Changes in breast cancer detection and mammography recall rates after the introduction of a computer-aided detection system.

BACKGROUND Computer-aided mammography is rapidly gaining clinical acceptance, but few data demonstrate its actual benefit in the clinical environment. We assessed changes in mammography recall and cancer detection rates after the introduction of a computer-aided detection system into a clinical radiology practice in an academic setting. METHODS We used verified practice- and outcome-related databases to compute recall rates and cancer detection rates for 24 Mammography Quality Standards Act-certified academic radiologists in our practice who interpreted 115,571 screening mammograms with (n = 59,139) or without (n = 56,432) the use of a computer-aided detection system. All statistical tests were two-sided. RESULTS For the entire group of 24 radiologists, recall rates were similar for mammograms interpreted without and with computer-aided detection (11.39% versus 11.40%; percent difference = 0.09, 95% confidence interval [CI] = -11 to 11; P =.96) as were the breast cancer detection rates for mammograms interpreted without and with computer-aided detection (3.49% versus 3.55% per 1000 screening examinations; percent difference = 1.7, 95% CI = -11 to 19; P =.68). For the seven high-volume radiologists (i.e., those who interpreted more than 8000 screening mammograms each over a 3-year period), the recall rates were similar for mammograms interpreted without and with computer-aided detection (11.62% versus 11.05%; percent difference = -4.9, 95% CI = -21 to 4; P =.16), as were the breast cancer detection rates for mammograms interpreted without and with computer-aided detection (3.61% versus 3.49% per 1000 screening examinations; percent difference = -3.2, 95% CI = -15 to 9; P =.54). CONCLUSION The introduction of computer-aided detection into this practice was not associated with statistically significant changes in recall and breast cancer detection rates, both for the entire group of radiologists and for the subset of radiologists who interpreted high volumes of mammograms.

[1]  Computer-Aided Detection of Breast Cancer: Has Promise Outstripped Performance? , 2004 .

[2]  P. Tan,et al.  Results of intermediate measures from a population‐based, randomized trial of mammographic screening prevalence and detection of breast carcinoma among asian women , 1998 .

[3]  D. Wolverton,et al.  Performance parameters for screening and diagnostic mammography: specialist and general radiologists. , 2002, Radiology.

[4]  R. Hendrick,et al.  Technical quality control practices in mammography screening programs in 22 countries. , 2002, International journal for quality in health care : journal of the International Society for Quality in Health Care.

[5]  L. Liberman,et al.  Breast imaging reporting and data system (BI-RADS). , 2002, Radiologic clinics of North America.

[6]  J. Elmore,et al.  Variability in radiologists' interpretations of mammograms. , 1994, The New England journal of medicine.

[7]  Emily F Conant,et al.  Association of volume and volume-independent factors with accuracy in screening mammogram interpretation. , 2003, Journal of the National Cancer Institute.

[8]  R. Brem,et al.  Radiologist detection of microcalcifications with and without computer-aided detection: a comparative study. , 2001, Clinical radiology.

[9]  Michael J Schell,et al.  Recall and detection rates in screening mammography , 2004, Cancer.

[10]  T. Freer,et al.  Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center. , 2001, Radiology.

[11]  Robert M. Nishikawa,et al.  Computer aided diagnosis of breast cancer on mammograms , 1997, Breast cancer.

[12]  L. Tabár,et al.  The natural history of breast carcinoma , 1999, Cancer.

[13]  S. Woolf,et al.  Breast Cancer Screening: A Summary of the Evidence for the U.S. Preventive Services Task Force , 2002, Annals of Internal Medicine.

[14]  E A Sickles,et al.  Initial versus subsequent screening mammography: comparison of findings and their prognostic significance. , 1995, AJR. American journal of roentgenology.

[15]  S. Zeger,et al.  Longitudinal data analysis using generalized linear models , 1986 .

[16]  S. Fields,et al.  Improved mammographic interpretation of masses using computer-aided diagnosis , 2000, European Radiology.

[17]  P. Tan,et al.  Results of intermediate measures of a population‐based, randomized trial of mammographic screening prevalence and detection of breast carcinoma among Asian women: the Singapore Breast Screening Project , 1998, Cancer.

[18]  M J Schell,et al.  Association of recall rates with sensitivity and positive predictive values of screening mammography. , 2001, AJR. American journal of roentgenology.

[19]  Helen Brown,et al.  Applied Mixed Models in Medicine , 2000, Technometrics.

[20]  K. Doi,et al.  Potential of computer-aided diagnosis to reduce variability in radiologists' interpretations of mammograms depicting microcalcifications. , 2001, Radiology.

[21]  Martin P DeSimio,et al.  Determining efficacy of mammographic CAD systems. , 2002, Journal of digital imaging.

[22]  L. Tabár,et al.  Potential contribution of computer-aided detection to the sensitivity of screening mammography. , 2000, Radiology.

[23]  N. Petrick,et al.  Improvement of radiologists' characterization of mammographic masses by using computer-aided diagnosis: an ROC study. , 1999, Radiology.

[24]  R. F. Wagner,et al.  Assessment of medical imaging and computer-assist systems: lessons from recent experience. , 2002, Academic radiology.