European Radiology

, Volume 20, Issue 3, pp 549–557

Computer-aided detection (CAD) of lung nodules in CT scans: radiologist performance and reading time with incremental CAD assistance

Authors

    • Department of RadiologyStanford University Medical Center
  • David Paik
    • Department of RadiologyStanford University Medical Center
  • David Olsen
    • Department of RadiologyStanford University Medical Center
  • Emily G. Liu
    • Department of RadiologyStanford University Medical Center
  • Lawrence C. Chow
    • Department of RadiologyOregon Health and Science University
  • Ann N. Leung
    • Department of RadiologyStanford University Medical Center
  • Robert Mindelzun
    • Department of RadiologyStanford University Medical Center
  • Kingshuk R. Choudhury
    • Department of RadiologyStanford University Medical Center
  • David P. Naidich
    • Department of RadiologyNew York University Medical Center
  • Sandy Napel
    • Department of RadiologyStanford University Medical Center
  • Geoffrey D. Rubin
    • Department of RadiologyStanford University Medical Center
Chest

DOI: 10.1007/s00330-009-1596-y

Cite this article as:
Roos, J.E., Paik, D., Olsen, D. et al. Eur Radiol (2010) 20: 549. doi:10.1007/s00330-009-1596-y

Abstract

Objective

The diagnostic performance of radiologists using incremental CAD assistance for lung nodule detection on CT and their temporal variation in performance during CAD evaluation was assessed.

Methods

CAD was applied to 20 chest multidetector-row computed tomography (MDCT) scans containing 190 non-calcified ≥3-mm nodules. After free search, three radiologists independently evaluated a maximum of up to 50 CAD detections/patient. Multiple free-response ROC curves were generated for free search and successive CAD evaluation, by incrementally adding CAD detections one at a time to the radiologists’ performance.

Results

The sensitivity for free search was 53% (range, 44%–59%) at 1.15 false positives (FP)/patient and increased with CAD to 69% (range, 59–82%) at 1.45 FP/patient. CAD evaluation initially resulted in a sharp rise in sensitivity of 14% with a minimal increase in FP over a time period of 100 s, followed by flattening of the sensitivity increase to only 2%. This transition resulted from a greater prevalence of true positive (TP) versus FP detections at early CAD evaluation and not by a temporal change in readers’ performance. The time spent for TP (9.5 s ± 4.5 s) and false negative (FN) (8.4 s ± 6.7 s) detections was similar; FP decisions took two- to three-times longer (14.4 s ± 8.7 s) than true negative (TN) decisions (4.7 s ± 1.3 s).

Conclusions

When CAD output is ordered by CAD score, an initial period of rapid performance improvement slows significantly over time because of non-uniformity in the distribution of TP CAD output and not to a changing reader performance over time.

Keywords

Multidetector-row computed tomographyMDCTComputer-aided detectionCADPulmonary nodulesDiagnostic performance

Copyright information

© European Society of Radiology 2009