Abstract
Background Recent evidence suggests that computer-aided detection (CAD) may have a negative impact on the interpretation of mammography—this necessitates timely evaluation of CAD in practice. We report a retrospective study of the incremental effect of CAD on the accuracy of full-field digital mammography (DM) as applied prospectively in breast assessment. Methods: Subjects were all consecutive women attending a self-referral breast centre in Florence between September 2005 and January 2007 (N = 3,425). DM was reported without, then with, CAD according to a standard protocol; all mammograms recalled on the basis of either the radiologist’s reading alone, or the radiologist’s reading after viewing CAD, were recalled to assessment. Results Overall recall rate (RR) was 13.1% and 107 cancers were diagnosed (90 invasive cancers, 8 DCIS, 9 malignant on cytology). The use of CAD allowed the additional detection of 5 cancers (three invasive cancers, one DCIS, one malignant on cytology) and caused one additional benign surgical biopsy, with a relative RR of 4.9%, and an incremental RR of 1.17%. The cancer detection rate (CDR) of DM interpreted with the use of CAD was 3.12% and did not significantly differ from the CDR of 2.9% based on DM without CAD (χ2 = 3.2, P = 0.07). Conclusion While the increase in CDR with the use of CAD only approached statistical significance, representing modest gains in absolute terms, the incremental number of cancers detected justifies the incremental recall and benign surgical biopsy attributable to CAD use. In our clinical setting, these data suggest more benefit than harm in using CAD with DM, and we will continue the use of CAD with ongoing monitoring of patient outcomes.
Similar content being viewed by others
References
Fenton JJ, Taplin SH, Carney PA et al (2007) Influence of computer-aided detection on performance of screening mammography. N Engl J Med 356:1399–1409
Houssami N, Given-Wilson R (2007) Incorporating new technologies into clinical practice without evidence of effectiveness in prospective studies: computer-aided detection (CAD) in breast screening reinforces the need for better initial evaluation. Breast 16:219–221
Taylor P, Given-Wilson RM (2005) Evaluation of computer-aided detection (CAD) devices. Br J Radiol 78S1:S26–S30
Brem RF, Baum J, Lechner M et al (2003) Improvement in sensitivity of screening mammography with computer-aided detection: a multi-institutional trial. AJR Am J Roentgenol 181:687–693
Warren Burhenne LJ, Wood SA, D’Orsi CJ et al (2000) Potential contribution of computer aided detection to the sensitivity of screening mammography. Radiology 215:554–562
Ciatto S, Rosselli Del Turco M, Risso G et al (2003) Comparison of standard reading and computer aided diagnosis (CAD) on a national proficiency test of screening mammography. Eur J Radiol 45:135–138
Houssami N, Irwig L (1998) Likelihood ratios for clinical examination, mammography, ultrasound and fine needle biopsy in women with breast problems. Breast 7:85–89
Bulgaresi P, Cariaggi P, Ciatto S, Houssami N (2006) Positive predictive value of breast fine needle aspiration cytology (FNAC) in combination with clinical and imaging findings: a series of 2,334 subjects with abnormal cytology. Breast Cancer Res Treat 97:319–321
Khoo LA, Taylor P, Given-Wilson RM (2005) Computer-aided detection in the United Kingdom National Breast Screening Programme: prospective study. Radiology 237:444–449
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Brancato, B., Houssami, N., Francesca, D. et al. Does computer-aided detection (CAD) contribute to the performance of digital mammography in a self-referred population?. Breast Cancer Res Treat 111, 373–376 (2008). https://doi.org/10.1007/s10549-007-9786-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10549-007-9786-2