RT Journal Article
T1 Automatic detection of pulmonary nodules: Evaluation of performance using two different MDCT scanners
A1 Souto Bayarri, José Miguel
A1 Suárez Cuenca, Jorge Juan
A1 García Tahoces, Pablo
A1 Revel, Marie-Pierre
A1 Delhaye, Damien
A1 Carreira Villamor, José Martín
A1 Remy-Jardin, Martin
A1 Remy, Jacque
K1 Computer aided diagnosis
K1 Computer-aided diagnosis
K1 Multidetector row computed tomography
K1 Pulmonary nodule
K1 Automatic detection of pulmonary nodules
AB The purpose of this study was to evaluate the diagnostic performance of a computer-aided diagnosis (CAD) system, on the detection of pulmonary nodules in multidetector row computed tomography (MDCT) images, by using  two different MDCT scanners. The computerized scheme was based on the iris filter. We have collected CT cases of patients with pulmonary nodules. We have included in the study one hundred and thirty-two calcified and noncalcified nodules, measuring 4-30 mm in diameter. CT examinations were performed by using two different equipments: a CT scanner (SOMATOM Emotion 6), and a dual-source computed tomography system (SOMATOM Definition) (Siemens Medical System, Forchheim, Germany), with the following parameters: collimation, 6x1.0mm (Emotion 6); and 64×0.6mm (Definition); 100-130 kV; 70-110 mAs. Data were reconstructed with a slice thickness of 1.25mm (Emotion 6) and 1mm (Definition). True positive cases were determined by an independent interpretation of the study by three experienced chest radiologists,  the panel decision being used as the reference standard. Free-response Receiver Operating Characteristic curves, sensitivity and number of false-positive per scan, were calculated. Our CAD scheme, for the test set of the study, yielded a sensitivity of 80%, with an average of 5.2 FPs per examination. At an average false positive rate of 9 per scan, our CAD scheme achieved sensitivities of 94% for all nodules, 94.5% for solid, 80% for non-solid, 84% for spiculated, and 97% for non-spiculated nodules. These encouraging results suggest that our CAD system, advocated as a second reader, may help radiologists in the detection of lung nodules in MDCT
PB Sciedu Press
SN 1925-4008
YR 2012
FD 2012
LK http://hdl.handle.net/10347/17788
UL http://hdl.handle.net/10347/17788
LA eng
NO BAYARRI, M., Suárez-Cuenca, J., Tahoces, P., Revel, M., Delhaye, D., & Carreira, J. et al. (2012). Automatic detection of pulmonary nodules: Evaluation of performance using two different MDCT scanners. Journal Of Biomedical Graphics And Computing, 2(2). doi: 10.5430/jbgc.v2n2p55
NO This work has been partially supported by the Xunta de Galicia (expte. nº PGIDIT06BTF20802PR), and by the FIS (expte. nº PI060058) and (expte. nº PI080072)
DS Minerva
RD 24 abr 2026