CAD May Not be Necessary for Microcalcifications in the Digital era, CAD May Benefit Radiologists for Masses

摘要: Objective: The aim of this study was to evaluate the effectiveness computer-aided detection (CAD) mark cancer on digital mammograms at time breast diagnosis and also review retrospectively whether CAD marked if visible any available prior mammograms, thus potentially identifying an earlier stage. We sought determine why lesions may or not be by CAD. In particular, we analyzed factors such as density, mammographic views, lesion characteristics. Materials Methods: Retrospective from 2004 2008 revealed 3445 diagnosed cancers in both symptomatic asymptomatic patients; 1293 these were imaged with full field mammography (FFDM). After diagnosis, a retrospective held radiologist staff, 43 found prior-year (false-negative cases); cases are basis analysis. All had evaluation studies. Data collected included patient demographics, palpability, type, size, marks current- needle biopsy method, pathology results (core and/or surgical), surgery size. Results: On staff radiologists, discovered mammograms. masses (mass classification mass, mass calcification, architectural distortion); no pure microcalcifications identified cohort. Mammograms applied able detect 79% (34/43) 56% (24/43) during year(s). heterogeneously dense/extremely dense tissue, (27/34) taken (19/34) At 32% (11/34) craniocaudal (CC) view, 21% (7/34) mediolateral oblique (MLO) view. Lesion size those similar, average being 15 12 mm, respectively. Conclusion: Our demonstrated that can invasive carcinomas even tissue. significant portion CC view only, which indicator radiologists especially vigilant when is