Predicting error in detecting mammographic masses among radiology trainees using statistical models based on BI‐RADS features. Issue 3 (26th February 2014)

• Record Type: Journal Article
• Authors: Grimm, Lars J.; Ghate, Sujata V.; Yoon, Sora C.; Kuzmiak, Cherie M.; Kim, Connie; Mazurowski, Maciej A.
• Is Part Of: Medical physics. Volume 41:Issue 3(2014)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2014-02-26
• Subjects: Mammography -- Mammography -- Education -- Instructional computer use; biomedical education -- computer aided instruction -- diagnostic radiography -- error statistics -- feature extraction -- mammography -- medical image processing -- sensitivity analysis -- statistical analysis; mammography -- education -- receiver operating characteristic curves -- performance; Biological material, e.g. blood, urine; Haemocytometers -- Digital computing or data processing equipment or methods, specially adapted for specific applications -- Image data processing or generation, in general -- Electrically‐operated educational appliances; Mammography -- Medical imaging -- Radiologists -- Ultrasonography -- Graduates -- Computer software -- Cancer -- Computer modeling -- Statistical model calculations -- Image detection systems; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1118/1.4866379
• Languages: English
• ISSNs: 0094-2405

Abstract

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.