Selective Display Of Computer-Aided Detection Findings With Associated Breast X-Ray Mammogram and/or Tomosynthesis Image Information

• US 20110110576A1
• Filed: 10/06/2010
• Published: 05/12/2011
• Est. Priority Date: 10/07/2009
• Status: Active Grant

• Current Assignee: Hologic Incorporated
• Original Assignee: Hologic Incorporated
• Inventors: Marshall, Julian, Hitzke, Georgia K., Kreeger, Kevin A., Chui, Haili
• Granted Patent: US 8,326,012 B2
• Time in Patent Office: Days
• US Class Current: 382/132
• CPC Class Codes: A61B 6/025 Tomosynthesis
• CPC Class Codes: A61B 6/0414 with compression means
• CPC Class Codes: A61B 6/463 characterised by displaying multiple images or images and diagnostic data on one display
• CPC Class Codes: A61B 6/465 adapted to display user selection data, e.g. graphical user interface, icons or menus
• CPC Class Codes: A61B 6/466 adapted to display 3D data
• CPC Class Codes: A61B 6/467 characterised by special input means
• CPC Class Codes: A61B 6/502 for diagnosis of breast, i.e. mammography
• CPC Class Codes: A61B 6/5217 extracting a diagnostic or physiological parameter from medical diagnostic data
• CPC Class Codes: A61B 6/5294 involving using additional data, e.g. patient information, image labeling, acquisition parameters
• CPC Class Codes: G06F 3/04815 Interaction with a metaphor-based environment or interaction object displayed as three-dimensional, e.g. changing the user viewpoint with respect to the environment or object
• CPC Class Codes: G06F 3/04817 using icons graphical or visual programming using iconic symbols G06F8/34
• CPC Class Codes: G06F 3/04845 for image manipulation, e.g. dragging, rotation, expansion or change of colour
• CPC Class Codes: G06F 3/04847 Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 11/003 Reconstruction from projections, e.g. tomography
• CPC Class Codes: G06T 11/008 Specific post-processing after tomographic reconstruction, e.g. voxelisation, metal artifact correction
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 15/08 Volume rendering
• CPC Class Codes: G06T 19/00 Manipulating 3D models or images for computer graphics
• 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 2207/30204 : Marker
• CPC Class Codes: G06T 2210/41 : Medical
• CPC Class Codes: G06T 2211/436 : Limited angle
• CPC Class Codes: G06T 2219/004 : Annotating, labelling
• 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 40/63 : for local operation
• CPC Class Codes: G16H 50/20 : for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 : for simulation or modelling of medical disorders

Abstract

Methods, systems, and related computer program products for processing and displaying computer-aided detection (CAD) information associated with medical breast x-ray images, such as breast x-ray tomosynthesis volumes and conventional x-ray mammograms, are described. For one preferred embodiment, CAD findings for several cases (or several individual data volumes) are selectively designated for marking such that a predetermined number of CAD findings per case (or per data volume) are marked for display across all of the cases (or data volumes). In another preferred embodiment, localized breast fibroglandular tissue density information is used together with certainty-of-finding information as a basis for selecting which candidate CAD findings to designate as marked CAD findings, with increased certainty-of-finding being required to mark CAD findings in regions of higher fibroglandular tissue density. In another preferred embodiment, CAD findings located within regions of excessively dense fibroglandular tissue are withheld altogether, and associated warnings are displayed.

Claims

1. A computer-implemented method for processing and displaying breast x-ray tomosynthesis information, comprising:

receiving a plurality of breast x-ray tomosynthesis cases, each case comprising at least one breast x-ray tomosynthesis data volume associated with at least one breast of a patient;

for each of said cases, determining a target count N representing a target number of marked computer-aided detection (CAD) findings to be displayed to a user on a review workstation in conjunction the at least one data volume for that case, wherein said target count N is independent of any breast tissue image information contained in any of said data volumes for any of said cases;

for each said case, receiving a set of candidate CAD findings associated with the at least one breast of the patient, each candidate CAD finding being associated with a potentially suspicious lesion in the at least one breast as identified by a CAD algorithm and characterizing the potentially suspicious lesion by a plurality of computed features including a certainty of finding metric;

for each said case, designating up to said target count N of said candidate CAD findings as being marked CAD findings according to the steps of;

(a) designating all of said candidate CAD findings as marked CAD findings if the number of candidate CAD findings in said received set is less than or equal to said target count N; and

(b) if said number of candidate CAD findings is greater than said target count N, processing said candidate CAD findings according to said computed features to designate exactly N of said candidate CAD findings as marked CAD findings; and

for each of said cases, displaying said at least one data volume to the user on the review workstation with viewable annotation markers thereon corresponding to each of said marked CAD findings, said review workstation not displaying annotation markers corresponding to the candidate CAD findings that are not marked CAD findings;

whereby the user experience provided by the review workstation in reviewing the plurality of cases is weighted more toward consistency in the number of marked CAD findings per case and less toward uniform evaluation of the candidate CAD findings across different cases.

2. The method of claim 1, wherein the target count N of marked CAD findings per case is user settable.

3. The method of claim 1, wherein:

for each said case, the target count N of marked CAD findings corresponds to a predetermined target count M of marked CAD findings per data volume times of the number of data volumes in the case; and

for each said case, if the number of candidate CAD findings in each data volume is greater than said predetermined target count M, said designating comprises designating exactly M candidate CAD findings from each said data volume as marked CAD findings.

4. The method of claim 3, wherein the target count M of marked CAD findings per data volume is user settable.

5. The method of claim 1, wherein:

for each said case, the target count N of marked CAD findings corresponds to a predetermined target count K of marked CAD findings per breast times of the number of breasts (i.e., one or two) imaged in the case; and

for each said case, if the number of candidate CAD findings for each imaged breast is greater than said predetermined target count K, said designating comprises designating exactly K candidate CAD findings from each imaged breast as marked CAD findings.

6. The method of claim 5, wherein the target count K of marked CAD findings per imaged breast is user settable.

7. A system including at least one processing unit configured to process and display breast x-ray tomosynthesis information according to the method of claim 1.

8. A non-transitory computer readable medium tangibly embodying one or more sequences of instructions wherein execution of the one or more sequences of instructions by one or more processors contained in one or more computing systems causes the one or more computing systems to process and display breast x-ray tomosynthesis information according to the method of claim 1.

9. A computer-implemented method for processing and displaying breast x-ray tomosynthesis information, comprising:

receiving a plurality of breast x-ray tomosynthesis data volumes, each data volume comprising a plurality of two-dimensional breast x-ray tomosynthesis reconstructed image slices;

receiving a target count N representing a target number of computer-aided detection (CAD) findings to be displayed to a user on a review workstation for each said data volume in conjunction with the image slices thereof, wherein said target count N is independent of any breast tissue image information contained in any of said data volumes;

for each said data volume, receiving a set of candidate CAD findings associated with the corresponding breast volume, each candidate CAD finding being associated with a potentially suspicious lesion in the corresponding breast volume as identified by a CAD algorithm and characterizing the potentially suspicious lesion by a plurality of computed features including a certainty of finding metric;

for each said data volume, designating up to said target count N of said candidate CAD findings as being marked CAD findings according to the steps of;

(a) designating all of said candidate CAD findings as marked CAD findings if the number of candidate CAD findings in said data volume is less than or equal to said target count N; and

(b) if said number of candidate CAD findings is greater than said target count N, processing said candidate CAD findings according to said computed features to designate exactly N of said candidate CAD findings as marked CAD findings; and

for each of said data volumes, displaying said plurality of image slices to the user on the review workstation with viewable annotation markers thereon corresponding to each of said marked CAD findings, said review workstation not displaying annotation markers corresponding to the candidate CAD findings that are not marked CAD findings;

whereby the user experience provided by the review workstation in reviewing the plurality of data volumes is weighted more toward consistency in the number of marked CAD findings per data volume and less toward uniform evaluation of the candidate CAD findings across different data volumes.

10. The method of claim 9, wherein the target count N of marked CAD findings per data volume is user settable.

11. A system including at least one processing unit configured to process and display breast x-ray tomosynthesis information according to the method of claim 9.

12. A non-transitory computer readable medium tangibly embodying one or more sequences of instructions wherein execution of the one or more sequences of instructions by one or more processors contained in one or more computing systems causes the one or more computing systems to process and display breast x-ray tomosynthesis information according to the method of claim 9.

13. A computer-implemented method for processing and displaying information associated with breast x-ray images, comprising:

receiving a medical x-ray image of a breast;

receiving a set of candidate computer-aided detection (CAD) findings associated with the medical x-ray image, each candidate CAD finding identifying a location of a potentially suspicious lesion in the breast and characterizing the potentially suspicious lesion by a plurality of computed features including a certainty of finding metric;

computing a fibroglandular tissue density map of the breast based at least in part on information associated with said medical x-ray image, said fibroglandular tissue density map characterizing each location therein by a fibroglandular tissue density metric representative of an absolute proportion, by volume, of fibroglandular breast tissue in a local neighborhood of that location;

designating each of said candidate CAD findings as being either a marked CAD finding or a non-marked CAD finding based on its associated certainty of finding metric and said fibroglandular tissue density metric at the location thereof; and

displaying said medical x-ray image to a user on a review workstation with viewable annotation markers thereon corresponding to each of said marked CAD findings, said review workstation not displaying annotation markers corresponding to the non-marked CAD findings;

wherein said designating is carried out such that, in order to be designated as marked CAD findings, candidate CAD findings at locations of higher fibroglandular tissue density require higher certainties of finding than is required for candidate CAD findings at locations of lower fibroglandular tissue density.

14. The method of claim 13, wherein said designating comprises:

determining a certainty of finding threshold value for each said candidate CAD detection based on said fibroglandular tissue density metric at the location thereof, wherein said certainty of finding threshold increases with increased fibroglandular tissue density for all said candidate CAD detection locations across the breast;

for each said candidate CAD detection, comparing its certainty of finding metric to said certainty of finding threshold value; and

designating said candidate CAD detection as a marked CAD detection only if said certainty of finding metric exceeds said certainty of finding threshold value.

15. The method of claim 13, further comprising:

processing the fibroglandular tissue density map to detect a contiguous region of the breast characterized by (a) a fibroglandular tissue density metric that is higher than a predetermined statistical threshold, and (b) a size and shape that is sufficient to substantially obscure an anatomical abnormality among the high fibroglandular density tissue therewithin; and

superimposing on said display of the medical x-ray image at said review workstation a graphical annotation that visually identifies said detected contiguous region.

16. The method of claim 15, further comprising displaying an advisory annotation on said review workstation display that communicates at least one of (a) an indication of reduced CAD algorithm validity for said detected contiguous region, and (b) a recommendation to image the breast using an alternative medical imaging modality.

17. The method of claim 15, further comprising designating or redesignating all candidate CAD findings located in said detected contiguous region as being non-marked CAD findings, whereby no candidate CAD findings located in said detected contiguous region are marked on said review workstation display.

18. The method of claim 15, wherein said medical x-ray image is a two-dimensional x-ray mammogram acquired with the breast in a compressed state between two generally parallel compression paddles, the x-ray image being acquired by projecting x-rays through the compressed breast from an x-ray source positioned on one side of the compression paddles toward an x-ray detector positioned on an opposite side of the compression paddles, and wherein said fibroglandular tissue density map is a two-dimensional volumetric breast density (VBD) map computed from the two-dimensional x-ray mammogram according to a predetermined VBD computation algorithm, the VBD map containing, for each location in the x-ray mammogram, information representative of an absolute cumulative height of the fibroglandular breast tissue and an absolute cumulative height of non-fibroglandular breast tissue in a correspondingly located column of breast tissue extending between said compression paddles.

19. The method of claim 18, wherein the contiguous region to be detected in said fibroglandular tissue density map is at least roughly circular with an average diameter in the range of 1 cm to 2 cm.

20. The method of claim 15, wherein said medical x-ray image is a breast x-ray tomosynthesis volume computed from a plurality of x-ray tomosynthesis projection images, each projection image being acquired with the breast in a compressed state between two generally parallel compression paddles, each projection image being acquired by projecting x-rays at a respective tomosynthesis projection angle through the compressed breast from an x-ray source positioned on one side of the compression paddles toward an x-ray detector positioned on an opposite side of the compression paddles, the breast x-ray tomosynthesis volume comprising a plurality of two-dimensional breast x-ray tomosynthesis reconstructed image slices corresponding to a respective plurality of slice depths in the breast volume, and wherein said fibroglandular tissue density map is a three-dimensional map computed according to the steps of:

receiving at least two of said x-ray tomosynthesis projection images;

processing each said projection image to compute therefrom a respective two-dimensional volumetric breast density (VBD) map according to a predetermined VBD computation algorithm, the VBD map containing, for each location in the projection image, information representative of an absolute cumulative height of the fibroglandular breast tissue and an absolute cumulative height of non-fibroglandular breast tissue in a correspondingly located column of breast tissue extending between said compression paddles at the associated tomosynthesis projection angle; and

processing said at least two VBD maps to generate the three-dimensional fibroglandular tissue density map.

21. The method of claim 20, wherein said three-dimensional fibroglandular tissue density map is computing by at least one of (a) backprojecting each said VBD map into three-dimensional space and accumulating the results, and (b) processing said at least two VBD maps according to a tomosynthesis reconstruction algorithm.

22. The method of claim 20, wherein the contiguous region to be detected in said fibroglandular tissue density map is at least roughly spherical with an average diameter in the range of 1 cm to 2 cm.

23. A system including at least one processing unit configured to process and display information associated with breast x-ray images according to the method of claim 13.

24. A non-transitory computer readable medium tangibly embodying one or more sequences of instructions wherein execution of the one or more sequences of instructions by one or more processors contained in one or more computing systems causes the one or more computing systems to process and display information associated with breast x-ray images according to the method of claim 13.

25. A computer-implemented method for processing and displaying information associated with breast x-ray images, comprising:

receiving a medical x-ray image of a breast;

receiving a set of computer-aided detection (CAD) findings associated with the medical x-ray image, each CAD finding identifying a location of a potentially suspicious lesion in the breast;

designating each of said CAD findings as being either a marked CAD finding or a non-marked CAD finding; and

displaying said medical x-ray image to a user on a review workstation with viewable annotation markers thereon corresponding to each of said marked CAD findings, said review workstation not displaying annotation markers corresponding to the unmarked CAD findings;

wherein said designating comprises;

(a) computing a fibroglandular tissue density map of the breast based at least in part on information associated with said medical x-ray image, said fibroglandular tissue density map characterizing each location therein by a fibroglandular tissue density metric representative of an absolute proportion, by volume, of fibroglandular breast tissue in a local neighborhood of that location;

(b) processing the fibroglandular tissue density map to detect a contiguous region of the breast characterized by (i) a fibroglandular tissue density metric that is higher than a predetermined statistical threshold, and (ii) a size and shape that is sufficient to substantially obscure an anatomical abnormality among the high fibroglandular density tissue therewithin; and

(c) designating all of said CAD findings located within said detected contiguous region as unmarked CAD findings.

26. The method of claim 25, further comprising superimposing on said display of the medical x-ray image at said review workstation a graphical annotation that visually identifies said detected contiguous region.

27. The method of claim 26, further comprising displaying an advisory annotation on said review workstation display that communicates at least one of (a) an indication of reduced CAD algorithm validity for said detected contiguous region, and (b) a recommendation to image the breast using an alternative medical imaging modality.

28. The method of claim 25, wherein said medical x-ray image is a two-dimensional x-ray mammogram acquired with the breast in a compressed state between two generally parallel compression paddles, the x-ray image being acquired by projecting x-rays through the compressed breast from an x-ray source positioned on one side of the compression paddles toward an x-ray detector positioned on an opposite side of the compression paddles, and wherein said fibroglandular tissue density map is a two-dimensional volumetric breast density (VBD) map computed from the two-dimensional x-ray mammogram according to a predetermined VBD computation algorithm, the VBD map containing, for each location in the x-ray mammogram, information representative of an absolute cumulative height of the fibroglandular breast tissue and an absolute cumulative height of non-fibroglandular breast tissue in a correspondingly located column of breast tissue extending between said compression paddles.

29. The method of claim 28, wherein the contiguous region to be detected in said fibroglandular tissue density map is at least roughly circular with an average diameter in the range of 1 cm to 2 cm.

30. The method of claim 25, wherein said medical x-ray image is a breast x-ray tomosynthesis volume computed from a plurality of x-ray tomosynthesis projection images, each projection image being acquired with the breast in a compressed state between two generally parallel compression paddles, each projection image being acquired by projecting x-rays at a respective tomosynthesis projection angle through the compressed breast from an x-ray source positioned on one side of the compression paddles toward an x-ray detector positioned on an opposite side of the compression paddles, the breast x-ray tomosynthesis volume comprising a plurality of two-dimensional breast x-ray tomosynthesis reconstructed image slices corresponding to a respective plurality of slice depths in the breast volume, and wherein said fibroglandular tissue density map is a three-dimensional map computed according to the steps of:

receiving at least two of said x-ray tomosynthesis projection images;

processing each said projection image to compute therefrom a respective two-dimensional volumetric breast density (VBD) map according to a predetermined VBD computation algorithm, the VBD map containing, for each location in the projection image, information representative of an absolute cumulative height of the fibroglandular breast tissue and an absolute cumulative height of non-fibroglandular breast tissue in a correspondingly located column of breast tissue extending between said compression paddles at the associated tomosynthesis projection angle; and

processing said at least two VBD maps to generate the three-dimensional fibroglandular tissue density map.

31. The method of claim 30, wherein said three-dimensional fibroglandular tissue density map is computing by at least one of (a) backprojecting each said VBD map into three-dimensional space and accumulating the results, and (b) processing said at least two VBD maps according to a tomosynthesis reconstruction algorithm, and wherein the contiguous region to be detected in said fibroglandular tissue density map is at least roughly spherical with an average diameter in the range of 1 cm to 2 cm.

32. A system including at least one processing unit configured to process and display information associated with breast x-ray images according to the method of claim 25.

33. A non-transitory computer readable medium tangibly embodying one or more sequences of instructions wherein execution of the one or more sequences of instructions by one or more processors contained in one or more computing systems causes the one or more computing systems to process and display information associated with breast x-ray images according to the method of claim 25.