27 May 2015 Radiological technologists’ performance for the detection of malignant microcalcifications in digital mammograms without and with a computer-aided detection system
Author Affiliations +
Abstract
The aim of this study was to investigate the diagnostic performance of radiological technologists (RTs) in the detection of malignant microcalcifications and to evaluate how much computer-aided detection (CADe) improved their performances compared with those by expert breast radiologists (BRs). Six board-certified breast RTs and four board-certified BRs participated in a free-response receiver operating characteristic observer study. The dataset consisted of 75 cases (25 malignant, 25 benign, and 25 normal cases) of digital mammograms, selected from the digital database for screening mammography provided by the University of South Florida. Average figure of merit (FOM) of the RTs’ performances was statistically analyzed using jack-knife free-response receiver operating characteristic and compared with that of expert BRs. The detection performance of RTs was significantly improved by using CADe; average sensitivity was increased from 46.7% to 56.7%, with a decrease in the average number of false positives per case from 0.19 to 0.13. Detection accuracy of an average FOM was improved from 0.680 to 0.816 (p=0.001) and the difference in FOMs between RTs and radiologists failed to reach statistical significance. RTs’ performances for the identification of malignant microcalcifications on digital mammography were sufficiently high and comparable to those of radiologists by using CADe.
© 2015 Society of Photo-Optical Instrumentation Engineers (SPIE) 2329-4302/2015/$25.00 © 2015 SPIE
Rie Tanaka, Miho Takamori, Yoshikazu Uchiyama, and Junji Shiraishi "Radiological technologists’ performance for the detection of malignant microcalcifications in digital mammograms without and with a computer-aided detection system," Journal of Medical Imaging 2(2), 024505 (27 May 2015). https://doi.org/10.1117/1.JMI.2.2.024505
Published: 27 May 2015
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Computer aided diagnosis and therapy

Mammography

Breast

Bromine

Digital mammography

Solids

Statistical analysis

Back to Top