound image, a CT image and a pathologic image.