3D Computer-Aided Detection for Digital Breast Tomosynthesis: Comparison with 2D Computer-Aided Detection for Digital Mammography in the Detection of Calcifications
A Jung Chu,
Nariya Cho,
Jung Min Chang,
Won Hwa Kim,
Su Hyun Lee,
Sung Eun Song,
Sung Ui Shin,
Woo Kyung Moon
Affiliations
A Jung Chu
Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Korea
Nariya Cho
Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Korea
Jung Min Chang
Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Korea
Won Hwa Kim
Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Korea
Su Hyun Lee
Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Korea
Sung Eun Song
Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Korea
Sung Ui Shin
Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Korea
Woo Kyung Moon
Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Korea
Purpose To retrospectively evaluate the performance of 3D computer-aided detection (CAD) for digital breast tomosynthesis (DBT) in the detection of calcifications in comparison with 2D CAD for digital mammography (DM). Materials and Methods Between 2012 and 2013, both 3D CAD and 2D CAD systems were retrospectively applied to the calcification data set including 69 calcifications (31 malignant calcifications and 38 benign calcifications) and the normal data set including 20 bilateral normal mammograms. Each data set consisted of paired DBT and DM images. Sensitivities for the detection of malignant calcifications were calculated from the calcification data set. False-positive mark rates were calculated from the normal data set. They were compared between the two systems. Results Sensitivities of 3D CAD [100% (31/31) at levels 2, 1, and 0] were same as those of the 2D CAD system [100% (31/31) at levels 2 and 1] (p = 1.0, respectively). The mean value of false-positive marks per view with 3D CAD was higher than that with 2D CAD at level 2 (0.52 marks ± 0.91 vs. 0.07 marks ± 0.26, p = 0.009). Conclusion 3D CAD for DBT showed equivalent sensitivity, albeit with a higher false-positive mark rate, than 2D CAD for DM in the detection of calcifications.
