RATIONALE AND OBJECTIVES: To retrospectively investigate the effect of a computer-aided detection (CAD) system on radiologists' performance for detecting small pulmonary nodules in computed tomography (CT) examinations, with a panel of expert radiologists serving as the reference standard. MATERIALS AND METHODS: Institutional review board approval was obtained. Our dataset contained 52 CT examinations collected by the Lung Image Database Consortium, and 33 from our institution. All CTs were read by multiple expert thoracic radiologists to identify the reference standard for detection. Six other thoracic radiologists read the CT examinations first without and then with CAD. Performance was evaluated using free-response receiver operating characteristics (FROC) and the jackknife FROC analysis methods (JAFROC) for nodules above different diameter thresholds. RESULTS: A total of 241 nodules, ranging in size from 3.0 to 18.6 mm (mean, 5.3 mm) were identified as the reference standard. At diameter thresholds of 3, 4, 5, and 6 mm, the CAD system had a sensitivity of 54%, 64%, 68%, and 76%, respectively, with an average of 5.6 false positives (FPs) per scan. Without CAD, the average figures of merit (FOMs) for the six radiologists, obtained from JAFROC analysis, were 0.661, 0.729, 0.793, and 0.838 for the same nodule diameter thresholds, respectively. With CAD, the corresponding average FOMs improved to 0.705, 0.763, 0.810, and 0.862, respectively. The improvement achieved statistical significance for nodules at the 3 and 4 mm thresholds (P = .002 and .020, respectively), and did not achieve significance at 5 and 6 mm (P = .18 and .13, respectively). At a nodule diameter threshold of 3 mm, the radiologists' average sensitivity and FP rate were 0.56 and 0.67, respectively, without CAD, and 0.67 and 0.78 with CAD. CONCLUSION: CAD improves thoracic radiologists' performance for detecting pulmonary nodules smaller than 5 mm on CT examinations, which are often overlooked by visual inspection alone.
RATIONALE AND OBJECTIVES: To retrospectively investigate the effect of a computer-aided detection (CAD) system on radiologists' performance for detecting small pulmonary nodules in computed tomography (CT) examinations, with a panel of expert radiologists serving as the reference standard. MATERIALS AND METHODS: Institutional review board approval was obtained. Our dataset contained 52 CT examinations collected by the Lung Image Database Consortium, and 33 from our institution. All CTs were read by multiple expert thoracic radiologists to identify the reference standard for detection. Six other thoracic radiologists read the CT examinations first without and then with CAD. Performance was evaluated using free-response receiver operating characteristics (FROC) and the jackknife FROC analysis methods (JAFROC) for nodules above different diameter thresholds. RESULTS: A total of 241 nodules, ranging in size from 3.0 to 18.6 mm (mean, 5.3 mm) were identified as the reference standard. At diameter thresholds of 3, 4, 5, and 6 mm, the CAD system had a sensitivity of 54%, 64%, 68%, and 76%, respectively, with an average of 5.6 false positives (FPs) per scan. Without CAD, the average figures of merit (FOMs) for the six radiologists, obtained from JAFROC analysis, were 0.661, 0.729, 0.793, and 0.838 for the same nodule diameter thresholds, respectively. With CAD, the corresponding average FOMs improved to 0.705, 0.763, 0.810, and 0.862, respectively. The improvement achieved statistical significance for nodules at the 3 and 4 mm thresholds (P = .002 and .020, respectively), and did not achieve significance at 5 and 6 mm (P = .18 and .13, respectively). At a nodule diameter threshold of 3 mm, the radiologists' average sensitivity and FP rate were 0.56 and 0.67, respectively, without CAD, and 0.67 and 0.78 with CAD. CONCLUSION: CAD improves thoracic radiologists' performance for detecting pulmonary nodules smaller than 5 mm on CT examinations, which are often overlooked by visual inspection alone.
Authors: Metin N Gurcan; Berkman Sahiner; Nicholas Petrick; Heang-Ping Chan; Ella A Kazerooni; Philip N Cascade; Lubomir Hadjiiski Journal: Med Phys Date: 2002-11 Impact factor: 4.071
Authors: Matthew S Brown; Jonathan G Goldin; Robert D Suh; Michael F McNitt-Gray; James W Sayre; Denise R Aberle Journal: Radiology Date: 2003-01 Impact factor: 11.105
Authors: S Sone; F Li; Z G Yang; S Takashima; Y Maruyama; M Hasegawa; J C Wang; S Kawakami; T Honda Journal: Br J Radiol Date: 2000-02 Impact factor: 3.039
Authors: Stefan Diederich; Dag Wormanns; Michael Semik; Michael Thomas; Horst Lenzen; Nikolaus Roos; Walter Heindel Journal: Radiology Date: 2002-03 Impact factor: 11.105
Authors: Stephen J Swensen; James R Jett; Thomas E Hartman; David E Midthun; Jeff A Sloan; Anne-Marie Sykes; Gregory L Aughenbaugh; Medy A Clemens Journal: Radiology Date: 2003-01-24 Impact factor: 11.105
Authors: E Lopez Torres; E Fiorina; F Pennazio; C Peroni; M Saletta; N Camarlinghi; M E Fantacci; P Cerello Journal: Med Phys Date: 2015-04 Impact factor: 4.071
Authors: Ethan Walker; Yiqiao Liu; InYoung Kim; David L Wilson; James P Basilion; Daniel L Popkin; Mark Biro; Sukanya Raj Iyer; Harib Ezaldein; Jeffrey Scott; Miesha Merati; Rachel Mistur; Bo Zhou; Brian Straight; Joshua J Yim; Matthew Bogyo; Margaret Mann Journal: Cancer Res Date: 2020-03-04 Impact factor: 12.701
Authors: Joseph E Burns; Jianhua Yao; Tatjana S Wiese; Hector E Muñoz; Elizabeth C Jones; Ronald M Summers Journal: Radiology Date: 2013-02-28 Impact factor: 11.105