Chest

European Radiology

, Volume 20, Issue 3, pp 549-557

First online:

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

  • Justus E. RoosAffiliated withDepartment of Radiology, Stanford University Medical Center Email author 
  • , David PaikAffiliated withDepartment of Radiology, Stanford University Medical Center
  • , David OlsenAffiliated withDepartment of Radiology, Stanford University Medical Center
  • , Emily G. LiuAffiliated withDepartment of Radiology, Stanford University Medical Center
  • , Lawrence C. ChowAffiliated withDepartment of Radiology, Oregon Health and Science University
  • , Ann N. LeungAffiliated withDepartment of Radiology, Stanford University Medical Center
  • , Robert MindelzunAffiliated withDepartment of Radiology, Stanford University Medical Center
  • , Kingshuk R. ChoudhuryAffiliated withDepartment of Radiology, Stanford University Medical Center
  • , David P. NaidichAffiliated withDepartment of Radiology, New York University Medical Center
    • , Sandy NapelAffiliated withDepartment of Radiology, Stanford University Medical Center
    • , Geoffrey D. RubinAffiliated withDepartment of Radiology, Stanford University Medical Center

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access

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 tomography MDCT Computer-aided detection CAD Pulmonary nodules Diagnostic performance