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
  • [21] Improved Curvature Estimation for Computer-aided Detection of Colonic Polyps in CT Colonography
    Zhu, Hongbin
    Fan, Yi
    Lu, Hongbing
    Liang, Zhengrong
    ACADEMIC RADIOLOGY, 2011, 18 (08) : 1024 - 1034
  • [22] Sensitivity of CT Colonography for Nonpolypoid Colorectal Lesions Interpreted by Human Readers and With Computer-Aided Detection
    Park, Seong Ho
    Kim, So Yeon
    Lee, Seung Soo
    Bogoni, Luca
    Kim, Ah Young
    Yang, Suk-Kyun
    Myung, Seung-Jae
    Byeon, Jeong-Sik
    Ye, Byong Duk
    Ha, Hyun Kwon
    AMERICAN JOURNAL OF ROENTGENOLOGY, 2009, 193 (01) : 70 - 78
  • [23] Computer-aided detection for CT colonography: update 2007
    Didier Bielen
    Gabriel Kiss
    Abdominal Imaging, 2007, 32 : 571 - 581
  • [24] Novel 3D Radiomic Features for computer-Aided Polyp Detection in CT Colonography
    Ren, Yacheng
    Chen, Yizhi
    Lu, Lin
    Zhao, Jun
    IEEE ACCESS, 2018, 6 : 74506 - 74520
  • [25] Current concepts in computer-aided detection for CT colonography
    Summers, Ronald M.
    2007 4TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING : MACRO TO NANO, VOLS 1-3, 2007, : 496 - 499
  • [26] Computer-Aided Detection of Non-polypoid Flat Lesions in CT Colonography: Observer Performance Study
    Ryu, Yasuji
    Naeppi, Janne J.
    Minh Phan
    Yoshida, Hiroyuki
    ABDOMINAL IMAGING: COMPUTATION AND CLINICAL APPLICATIONS, 2013, 8198 : 81 - 88
  • [27] Comparative performance of a primary-reader and second-reader paradigm of computer-aided detection for CT colonography in a low-prevalence screening population
    Mototaka Miyake
    Gen Iinuma
    Stuart A. Taylor
    Steve Halligan
    Tsuyoshi Morimoto
    Tamaki Ichikawa
    Hideto Tomimatsu
    Gareth Beddoe
    Kazuro Sugimura
    Yasuaki Arai
    Japanese Journal of Radiology, 2013, 31 : 310 - 319
  • [28] Computer-aided detection of colonic polyps at CT colonography using a Hessian matrix-based algorithm: Preliminary study
    Kim, Se Hyung
    Lee, Jeong Min
    Lee, Joon-Goo
    Kim, Jong Hyo
    Lefere, Philippe A.
    Han, Joon Koo
    Choi, Byung Ihn
    AMERICAN JOURNAL OF ROENTGENOLOGY, 2007, 189 (01) : 41 - 51
  • [29] Impact of Computer-aided Detection on the Cost-effectiveness of CT Colonography
    Regge, Daniele
    Hassan, Cesare
    Pickhardt, Perry J.
    Laghi, Andrea
    Zullo, Angelo
    Kim, David H.
    Iafrate, Franco
    Morini, Sergio
    RADIOLOGY, 2009, 250 (02) : 488 - 497
  • [30] CT Colonography: Preliminary Assessment of a Double-Read Paradigm That Uses Computer-aided Detection as the First Reader
    Iussich, Gabriella
    Correale, Loredana
    Senore, Carlo
    Segnan, Nereo
    Laghi, Andrea
    Iafrate, Franco
    Campanella, Delia
    Neri, Emanuele
    Cerri, Francesca
    Hassan, Cesare
    Regge, Daniele
    RADIOLOGY, 2013, 268 (03) : 743 - 751