Displaying computer-aided detection information with associated breast tomosynthesis image information
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, are described. An interactive graphical user interface for displaying a tomosynthesis data volume is described that includes a display of a two-dimensional composited image having slabbed sub-images spatially localized to marked CAD findings. Also described is a graphical navigation tool for optimized CAD-assisted viewing of the data volume, comprising a plurality of CAD indicator icons running near and along a slice ruler, each CAD indicator icon spanning a contiguous segment of the slice ruler and corresponding in depthwise position and extent to a subset of image slices spanned by the associated CAD finding, each CAD indicator icon including at least one single-slice highlighting mark indicating a respective image slice containing viewable image information corresponding to the associated CAD finding.
1. A computer-implemented method for processing and displaying information associated with breast x-ray images, comprising:
acquiring or receiving x-ray image data of a breast; and
generating or receiving candidate computer aided detection (CAD) findings associated with the x-ray image data, 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 comprising a certainty of finding metric;
computing a fibroglandular tissue density map of the breast based at least in part on information associated with the acquired or received x-ray image data of the breast, the 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,
wherein the fibroglandular tissue density map indicates a range of densities in the breast and respective candidate CAD findings are designated as marked or non-marked based at least in part on respective associated certainty of finding metrics and respective fibroglandular tissue density metrics at respective candidate CAD finding locations.
2. The method of claim 1 , wherein the acquired or received x-ray image data comprises a breast x-ray tomosynthesis volume computed from a plurality of x-ray tomosynthesis projection images, 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 the fibroglandular tissue density map is a three-dimensional map.
3. The method of claim 2 , wherein computing the fibroglandular tissue density map comprises processing at least two of the x-ray tomosynthesis projection images to compute, for each of the at least two processed x-ray tomosynthesis projection images, 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 respective x-ray tomosynthesis 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.
4. The method of claim 1 , further comprising displaying the fibroglandular tissue density map of the breast to a user on a review workstation.
5. The method of claim 4 , wherein the x-ray image data comprises a two-dimensional x-ray mammogram, and wherein the fibroglandular tissue density map is a two-dimensional volumetric breast density (VBD) map.
6. 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 1 .
7. 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 1 .
8. The method of claim 1 , wherein designating a candidate CAD finding at a location of higher fibroglandular tissue density as a marked CAD finding requires a higher certainly of finding than is required for designating a candidate CAD finding as a marked CAD finding at a location of lower fibroglandular tissue density.
9. The method of claim 4 , further comprising displaying a breast x-ray image to the user on the review workstation with viewable annotation markers of the breast x-ray image corresponding to each marked CAD finding.
10. The method of claim 9 , wherein the review workstation does not display annotation markers corresponding to non-marked CAD findings.
11. The method of claim 1 , the fibroglandular tissue density metric being based on a physical description of the breast.
12. The method of claim 11 , the physical description of the breast comprising a height of fibroglandular tissue above a pixel image.
13. A computer-implemented method for processing and displaying information associated with breast x-ray images, comprising:
acquiring or receiving x-ray image data of a breast, wherein the acquired or received x-ray image data comprises a breast x-ray tomosynthesis volume computed from a plurality of x-ray tomosynthesis projection images, 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
computing a three-dimensional fibroglandular tissue density map of the breast based at least in part on information associated with the acquired or received x-ray image data of the breast, the three-dimensional 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, wherein computing the three-dimensional fibroglandular tissue density map comprises processing at least two of the x-ray tomosynthesis projection images to compute, for each of the at least two processed x-ray tomosynthesis projection images, 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 respective x-ray tomosynthesis 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, wherein the three-dimensional fibroglandular tissue density map indicates a range of densities in the breast.
14. The method of claim 13 , further comprising displaying the three-dimensional fibroglandular tissue density map of the breast to a user on a review workstation.
15. The method of claim 13 , wherein the x-ray image data comprises a two-dimensional x-ray mammogram.
16. The method of claim 13 , further comprising:
generating or receiving candidate computer aided detection findings associated with the x-ray image data, 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 comprising a certainty of finding metric,
wherein respective candidate CAD findings are designated as marked or non-marked based at least in part on respective certainties of finding metrics and respective fibroglandular tissue density metrics at respective candidate CAD finding locations.
17. The method of claim 16 , wherein designating a candidate CAD finding at a location of higher fibroglandular tissue density as a marked CAD finding requires a higher certainly of finding than is required for designating a candidate CAD finding as a marked CAD finding at a location of lower fibroglandular tissue density.
18. The method of claim 17 , further comprising displaying a breast x-ray image to the user on the review workstation with viewable annotation markers of the breast x-ray image corresponding to each marked CAD finding.
19. The method of claim 18 , wherein the review workstation does not display annotation markers corresponding to non-marked CAD findings.
20. The method of claim 13 , the fibroglandular tissue density metric being based on a physical description of the breast.
21. The method of claim 20 , the physical description of the breast comprising a height of fibroglandular tissue above a pixel image.
22. 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 .
23. 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 .