Role of computer-aided detection in very small screening detected invasive breast cancers.

摘要: This study aims to assess computer-aided detection (CAD) performance with full-field digital mammography (FFDM) in very small (equal or less than 1 cm) invasive breast cancers. Sixty-eight cancers equal 1 cm were retrospectively studied. All cases detected FFDM women aged 49–69 years from our cancer screening program. Radiological characteristics of lesions following BI-RADS descriptors recorded and compared CAD sensitivity. Age, size, classification, density type, histological type the neoplasm, role also assessed. Per-study specificity mass false-positive rate determined by using 100 normal consecutive studies. Thirty-seven (54.4 %) masses, 17 (25 %) calcifications, 6 (8.8 %) masses 7 (10.3 %) architectural distortions, 1 asymmetry (1.5 %) found. showed an overall sensitivity 86.7 % (masses, 86.5 %; 100 %; distortion, 57.14 %), failed detect 9 out 68 cases: 5 37 3 asymmetry. Fifteen hyperdense, all them CAD. No association was seen among morphology margins detectability. 26 % 1.76 false marks per study. In conclusion, shows a high low specificity. Lesion histology, do not influence Mammographic features, density, thickness spicules distortions influence.