A comparison of axial versus coronal image viewing in computer-aided detection of lung nodules on CT

被引:7
|
作者
Iwasawa, Tae [1 ]
Matsumoto, Sumiaki [2 ,3 ]
Aoki, Takatoshi [4 ]
Okada, Fumito [5 ]
Nishimura, Yoshihiro [6 ]
Yamagata, Hitoshi [7 ]
Ohno, Yoshiharu [2 ,3 ]
机构
[1] Kanagawa Cardiovasc & Resp Ctr, Dept Radiol, Kanazawa Ku, Yokohama, Kanagawa 2360051, Japan
[2] Kobe Univ, Grad Sch Med, Adv Biomed Imaging Res Ctr, Kobe, Hyogo 657, Japan
[3] Kobe Univ, Grad Sch Med, Dept Radiol, Div Diagnost & Funct Imaging Res, Kobe, Hyogo 657, Japan
[4] Univ Occupat & Environm Hlth, Dept Radiol, Kitakyushu, Fukuoka 807, Japan
[5] Oita Univ, Fac Med, Dept Radiol, Oita 87011, Japan
[6] Kobe Univ, Grad Sch Med, Dept Internal Med, Div Resp Med, Kobe, Hyogo 657, Japan
[7] Toshiba Med Syst Corp, Otawara, Japan
关键词
Lung; Neoplasm; CT; Computer-aided detection; RADIOLOGISTS DETECTION; PULMONARY NODULES; MULTIDETECTOR CT; 2ND READER; ROW CT; DIAGNOSIS; OBSERVER; PERFORMANCE; CAD; MPR;
D O I
10.1007/s11604-014-0383-0
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
To compare primarily viewing axial images (Axial mode) versus coronal reconstruction images (Coronal mode) in computer-aided detection (CAD) of lung nodules on multidetector computed tomography (CT) in terms of detection performance and reading time. Sixty CT data sets from two institutions were collected prospectively. Ten observers (6 radiologists, 4 pulmonologists) with varying degrees of experience interpreted the data sets using CAD as a second reader (performing nodule detection first without then with aid). The data sets were interpreted twice, once each for Axial and Coronal modes, in two sessions held 4 weeks apart. Jackknife free-response receiver-operating characteristic analysis was used to compare detection performances in the two modes. Mean figure-of-merit values with and without aid were 0.717 and 0.684 in Axial mode and 0.702 and 0.671 in Coronal mode; use of CAD significantly increased the performance of observers in both modes (P < 0.01). Mean reading times for radiologists did not significantly differ between Axial (156 +/- A 74 s) and Coronal mode (164 +/- A 69 s; P = 0.08). Mean reading times for pulmonologists were significantly lower in Coronal (112 +/- A 53 s) than in Axial mode (130 +/- A 80 s; P < 0.01). There was no statistically significant difference between Axial and Coronal modes for lung nodule detection with CAD.
引用
收藏
页码:76 / 83
页数:8
相关论文
共 50 条
  • [21] Computer-aided detection (CAD) of lung nodules in CT scans: radiologist performance and reading time with incremental CAD assistance
    Roos, Justus E.
    Paik, David
    Olsen, David
    Liu, Emily G.
    Chow, Lawrence C.
    Leung, Ann N.
    Mindelzun, Robert
    Choudhury, Kingshuk R.
    Naidich, David P.
    Napel, Sandy
    Rubin, Geoffrey D.
    EUROPEAN RADIOLOGY, 2010, 20 (03) : 549 - 557
  • [22] Computer-aided detection (CAD) of lung nodules in CT scans: radiologist performance and reading time with incremental CAD assistance
    Justus E. Roos
    David Paik
    David Olsen
    Emily G. Liu
    Lawrence C. Chow
    Ann N. Leung
    Robert Mindelzun
    Kingshuk R. Choudhury
    David P. Naidich
    Sandy Napel
    Geoffrey D. Rubin
    European Radiology, 2010, 20 : 549 - 557
  • [23] A cloud-based computer-aided detection system improves identification of lung nodules on computed tomography scans of patients with extra-thoracic malignancies
    Vassallo, Lorenzo
    Traverso, Alberto
    Agnello, Michelangelo
    Bracco, Christian
    Campanella, Delia
    Chiara, Gabriele
    Fantacci, Maria Evelina
    Torres, Ernesto Lopez
    Manca, Antonio
    Saletta, Marco
    Giannini, Valentina
    Mazzetti, Simone
    Stasi, Michele
    Cerello, Piergiorgio
    Regge, Daniele
    EUROPEAN RADIOLOGY, 2019, 29 (01) : 144 - 152
  • [24] Computer-aided detection and automated CT volumetry of pulmonary nodules
    Marten, Katharina
    Engelke, Christoph
    EUROPEAN RADIOLOGY, 2007, 17 (04) : 888 - 901
  • [25] Computer-aided detection and automated CT volumetry of pulmonary nodules
    Katharina Marten
    Christoph Engelke
    European Radiology, 2007, 17 : 888 - 901
  • [26] Evaluation of a computer aided detection system for lung nodules with ground glass opacity component on multidetector-row CT
    Beigelman-Aubry, C.
    Hill, C.
    Boulanger, X.
    Brun, A. L.
    Leclercq, D.
    Golmard, J. L.
    Grenier, P. A.
    Lucidarme, O.
    JOURNAL DE RADIOLOGIE, 2009, 90 (12): : 1843 - 1849
  • [27] Improvement in detection of pulmonary nodules: Digital image processing and computer-aided diagnosis
    MacMahon, H
    RADIOGRAPHICS, 2000, 20 (04) : 1169 - 1177
  • [28] Application value of a computer-aided diagnosis and management system for the detection of lung nodules
    Chen, Jingwen
    Cao, Rong
    Jiao, Shengyin
    Dong, Yunpeng
    Wang, Zilong
    Zhu, Hua
    Luo, Qian
    Zhang, Lei
    Wang, Han
    Yin, Xiaorui
    QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2023, 13 (10) : 6929 - +
  • [29] Computer-aided detection of lung nodules by SVM based on 3D matrix patterns
    Wang, Qingzhu
    Kang, Wenwei
    Wu, Chunming
    Wang, Bin
    CLINICAL IMAGING, 2013, 37 (01) : 62 - 69
  • [30] True Detection Versus "Accidental" Detection of Small Lung Cancer by a Computer-Aided Detection (CAD) Program on Chest Radiographs
    Li, Feng
    Engelmann, Roger
    Doi, Kunio
    MacMahon, Heber
    JOURNAL OF DIGITAL IMAGING, 2010, 23 (01) : 66 - 72