Computerized Detection of Breast Cancer On Automated Breast Ultrasound for Women with Dense Breasts
K Drukker*, C Sennett, M Giger, Univ Chicago, Chicago, ILWE-E-134-4 Wednesday 2:00PM - 3:50PM Room: 134
Purpose. Develop a computer-aided detection method and investigate its feasibility for detection of breast cancer in automated 3D ultrasound for women with dense breasts.
Methods. The HIPAA-compliant study involved a dataset of 3D automated breast ultrasound image volumes (views) acquired with a U-Systems SomoV ABUS system for 185 asymptomatic women with dense breasts (BI-RADS Composition/Density 3 or 4). For each patient, three 3D views per breast were acquired. A total of 52 patients had breast cancer (61 cancers) and 31 patients (32 cancers) had a screening-mammogram, clinically-assigned BI-RADS Assessment Category 1 or 2, i.e., were mammographically negative. All software was developed in-house and involved 3 steps: 1) detection of initial tumor candidates, 2) characterization of candidates, and 3) elimination of false-positive detections. Performance was assessed through the cancer detection sensitivity as a function of the number of marks (detections) per view.
Results. At a single mark per view, i.e., 6 marks per patient, the median detection sensitivity of our computerized method was 50.0% (16/32) for the patients with a screening mammogram assigned BI-RADS category 1 or 2, similar to the 49.9% on average obtained for these by patients by 17 radiologists in a reader study. At 3 marks per view, the sensitivity was 69% (22/32)+/-5% for the BI-RADS 1 and 2 patients, and 64% (39/61)+/-3% for all patients.
Conclusion. Promising detection sensitivity was obtained for this 3D ultrasound dataset of women with dense breasts at a rate of false-positive detections that may be feasible for clinical implementation.
Funding Support, Disclosures, and Conflict of Interest: Conflict of interest statement: M.L.G. is a stockholder in R2 Technology/Hologic and receives royalties from Hologic, GE Medical Systems, MEDIAN Technologies, Riverain Medical, Mitsubishi and Toshiba. K.D. received royalties from Hologic. It is the University of Chicago Conflict of Interest Policy that investigators disclose publicly actual or potential significant financial interest that would reasonably appear to be directly and significantly affected by the research activities. Funding: This work was supported in part by NIH S10 RR021039 and P30 CA14599. and the Department of Radiology of the University of Chicago