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
  • [1] Reduction of false positives on the rectal tube in computer-aided detection for CT colonography
    Iordanescu, G
    Summers, RM
    MEDICAL PHYSICS, 2004, 31 (10) : 2855 - 2862
  • [2] CT colonography with computer-aided detection as a second reader: Observer performance study
    Petrick, Nicholas
    Haider, Maruf
    Summers, Ronald M.
    Yeshwant, Srinath C.
    Brown, Linda
    Iuliano, Edward M.
    Louie, Adeline
    Choi, J. Richard
    Pickhardt, Perry J.
    RADIOLOGY, 2008, 246 (01) : 148 - 156
  • [3] CT Colonography with Computer-aided Detection: Recognizing the Causes of False-Positive Reader Results
    Trilisky, Igor
    Dachman, Abraham H.
    Wroblewski, Kristen
    Vannier, Michael W.
    Horne, John M.
    RADIOGRAPHICS, 2014, 34 (07) : 1885 - 1905
  • [4] Computer-aided detection of polyps in CT colonography:: Evaluation of volumetric features in differentiating polyps from false positives
    Näppi, J
    Dachman, AH
    MacEneaney, PM
    Yoshida, H
    CARS 2001: COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2001, 1230 : 635 - 640
  • [5] Projection-based features for reducing false positives in computer-aided detection of colonic polyps in CT colonography
    Zhu, Hongbin
    Barish, Matthew
    Pickhardt, Perry
    Fan, Yi
    Posniak, Erica
    Richards, Robert
    Liang, Zhengrong
    MEDICAL IMAGING 2010: COMPUTER - AIDED DIAGNOSIS, 2010, 7624
  • [6] Computer-Aided Detection False Positives in Colonoscopy
    Hsieh, Yu-Hsi
    Tang, Chia-Pei
    Tseng, Chih-Wei
    Lin, Tu-Liang
    Leung, Felix W.
    DIAGNOSTICS, 2021, 11 (06)
  • [7] Computer-aided detection for CT colonography
    Xu Y.-R.
    Zhao J.
    Journal of Shanghai Jiaotong University (Science), 2014, 19 (05) : 531 - 537
  • [8] Computer-Aided Detection for CT Colonography
    徐嫣然
    赵俊
    JournalofShanghaiJiaotongUniversity(Science), 2014, 19 (05) : 531 - 537
  • [9] Invited Commentary on "CT Colonography with Computer-aided Detection: Recognizing the Causes of False-Positive Reader Results"
    Yee, Judy
    RADIOGRAPHICS, 2014, 34 (07) : 1906 - 1907
  • [10] Effect of computer-aided detection as a second reader in multidetector-row CT colonography
    Thomas Mang
    Philipp Peloschek
    Christina Plank
    Andrea Maier
    Anno Graser
    Michael Weber
    Christian Herold
    Luca Bogoni
    Wolfgang Schima
    European Radiology, 2007, 17 : 2598 - 2607