Four separate studies conducted as blinded retrospective radiologist reviews of screening mammograms where cancer subsequently developed found lesions requiring work-up or biopsy in 25% to 41% of cases. Three non-blinded retrospective reviews by radiologists identified 57% to 75% of cancers. Among breast cancers detected by radiologists on blinded retrospective review in one study, computer aided detection (CAD) would have found 77%. These studies suggest that improved cancer detection rates could result if radiologists who interpret screening mammography were aided by computers.
One prospective study initiated on that premise found that CAD increased the screening detection rate by 19.5%. At the current state-of-the-art, CAD performs best for cancers presenting as calcifications, less well for cancers appearing as spiculated masses, and least well for cancers appearing as circumscribed masses. CAD does not seem to increase false positive call back rates for additional imaging work-up or to increase false positive biopsy rates.
References
1.
TabarL., VitakB., ChenH.-H., YenM.-F., DuffyS. W., SmithR. A.Beyond randomized trials: Organized mammographic screening substantially reduces breast cancer mortality. Cancer. 91, 1724–1731 (2000).
2.
FeigS. A.Screening Mammography: Effect of Image Quality On Clinical Outcome. AJR Am J Roentgenol.178, 805–807 (2002).
3.
HendrickR. E.Quality assurance in mammography: Accreditation, legislation, and compliance with quality assurance standards. Radiol Clin North Am.30, 243–256 (1992).
4.
BassettL. W., FarriaD. M., BansalS., FarquharM. A., WilcoxP. A., FeigS. A.Reasons for failure of a mammography unit at clinical image review in the American College of Radiology Mammography Accreditation Program. Radiology.215, 698–702 (2000).
5.
MonseesB. S.The Mammography Quality Standards Act: An overview of regulations and guidance. Radiol Clin North Am.38, 759–772 (2000).
6.
BirdwellR. L., IkedaD. M., O'ShaughnessyK. F., SicklesE. A.Mammographic characteristics of 115 missed carcinomas later detected with screening mammography and the potential utility of computer-aided detection. Radiology. 219, 192–202 (2000).
7.
HarveyJ. A., FajardoL. L., InnisC. A.Previous mammograms in patients with impalpable carcinoma: Retrospective vs blinded interpretation. AJR Am J Roentgenol.161, 1167–1172 (1993).
8.
MobergK., GrundstromH., TornbergS., LundquistH., SvaneG., HavervallL., MurenC.Two models for radiological reviewing of interval cancers. J Med Screen.6, 35–39 (1999).
9.
Van DijckJ., VerbeekA., HendriksJ., HollandR.The current detectability of breast cancer in a mammographic screening program: A review of the previous mammograms of interval and screen-detected cancers. Cancer.72, 1933–1938 (1993).
10.
YankaskasB. C., SchellM. J., BirdR. E., DesrochersD. A.Reassessment of breast cancers missed during routine screening mammography: A community-based study. AJR Am J Roentgenol.177, 535–541 (2001).
11.
VitakB.Invasive interval cancers in the Ostergotland Mammographic Programme: Radiological analysis. Eur Radiol.8, 639–646 (1998).
12.
Warren-BurhenneL. J., WoodS. A., D'OrsiC. J., FeigS. A., KopansD. B., O'ShaughnessyK. F., SicklesE. A., TabarL., VybornyC. J., CastellinoR. A.Potential contribution of computer-aided detection to the sensitivity of screening mammography. Radiology.215, 554–562 (2000).
13.
ThurfjellE., Gelig-ThurfjellM., EggeE., BjurstamN.Sensitivity and specificity of computer-assisted breast cancer detection in mammography screening. Acta Radiologica.39, 384–388 (1998).
14.
FreerT. W., UlisseyM. J.Screening mammography with computer-aided detection: Prospective study of 12, 860 patients in a community breast center. Radiology.220, 781–786 (2001).
15.
NakaharaH., NambaK., FukamiA., WatanabeR., MitsuhiroM., MatsuT., NishimuraS., JinnouchiS., NagamachiS., OhnishiT., FutamiS., FloresL. G.II, NakaharaM., TamuraS.Computer-aided diagnosis (CAD) for mammography: Preliminary results. Breast Cancer (The Journal of the Japanese Breast Cancer Society). 5, 401–405 (1998).
16.
te BrakeG. M., KarssemeijerN., HendriksJ. H. C. L.Automated detection of breast carcinomas not detected in a screening program. Radiology.207, 465–571 (1998).
17.
VybornyC. J., DoiT., O'ShaughnessyK. F., RomsdahlH. M., SchneiderA. C., SteinA. A.Breast cancer: Importance of spiculation in computer-aided detection. Radiology.215, 703–707 (2000).
18.
D'OrsiC. J., BassettL. W., FeigS. A., JacksonV. P., KopansD. B., LinverM., SicklesE. A., StellingC. B.Illustrated Breast Imaging Reporting and Data System (BI-RADS™). Third Edition. American College of Radiology. Reston VA. (1998).
19.
HuntK. A., RosenE. L., SicklesE. A.Outcome analysis for women undergoing annual versus biennial screening mammography: A review of 24, 211 examinations. AJR Am J Roentgenol.173, 285–289 (1998).
20.
YankaskasB. C., ClevelandR. J., SchellM. J., KozarR.Association of recall rates with sensitivity and positive predictive values of screening mammography. AJR Am J Roentgenol.177, 543–549 (2000).
21.
SicklesE. A.Management of probably benign lesions. Radiol Clin North Am.33, 1123–1130 (1995).
