Diagnostic Accuracy of Digital Screening Mammography With and Without Computer-Aided Detection | Breast Cancer | JAMA Internal Medicine | JAMA Network
[Skip to Navigation]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address Please contact the publisher to request reinstatement.
US Food and Drug Administration.  Summary of Safety and Effectiveness Data. R2 Technologies (P970058) 1998. P970058.http://www.fda.gov/ohrms/dockets/98fr/123098b.txt.
Fenton  JJ, Xing  G, Elmore  JG,  et al.  Short-term outcomes of screening mammography using computer-aided detection: a population-based study of Medicare enrollees.  Ann Intern Med. 2013;158(8):580-587.PubMedGoogle ScholarCrossref
Rao  VM, Levin  DC, Parker  L, Cavanaugh  B, Frangos  AJ, Sunshine  JH.  How widely is computer-aided detection used in screening and diagnostic mammography?  J Am Coll Radiol. 2010;7(10):802-805.PubMedGoogle ScholarCrossref
Gilbert  FJ, Astley  SM, McGee  MA,  et al.  Single reading with computer-aided detection and double reading of screening mammograms in the United Kingdom National Breast Screening Program.  Radiology. 2006;241(1):47-53.PubMedGoogle ScholarCrossref
Cole  EB, Zhang  Z, Marques  HS, Edward Hendrick  R, Yaffe  MJ, Pisano  ED.  Impact of computer-aided detection systems on radiologist accuracy with digital mammography.  AJR Am J Roentgenol. 2014;203(4):909-916.PubMedGoogle ScholarCrossref
Ciatto  S, Del Turco  MR, Risso  G,  et al.  Comparison of standard reading and computer aided detection (CAD) on a national proficiency test of screening mammography.  Eur J Radiol. 2003;45(2):135-138.PubMedGoogle ScholarCrossref
Taplin  SH, Rutter  CM, Lehman  CD.  Testing the effect of computer-assisted detection on interpretive performance in screening mammography.  AJR Am J Roentgenol. 2006;187(6):1475-1482.PubMedGoogle ScholarCrossref
Freer  TW, Ulissey  MJ.  Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center.  Radiology. 2001;220(3):781-786.PubMedGoogle ScholarCrossref
Birdwell  RL, Bandodkar  P, Ikeda  DM.  Computer-aided detection with screening mammography in a university hospital setting.  Radiology. 2005;236(2):451-457.PubMedGoogle ScholarCrossref
Ko  JM, Nicholas  MJ, Mendel  JB, Slanetz  PJ.  Prospective assessment of computer-aided detection in interpretation of screening mammography.  AJR Am J Roentgenol. 2006;187(6):1483-1491.PubMedGoogle ScholarCrossref
Morton  MJ, Whaley  DH, Brandt  KR, Amrami  KK.  Screening mammograms: interpretation with computer-aided detection—prospective evaluation.  Radiology. 2006;239(2):375-383.PubMedGoogle ScholarCrossref
Georgian-Smith  D, Moore  RH, Halpern  E,  et al.  Blinded comparison of computer-aided detection with human second reading in screening mammography.  AJR Am J Roentgenol. 2007;189(5):1135-1141.PubMedGoogle ScholarCrossref
Gur  D, Sumkin  JH, Rockette  HE,  et al.  Changes in breast cancer detection and mammography recall rates after the introduction of a computer-aided detection system.  J Natl Cancer Inst. 2004;96(3):185-190.PubMedGoogle ScholarCrossref
Cupples  TE, Cunningham  JE, Reynolds  JC.  Impact of computer-aided detection in a regional screening mammography program.  AJR Am J Roentgenol. 2005;185(4):944-950.PubMedGoogle ScholarCrossref
Romero  C, Varela  C, Muñoz  E, Almenar  A, Pinto  JM, Botella  M.  Impact on breast cancer diagnosis in a multidisciplinary unit after the incorporation of mammography digitalization and computer-aided detection systems.  AJR Am J Roentgenol. 2011;197(6):1492-1497.PubMedGoogle ScholarCrossref
Gromet  M.  Comparison of computer-aided detection to double reading of screening mammograms: review of 231,221 mammograms.  AJR Am J Roentgenol. 2008;190(4):854-859.PubMedGoogle ScholarCrossref
Gilbert  FJ, Astley  SM, Gillan  MG,  et al; CADET II Group.  Single reading with computer-aided detection for screening mammography.  N Engl J Med. 2008;359(16):1675-1684.PubMedGoogle ScholarCrossref
Fenton  JJ, Taplin  SH, Carney  PA,  et al.  Influence of computer-aided detection on performance of screening mammography.  N Engl J Med. 2007;356(14):1399-1409.PubMedGoogle ScholarCrossref
Fenton  JJ, Abraham  L, Taplin  SH,  et al; Breast Cancer Surveillance Consortium.  Effectiveness of computer-aided detection in community mammography practice.  J Natl Cancer Inst. 2011;103(15):1152-1161.PubMedGoogle ScholarCrossref
National Cancer Institute Breast Cancer Surveillance Consortium. http://breastscreening.cancer.gov/.
Yankaskas  BC, Taplin  SH, Ichikawa  L,  et al.  Association between mammography timing and measures of screening performance in the United States.  Radiology. 2005;234(2):363-373.PubMedGoogle ScholarCrossref
D’Orsi  CJ, Sickles  EA, Mendelson  EB,  et al.  ACR BI-RADS Atlas, Breast Imaging Reporting and Data System. Reston, VA: American College of Radiology; 2013.
Sickles  EA, D’Orsi  CJ, Bassett  LW,  et al. ACR BI-RADS Mammography. In:  ACR BI-RADS, Breast Imaging Reporting and Data System.5th ed. Reston, VA: American College of Radiology; 2013.
Sickles  EA, D’Orsi  CJ. ACR BI-RADS Follow-up and Outcome Monitoring. In:  ACR BI-RADS Atlas, Breast Imaging Reporting and Data System. Reston, VA: American College of Radiology; 2013.
Rutter  CM, Gatsonis  CA.  A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations.  Stat Med. 2001;20(19):2865-2884.PubMedGoogle ScholarCrossref
Pepe  MS, ed.  The Statistical Evaluation of Medical Tests for Classification and Prediction. New York, NY: Oxford University Press; 2003.
Elmore  JG, Carney  PA.  Computer-aided detection of breast cancer: has promise outstripped performance?  J Natl Cancer Inst. 2004;96(3):162-163.PubMedGoogle ScholarCrossref
Feig  SA, Sickles  EA, Evans  WP, Linver  MN.  Re: Changes in breast cancer detection and mammography recall rates after the introduction of a computer-aided detection system.  J Natl Cancer Inst. 2004;96(16):1260-1261.PubMedGoogle ScholarCrossref
Hall  FM.  Breast imaging and computer-aided detection.  N Engl J Med. 2007;356(14):1464-1466.PubMedGoogle ScholarCrossref
Feig  SA, Birdwell  RL, Linver  MN.  Computer-aided screening mammography.  N Engl J Med. 2007;357(1):84.PubMedGoogle Scholar
Gur  D.  Computer-aided screening mammography.  N Engl J Med. 2007;357(1):83-84.PubMedGoogle ScholarCrossref
Birdwell  RL.  The preponderance of evidence supports computer-aided detection for screening mammography.  Radiology. 2009;253(1):9-16.PubMedGoogle ScholarCrossref
Philpotts  LE.  Can computer-aided detection be detrimental to mammographic interpretation?  Radiology. 2009;253(1):17-22.PubMedGoogle ScholarCrossref
Berry  DA.  Computer-assisted detection and screening mammography: where’s the beef?  J Natl Cancer Inst. 2011;103(15):1139-1141.PubMedGoogle ScholarCrossref
Nishikawa  RM, Giger  ML, Jiang  Y, Metz  CE.  Re: effectiveness of computer-aided detection in community mammography practice.  J Natl Cancer Inst. 2012;104(1):77-78.PubMedGoogle ScholarCrossref
Levman  J.  Re: effectiveness of computer-aided detection in community mammography practice.  J Natl Cancer Inst. 2012;104(1):77-78.PubMedGoogle ScholarCrossref
Nishikawa  RM, Giger  ML, Doi  K, Vyborny  CJ, Schmidt  RA.  Computer-aided detection of clustered microcalcifications: an improved method for grouping detected signals.  Med Phys. 1993;20(6):1661-1666.PubMedGoogle ScholarCrossref
Jiang  Y, Nishikawa  RM, Schmidt  RA, Metz  CE, Giger  ML, Doi  K.  Improving breast cancer diagnosis with computer-aided diagnosis.  Acad Radiol. 1999;6(1):22-33.PubMedGoogle ScholarCrossref
Taylor  P, Potts  HW.  Computer aids and human second reading as interventions in screening mammography: two systematic reviews to compare effects on cancer detection and recall rate.  Eur J Cancer. 2008;44(6):798-807.PubMedGoogle ScholarCrossref
Gross  CP, Long  JB, Ross  JS,  et al.  The cost of breast cancer screening in the Medicare population.  JAMA Intern Med. 2013;173(3):220-226.PubMedGoogle ScholarCrossref
Nass  S, Ball  J, eds.  Improving Breast Imaging Quality Standards. Institute of Medicine and National Research Council of the National Academies. Washington, DC: The National Academies Press; 2005.
American Board of Internal Medicine Foundation. Choosing Wisely campaign. http://www.abimfoundation.org/Initiatives/Choosing-Wisely.aspx. Accessed September 1, 2015,
Original Investigation
Less Is More
November 2015

Diagnostic Accuracy of Digital Screening Mammography With and Without Computer-Aided Detection

Author Affiliations
  • 1Department of Radiology, Massachusetts General Hospital, Boston
  • 2Group Health Research Institute, Seattle, Washington
  • 3Departments of Medicine and Epidemiology and Biostatistics, University of California, San Francisco, San Francisco
  • 4Norris Cotton Cancer Center, Geisel School of Medicine at Dartmouth, Dartmouth College, Lebanon, New Hampshire
  • 5Department of Public Health Sciences, School of Medicine, University of California, Davis
JAMA Intern Med. 2015;175(11):1828-1837. doi:10.1001/jamainternmed.2015.5231

Importance  After the US Food and Drug Administration (FDA) approved computer-aided detection (CAD) for mammography in 1998, and the Centers for Medicare and Medicaid Services (CMS) provided increased payment in 2002, CAD technology disseminated rapidly. Despite sparse evidence that CAD improves accuracy of mammographic interpretations and costs over $400 million a year, CAD is currently used for most screening mammograms in the United States.

Objective  To measure performance of digital screening mammography with and without CAD in US community practice.

Design, Setting, and Participants  We compared the accuracy of digital screening mammography interpreted with (n = 495 818) vs without (n = 129 807) CAD from 2003 through 2009 in 323 973 women. Mammograms were interpreted by 271 radiologists from 66 facilities in the Breast Cancer Surveillance Consortium. Linkage with tumor registries identified 3159 breast cancers in 323 973 women within 1 year of the screening.

Main Outcomes and Measures  Mammography performance (sensitivity, specificity, and screen-detected and interval cancers per 1000 women) was modeled using logistic regression with radiologist-specific random effects to account for correlation among examinations interpreted by the same radiologist, adjusting for patient age, race/ethnicity, time since prior mammogram, examination year, and registry. Conditional logistic regression was used to compare performance among 107 radiologists who interpreted mammograms both with and without CAD.

Results  Screening performance was not improved with CAD on any metric assessed. Mammography sensitivity was 85.3% (95% CI, 83.6%-86.9%) with and 87.3% (95% CI, 84.5%-89.7%) without CAD. Specificity was 91.6% (95% CI, 91.0%-92.2%) with and 91.4% (95% CI, 90.6%-92.0%) without CAD. There was no difference in cancer detection rate (4.1 in 1000 women screened with and without CAD). Computer-aided detection did not improve intraradiologist performance. Sensitivity was significantly decreased for mammograms interpreted with vs without CAD in the subset of radiologists who interpreted both with and without CAD (odds ratio, 0.53; 95% CI, 0.29-0.97).

Conclusions and Relevance  Computer-aided detection does not improve diagnostic accuracy of mammography. These results suggest that insurers pay more for CAD with no established benefit to women.