Influence of Computer-Aided Detection False-Positives on Reader Performance and Diagnostic Confidence for CT Colonography

被引:19
|
作者
Taylor, Stuart A. [1 ]
Brittenden, John [2 ]
Lenton, James [3 ]
Lambie, Hannah [3 ]
Goldstone, Anthony [3 ]
Wylie, Peter N. [4 ]
Tolan, Damian [3 ]
Burling, David [4 ]
Honeyfield, Leslie [5 ]
Bassett, Paul [6 ]
Halligan, Steve [1 ]
机构
[1] Univ Coll London Hosp, Dept Specialist Imaging, London NW1 2BU, England
[2] Pinderfields Gen Hosp, Dept Clin Radiol, Wakefield, W Yorkshire, England
[3] Leeds Teaching Hosp NHS Trust, Leeds Gen Infirm, Dept Clin Radiol, Leeds, W Yorkshire, England
[4] St Marks Hosp, Dept Intestinal Imaging, Harrow, Middx, England
[5] Medicsight PLC, London, England
[6] Stat Consultancy, Ruislip, Middx, England
关键词
colorectal cancer; computer-aided detection; CT colonography; screening; TOMOGRAPHIC VIRTUAL COLONOSCOPY; POLYP DETECTION; ASSISTED DETECTION; 2ND READER; REDUCTION; CAD; SOFTWARE;
D O I
10.2214/AJR.08.1625
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
OBJECTIVE. The objective of our study was to investigate whether an increasing number of computer-aided detection (CAD) false-positives decreases reader sensitivity, specificity, and confidence for nonexpert readers of CT colonography (CTC). MATERIALS AND METHODS. Fifty CTC data sets (29 men; mean age, 65 years), 25 of which contained 35 polyps >= 5 mm, were selected in which CAD had 100% polyp sensitivity at two sphericity settings (0 and 75) but differed in the number of false-positives. The data sets were read by five readers twice: once at each sphericity setting. Sensitivity, specificity, report time, and confidence before and after second-read CAD were compared using the paired exact and Student's t test, respectively. Receiver operating characteristic (ROC) curves were generated using reader confidence (1-100) in correct case classification (normal or abnormal). RESULTS. CAD generated a mean of 42 (range, 3-118) and 15 (range, 1-36) false-positives at a sphericity of 0 and 75, respectively. CAD at both settings increased per-patient sensitivity from 82% to 87% (p = 0.03) and per-polyp sensitivity by 8% and 10% for a sphericity of 0 and 75, respectively (p < 0.001). Specificity decreased from 84% to 79% (sphericity 0 and 75, p = 0.03 and 0.07). There was no difference in sensitivity, specificity, or reader confidence between sphericity settings (p = 1.0, 1.0, 0.11, respectively). The area under the ROC curve was 0.78 (95% CI, 0.70-0.86) and 0.77 (0.68-0.85) for a sphericity of 0 and 75, respectively. CAD added a median of 4.4 minutes (interquartile range [IQR], 2.7-6.5 minutes) and 2.2 minutes (IQR, 1.2-4.0 minutes) for a sphericity of 0 and 75, respectively (p < 0.001). CONCLUSION. CAD has the potential to increase the sensitivity of readers inexperienced with CTC, although specificity may be reduced. An increased number of CAD-generated false-positives does not negate any beneficial effect but does reduce efficiency.
引用
收藏
页码:1682 / 1689
页数:8
相关论文
共 50 条
  • [41] Deep learning of contrast-coated serrated polyps for computer-aided detection in CT colonography
    Nappi, Janne J.
    Pickhardt, Perry
    Kim, David H.
    Hironaka, Toru
    Yoshida, Hiroyuki
    MEDICAL IMAGING 2017: COMPUTER-AIDED DIAGNOSIS, 2017, 10134
  • [42] Random Forest Based Computer-Aided Detection of Polyps in CT Colonography
    Ma, Ming
    Wang, Huafeng
    Song, Bowen
    Hu, Yifan
    Gu, Xianfeng
    Liang, Zhengrong
    2014 IEEE NUCLEAR SCIENCE SYMPOSIUM AND MEDICAL IMAGING CONFERENCE (NSS/MIC), 2014,
  • [43] Effect of Computer-aided Detection for CT Colonography in a Multireader, Multicase Trial
    Dachman, Abraham H.
    Obuchowski, Nancy A.
    Hoffmeister, Jeffrey W.
    Hinshaw, J. Louis
    Frew, Michael I.
    Winter, Thomas C.
    Van Uitert, Robert L.
    Periaswamy, Senthil
    Summers, Ronald M.
    Hillman, Bruce J.
    RADIOLOGY, 2010, 256 (03) : 827 - 835
  • [44] Computer-aided detection of polyps in CT colonography based on geometric features
    Yoshida, H
    Masutani, Y
    MacEnaney, P
    Dachman, A
    MEDICAL IMAGING 2001: PHYSIOLOGY AND FUNCTION FROM MULTIDIMENSIONAL IMAGES, 2001, 4321 : 53 - 57
  • [45] Computer-aided detection in CT colonography: initial clinical experience using a prototype system
    A. Graser
    F. T. Kolligs
    T. Mang
    C. Schaefer
    S. Geisbüsch
    M. F. Reiser
    C. R. Becker
    European Radiology, 2007, 17 : 2608 - 2615
  • [46] CT colonography:: Does improved z resolution help computer-aided polyp detection?
    Sundaram, P
    Beaulieu, CF
    Paik, DS
    Schraedley-Desmond, P
    Napel, S
    MEDICAL PHYSICS, 2003, 30 (10) : 2663 - 2674
  • [47] Computer-Aided Detection of Colorectal Polyps at CT Colonography: Prospective Clinical Performance and Third-Party Reimbursement
    Ziemlewicz, Timothy J.
    Kim, David H.
    Hinshaw, J. Louis
    Lubner, Meghan G.
    Robbins, Jessica B.
    Pickhardt, Perry J.
    AMERICAN JOURNAL OF ROENTGENOLOGY, 2017, 208 (06) : 1244 - 1248
  • [48] Computer-aided detection in CT colonography:: initial clinical experience using a prototype system
    Graser, A.
    Kolligs, F. T.
    Mang, T.
    Schaefer, C.
    Geisbuesch, S.
    Reiser, M. F.
    Becker, C. R.
    EUROPEAN RADIOLOGY, 2007, 17 (10) : 2608 - 2615
  • [49] High performance computer aided detection system for polyp detection in CT colonography with fluid and fecal tagging
    Liu, Jiamin
    Wang, Shijun
    Kabadi, Suraj
    Summers, Ronald M.
    MEDICAL IMAGING 2009: COMPUTER-AIDED DIAGNOSIS, 2009, 7260
  • [50] REDUCING THE FALSE POSITIVE RATE OF COMPUTER AIDED DETECTION FOR CT COLONOGRAPHY USING CONTENT BASED IMAGE RETRIEVAL
    Aman, Javed
    Yao, Jianhua
    Summers, Ronald M.
    2009 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, VOLS 1 AND 2, 2009, : 915 - 918