Predicting error in detecting mammographic masses among radiology trainees using statistical models based on BI-RADS features

Authors

  • Grimm Lars J.,

    Corresponding author
    1. Department of Radiology, Duke University Medical Center, Box 3808, Durham, North Carolina 27710
    • Author to whom correspondence should be addressed. Electronic mail: Lars.grimm@duke.edu; Telephone: (919) 684-7293; Fax: (919) 684-7151.

    Search for more papers by this author
  • Ghate Sujata V.,

    1. Department of Radiology, Duke University Medical Center, Box 3808, Durham, North Carolina 27710
    Search for more papers by this author
    • b)

      Telephone: (919) 684-7649; Fax: (919) 684-7114.

  • Yoon Sora C.,

    1. Department of Radiology, Duke University Medical Center, Box 3808, Durham, North Carolina 27710
    Search for more papers by this author
    • c)

      Telephone: (919) 684-7645; Fax: (919) 684-7114.

  • Kuzmiak Cherie M.,

    1. Department of Radiology, University of North Carolina School of Medicine, 2006 Old Clinic, CB# 7510, Chapel Hill, North Carolina 27599
    Search for more papers by this author
    • d)

      Telephone: (919) 966-1081; Fax: (919) 966-1994.

  • Kim Connie,

    1. Department of Radiology, Duke University Medical Center, Box 3808, Durham, North Carolina 27710
    Search for more papers by this author
    • c)

      Telephone: (919) 684-7645; Fax: (919) 684-7114.

  • Mazurowski Maciej A.

    1. Duke University Medical Center, Box 2731 Medical Center, Durham, North Carolina 27710
    Search for more papers by this author
    • e)

      Telephone: (919) 684-1466; Fax: (919) 684-1494.


Abstract

Purpose:

The purpose of this study is to explore Breast Imaging-Reporting and Data System (BI-RADS) features as predictors of individual errors made by trainees when detecting masses in mammograms.

Methods:

Ten radiology trainees and three expert breast imagers reviewed 100 mammograms comprised of bilateral medial lateral oblique and craniocaudal views on a research workstation. The cases consisted of normal and biopsy proven benign and malignant masses. For cases with actionable abnormalities, the experts recorded breast (density and axillary lymph nodes) and mass (shape, margin, and density) features according to the BI-RADS lexicon, as well as the abnormality location (depth and clock face). For each trainee, a user-specific multivariate model was constructed to predict the traineeˈs likelihood of error based on BI-RADS features. The performance of the models was assessed using area under the receive operating characteristic curves (AUC).

Results:

Despite the variability in errors between different trainees, the individual models were able to predict the likelihood of error for the trainees with a mean AUC of 0.611 (range: 0.502–0.739, 95% Confidence Interval: 0.543–0.680,p < 0.002).

Conclusions:

Patterns in detection errors for mammographic masses made by radiology trainees can be modeled using BI-RADS features. These findings may have potential implications for the development of future educational materials that are personalized to individual trainees.

Ancillary