Is CAD Able to Assist in the Detection of Subtle Breast Findings - Lobular Cancers, and T1a/T1b Masses in Dense Breasts?

Isaac Leichter, Zahava Gallimidi, Asnat Heyman-Reiss, Nicolas Merlet, Eli Ratner, Menachem Abramov, Inna Stainvas, Richard Lederman

Abstract: 234 pathology-proven FFDM malignant cases and 3872 normal cases were culled retrospectively from 6 screening facilities. For malignant cases, location and size of the biopsied finding and breast density were recorded. All cases were run with a prototype CAD algorithm (Siemens) to evaluate the impact of breast density, lesion size and lesion pathology on CAD performance. The overall CAD sensitivity was 84.2%, with 85.5% sensitivity in "non-dense" breasts and 82.3% in "dense" breasts (p=0.26). No significant difference (p=0.10) was found between CAD sensitivity for ductal lesions (86.4%) and lobular lesions (70.6%). The sensitivity for invasive ductal lesions (86.9%) was slightly higher (p=0.30) than for in-situ lesions (82.6%). The CAD sensitivity for large masses (90.1%) was significantly higher (p<0.001) than for small masses (66.0%). The false mark rate was 1.01. The study indicates that CAD can assist the radiologist in identifying suspicious lesions, independent of breast density, lesion pathology or invasiveness.