Radiological technologists’ performance for the detection of malignant microcalcifications in digital mammograms without and with a computer-aided detection system

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.

[1]  Dev P Chakraborty,et al.  Observer studies involving detection and localization: modeling, analysis, and validation. , 2004, Medical physics.

[2]  Junji Shiraishi,et al.  Basic concepts and development of an all-purpose computer interface for ROC/FROC observer study , 2012, Radiological Physics and Technology.

[3]  Effect of screening mammography on cumulative survival of Japanese women aged 40–69 years with breast cancer , 2014, Breast Cancer.

[4]  David Gur,et al.  A comparison of two data analyses from two observer performance studies using Jackknife ROC and JAFROC. , 2005, Medical physics.

[5]  K. Doi,et al.  Computer-aided diagnosis scheme for histological classification of clustered microcalcifications on magnification mammograms. , 2004, Medical physics.

[6]  P. Nelemans,et al.  Performance of radiographers in mammogram interpretation: a systematic review. , 2008, Breast.

[7]  Koji Yamamoto,et al.  Computer-aided diagnosis scheme using a filter bank for detection of microcalcification clusters in mammograms , 2006, IEEE Transactions on Biomedical Engineering.

[8]  A. Jemal,et al.  Global Patterns of Cancer Incidence and Mortality Rates and Trends , 2010, Cancer Epidemiology, Biomarkers & Prevention.

[9]  Jonathan H Sunshine,et al.  How widely is computer-aided detection used in screening and diagnostic mammography? , 2010, Journal of the American College of Radiology : JACR.

[10]  Luisa P. Wallace,et al.  The "laboratory" effect: comparing radiologists' performance and variability during prospective clinical and laboratory mammography interpretations. , 2008, Radiology.

[11]  Noriaki Ohuchi,et al.  Improved Detection Rate of Early Breast Cancer in Mass Screening Combined with Mammography , 1993, Japanese journal of cancer research : Gann.

[12]  Corinne Balleyguier,et al.  CAD in questions/answers Review of the literature. , 2009, European journal of radiology.

[13]  Adele Lauria,et al.  GPCALMA: implementation in Italian hospitals of a computer aided detection system for breast lesions by mammography examination. , 2009, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[14]  C E Metz,et al.  Some practical issues of experimental design and data analysis in radiological ROC studies. , 1989, Investigative radiology.

[15]  Dev P Chakraborty,et al.  Validation and statistical power comparison of methods for analyzing free-response observer performance studies. , 2008, Academic radiology.

[16]  S. Astley,et al.  Single reading with computer-aided detection for screening mammography. , 2008, The New England journal of medicine.

[17]  David Gur,et al.  Prevalence effect in a laboratory environment. , 2003, Radiology.

[18]  E. Denton,et al.  Can radiographers read screening mammograms? , 2003, Clinical radiology.

[19]  Anabel M Scaranelo,et al.  Sensitivity of a Direct Computer-aided Detection System in Full-field Digital Mammography for Detection of Microcalcifications Not Associated with Mass or Architectural Distortion , 2010, Canadian Association of Radiologists journal = Journal l'Association canadienne des radiologistes.

[20]  D. Chakraborty,et al.  Free-response methodology: alternate analysis and a new observer-performance experiment. , 1990, Radiology.

[21]  Adrian M. K. Thomas,et al.  Reporting by radiographers: a policy and practice guide , 2004 .

[22]  A. Nowacki,et al.  Understanding Equivalence and Noninferiority Testing , 2011, Journal of General Internal Medicine.