PURPOSE: The aim of this study was to evaluate the efficacy of a computer-aided diagnosis (CAD) system we developed that can also respond to subsolid nodules, for lung cancer screening using low-dose spiral computed tomography (LDCT). MATERIALS AND METHODS: The institutional review board approved this study. A total of 30 positive cases (including 15 lung cancer cases) that needed further examination and 30 negative cases were used for the observer performance study. Three thoracic radiologists, five general radiologists, and three residents participated in this study in which they first read the original CT image on its own and then reassessed the same image with the assistance of CAD. Radiologists' performance was evaluated using receiver operating characteristic (ROC) analysis. RESULTS: The Az values without and with CAD were 0.872 and 0.910 for the thoracic radiologists, 0.864 and 0.924 for general radiologists, and 0.875 and 0.837 for residents, respectively. The detection accuracy improved significantly for the thoracic and general radiologists with our CAD system; however, no statistically significant difference between without or with CAD was seen for residents. CONCLUSION: This CAD system is beneficial in the detection of pulmonary nodules on LDCT when used by experienced radiologists.
PURPOSE: The aim of this study was to evaluate the efficacy of a computer-aided diagnosis (CAD) system we developed that can also respond to subsolid nodules, for lung cancer screening using low-dose spiral computed tomography (LDCT). MATERIALS AND METHODS: The institutional review board approved this study. A total of 30 positive cases (including 15 lung cancer cases) that needed further examination and 30 negative cases were used for the observer performance study. Three thoracic radiologists, five general radiologists, and three residents participated in this study in which they first read the original CT image on its own and then reassessed the same image with the assistance of CAD. Radiologists' performance was evaluated using receiver operating characteristic (ROC) analysis. RESULTS: The Az values without and with CAD were 0.872 and 0.910 for the thoracic radiologists, 0.864 and 0.924 for general radiologists, and 0.875 and 0.837 for residents, respectively. The detection accuracy improved significantly for the thoracic and general radiologists with our CAD system; however, no statistically significant difference between without or with CAD was seen for residents. CONCLUSION: This CAD system is beneficial in the detection of pulmonary nodules on LDCT when used by experienced radiologists.
Authors: Pamela M McMahon; Chung Yin Kong; Bruce E Johnson; Milton C Weinstein; Jane C Weeks; Karen M Kuntz; Jo-Anne O Shepard; Stephen J Swensen; G Scott Gazelle Journal: Radiology Date: 2008-05-05 Impact factor: 11.105
Authors: C I Henschke; D I McCauley; D F Yankelevitz; D P Naidich; G McGuinness; O S Miettinen; D M Libby; M W Pasmantier; J Koizumi; N K Altorki; J P Smith Journal: Lancet Date: 1999-07-10 Impact factor: 79.321
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: S Sone; F Li; Z G Yang; T Honda; Y Maruyama; S Takashima; M Hasegawa; S Kawakami; K Kubo; M Haniuda; T Yamanda Journal: Br J Cancer Date: 2001-01-05 Impact factor: 7.640
Authors: Christopher G Slatore; Nanda Horeweg; James R Jett; David E Midthun; Charles A Powell; Renda Soylemez Wiener; Juan P Wisnivesky; Michael K Gould Journal: Am J Respir Crit Care Med Date: 2015-08-15 Impact factor: 21.405
Authors: R Kakinuma; K Ashizawa; T Kobayashi; A Fukushima; H Hayashi; T Kondo; M Machida; M Matsusako; K Minami; K Oikado; M Okuda; S Takamatsu; M Sugawara; S Gomi; Y Muramatsu; K Hanai; Y Muramatsu; M Kaneko; R Tsuchiya; N Moriyama Journal: Br J Radiol Date: 2012-09 Impact factor: 3.039