Selective Display Of Computer-Aided Detection Findings With Associated Breast X-Ray Mammogram and/or Tomosynthesis Image Information
First Claim
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.
6 Assignments
0 Petitions
Accused Products
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.
106 Citations
33 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
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. - View Dependent Claims (10, 11, 12)
-
-
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. - View Dependent Claims (14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24)
-
-
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. - View Dependent Claims (26, 27, 28, 29, 30, 31, 32, 33)
-
Specification