Download PDF
Radiologie up2date 2012; 12(1): 55-72
DOI: 10.1055/s-0030-1257160
Brustbildgebung/Mammografie

© Georg Thieme Verlag KG Stuttgart · New York

CAD in der Mammadiagnostik: Einsatz bei Mammografie und MRT

CAD in breast imaging: application in mammography and MR mammographyS.  Obenauer, K.-P.  Hermann
Further Information

Publication History

Publication Date:
17 March 2012 (online)

Also available at
    Permissions and Reprints All articles of this category

Zusammenfassung

In vielen Bereichen der diagnostischen Radiologie wird zunehmend der Einsatz von computerassistierten Diagnosesystemen (CAD-Systemen) geprüft. In der Mammografie ist dies von besonderem Interesse, da eine Zweitbefundung zeit- und kostenintensiv ist. Aufgrund der hohen Rate an falsch positiven Befunden ist jedoch derzeit der routinemäßige Einsatz der CAD-Systeme noch nicht in den klinischen Alltag eingezogen, sodass das Double Reading auch nicht durch einen Computer aktuell zu ersetzen ist. Es bleibt abzuwarten, ob die Technik in der Zukunft hier Verbesserungen bringt.

Abstract

Computer aided diagnosis systems (CAD-systems) are evaluated in different parts of diagnostic imaging. In breast imaging double reading which is time- and cost spending is necessary. Therefore a lot of studies evaluated the use of CAD-systems in mammography. However the rate of false-positives is too high to implement CAD-systems as double reader in routine work. In the future, improvements in this technique could perhaps change the performance of CAD-systems.

Key words

Computer aided diagnosis systems - diagnostic imaging - mammography

Kernaussagen

  • Zur Qualitätssicherung der mammografischen Befundauswertung schreiben die Richtlinien der European Society of Mastology (EUSOMA) eine Doppelbefundung vor, wodurch die Sensitivität um ca. 15 % gesteigert werden kann.

  • Eine mögliche Alternative zur ärztlichen Zweitbefundung könnten CAD-Systeme darstellen.

  • Neben einer hohen Sensitivität besitzen die CAD-Systeme aber eine geringe Spezifität bei hoher Anzahl an falsch positiven Markierungen. Hier bleibt abzuwarten, ob in der Zukunft eine technische Verbesserung erzielt werden kann.

  • In der MR-Mammografie soll der Radiologe durch die CAD-Systeme bei der Einordnung von Befunden in Benignität oder Malignität unterstützt werden. Auch sollen die Systeme die Kurvenanalyse automatisch in Form einer farbcodierten Analyse erledigen.

  • Damit soll wiederum die Anzahl der falsch positiven Markierungen reduziert und die Zeit für die Interpretation der MR-Mammografie verkürzt werden.

  • Aber auch hier bleibt der Radiologe und seine Erfahrung weiterhin das entscheidende Kriterium.

Literatur

  • 1 Blendl C, Hermann K-P, Mertelmeier T. Anwendungen und Prüfverfahren für digitale Mammografie-Einrichtungen.. Berlin: Beuth Verlag GmbH; 2005
    Google Scholar
  • 2 Eadie L H, Taylor P, Gibson A P. A systematic review of computer-assisted diagnosis in diagnostic cancer imaging.  Eur J Radiol. 2012;  81 e70-76
    Google Scholar
  • 3 Jiang Y, Nishikawara R M, Schmidt R A et al. Potential of computer-aided diagnosis to reduce variability in radiologists’ interpretations of mammograms depicting microcalcifications.  Radiology. 2011;  220 787-794
    Google Scholar
  • 4 Malich A, Marx C, Facius M et al. Tumor detection rate of a new commercially available computer-aided detection system.  Eur Radiol. 2001;  11 2454-2459
    Google Scholar
  • 5 Sittek H, Perlet C, Helmberger R et al. Computerassistierte Analyse von Mammografien in der klinischen Routinediagnostik.  Radiologe. 1998;  38 848-852
    Google Scholar
  • 6 Vyborny C J, Doi T, O’Shaughnessy K et al. Breast cancer: importance of spiculation in computer-aided detection.  Radiology. 2000;  215 703-707
    Google Scholar
  • 7 Kegelmeyer W P, Prudeda J M, Bourland P D et al. Computer-aided mammographic screening for spiculated lesions.  Radiology. 1994;  191 331-337
    Google Scholar
  • 8 Lehman C D, Peacock S, DeMartini W B, Chen X. A new automated software system to evaluate breast MR examinations: improved specificity without decreased sensitivity.  Am J Roentgenol. 2006;  187 51-56
    Google Scholar
  • 9 Williams T C, DeMartini W B, Partridge S C et al. Breast MR imaging: computer-aided evaluation program for discriminating benign from malignant lesions.  Radiology. 2007;  244 94-103
    Google Scholar
  • 10 Blieheuvel C, Weigel S, Heindel W. Mammography Screening: Evidence, History and Current Practice in Germany and Other European Countries.  Breast Care (Basel). 2011;  6 104-109
    Google Scholar
  • 11 Diekmann S, Diekmann F. Mammography screening in Germany.  Radiologe. 2008;  1 17-25
    Google Scholar
  • 12 Shapiro S, Strax P, Venet L. Periodic breast cancer screening in reducing mortality from breast cancer.  JAMA. 1971;  215 1777-1785
    Google Scholar
  • 13 Tabar L, Fagerberg C J, Gad A et al. Reduction in mortality from breast cancer after mass screening with mammography.  Lancet. 1985;  2 829-832
    Google Scholar
  • 14 Thurfjell E L, Lernevall K A, Taube A A. Benefit of independent double reading in a population-based mammography screening program.  Radiology. 1994;  1 241-244
    Google Scholar
  • 15 Funovics M, Schamp S, Helbich T H et al. Evaluation of a computer-assisted diagnosis system in breast carcinoma.  Fortschr Röntgenstr. 2001;  3 218-223
    Google Scholar
  • 16 Brem R F, Baum J, Lechner M et al. Improvement in sensitivity of screening mammography with computer-aided detection: a multiinstitutional trial.  Am J Roentgenol. 2003;  181 687-693
    Google Scholar
  • 17 Bandodkar P, Birdwell R L, Ikeda D M. Computer aided detection (CAD) with screening mammography in an academic institution: preliminary findings.  Radiology. 2002;  225 458
    Google Scholar
  • 18 Malich A, Sauner D, Marx C et al. Influence of breast lesion size and histologic findings on tumor detection. Rate of a computer-aided detection system.  Radiology. 2003;  228 851-856
    Google Scholar
  • 19 Morton M J, Whaley D H, Brandt K R, Amrami K K. Screening mammograms: interpretation with computer-aided detection – prospective evaluation.  Radiology. 2006;  239 375-383
    Google Scholar
  • 20 Obenauer S, Sohns C, Werner C, Grabbe E. Retrospective analysis of a computer-aided detection (CAD) system in full-field digital mammography in correlation to tumor histology.  Fortschr Röntgenstr. 2005;  177 1103-1109
    Google Scholar
  • 21 Obenauer S, Sohns C, Werner C, Grabbe E. Impact of breast density on computer-aided detection in full-field digital mammography.  J Dig Imaging. 2006;  19 258-263
    Google Scholar
  • 22 Winsberg F, Elkin M, Macy J et al. Detection of radiographic abnormalities in mammograms by means of optical scanning an computer analysis.  Radiology. 1967;  89 211-215
    Google Scholar
  • 23 Bick U. Computerassistierte Diagnose in der Screening Mammografie.  Radiologe. 1996;  36 72-80
    Google Scholar
  • 24 Giger M L. Update on the potential of computer-aided diagnosis for breast cancer.  Future Oncol. 2010;  6 1-4
    Google Scholar
  • 25 Jiang Y. Malignant and benign clustered microcalzifications: Automated feature analysis and classification.  Radiology. 1996;  198 671-678
    Google Scholar
  • 26 Freer T W, Ulissey M J. Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center.  Radiology. 2001;  3 781-786
    Google Scholar
  • 27 Cupples T E, Cunningham J E, Reynolds J C. Impact of computer-aided detection (CAD) in a regional screening mammography program.  Am J Roentgenol. 2005;  185 944-950
    Google Scholar
  • 28 Quek S T, Thng C H, Khoo J B, Koh W L. Radiologists detection of mammographic abnormalities with and without a computer-aided detection system.  Australas Radiol. 2003;  3 257-260
    Google Scholar
  • 29 Chan H P, Doi K, Vyborny C J et al. Improvement in radiologists detection of clustered microcalcifications on mammograms. The potential of computer-aided diagnosis.  Invest Radiol. 1990;  10 1102-1110
    Google Scholar
  • 30 Birdwell R L, Ikeda D M, Shoughnessy K F et al. Mammographic characteristics of 115 missed cancers later detected with screening mammography and potential utility of computer-aided detection.  Radiology. 2001;  219 192-202
    Google Scholar
  • 31 Yang S K, Moon W K, Cho N et al. Screening mammography detected cancers: sensitivity of a computer-aided detection system applied to full-field digital mammograms.  Radiology. 2007;  244 104-111
    Google Scholar
  • 32 Dean J C, Ilvento C C. Improved cancer detection using computer-aided detection with diagnostic and screening mammography: prospective study of 104 cancers.  Am J Roentgenol. 2006;  187 20-28
    Google Scholar
  • 33 Ko J M, Nickolas M J, Mendel J B. Prospective assessment of computer-aided detection in interpretation of screening mammography.  Am J Roentgenol. 2006;  187 1483-1491
    Google Scholar
  • 34 Kim S J, Moon W K, Kim S-Y et al. Comparison of two software versions of a commercially available computer-aided detection (CAD) system for detecting breast cancer.  Acta Radiologica. 2010;  5 482-490
    Google Scholar
  • 35 Fenton J J, Abraham L, Taplin S H et al. Effectiveness of computer-aided detection in community mammography practice.  J Natl Cancer Inst. 2011;  103 1152-1161
    Google Scholar
  • 36 Bolivar A V, Gomez S S, Merino S P et al. Computer-aided detection system applied to full-field digital mammograms.  Acta Radiologica. 2010;  10 1086-1091
    Google Scholar
  • 37 Ciatto S, Ambrogetti D, Bonardi R et al. Comparison of two commercial systems for computer-assisted detection (CAD) as an aid to interpreting screening mammograms.  Radiol Med. 2004;  107 480-488
    Google Scholar
  • 38 Baines C J, Miller A B, Wall C et al. Sensitivity and specificity of first screen mammography in the Canadian national breast screen study: A preliminary report from five centers.  Radiology. 1986;  160 295-298
    Google Scholar
  • 39 Bird R E, Wallace T W, Yankaskas B C. Analysis of cancers missed at screening mammography.  Radiology. 1992;  3 613-617
    Google Scholar
  • 40 Karssemeijer N, Otten J D, Verbeek A L et al. Computer-aided detection versus independent double reading of masses in mammograms.  Radiology. 2003;  227 192-200
    Google Scholar
  • 41 Singh S, Maxwell J, Baker J A et al. Computer-aided classification of breast masses: performance and interobserver variability of expert radiologists versus residents.  Radiology. 2011;  258 73-80
    Google Scholar
  • 42 James J J, Gilbert F J, Wallis M G et al. Mammographic features of breast cancers at single reading with computer-aided detection and at double reading in a large multicenter prospective trial of computer-aided detection: CADET II.  Radiology. 2010;  256 379-386
    Google Scholar
  • 43 Guerriero C, Gillan M GC, Cairns J et al. Is computer aided detection (CAD) cost effective in screening mammography? A model based on the CADET II study.  BMC Health Services Research. 2011;  11 11
    Google Scholar
  • 44 Elter M, Schulz-Wendtland R, Wittenberg T. The prediction of breast cancer biopsy outcomes using two CAD approaches that both emphasize an intelligible decision process.  Med Phys. 2007;  23 4164-4172
    Google Scholar
  • 45 Bluemke D A, Gatsonis C A, Chen M H et al. Magnetic resonance imaging of the breast prior to biopsy.  JAMA. 2004;  292 2735-2742
    Google Scholar
  • 46 Lee C H. Problem solving MR imaging of the breast.  Radiol Clin North Am. 2004;  42 919-934
    Google Scholar
  • 47 Peters N H, Borel Rinkes I H, Zuithoff N P et al. Meta-analysis of MR imaging in the diagnosis of breast lesions.  Radiology. 2008;  246 116-124
    Google Scholar
  • 48 Kuhl C K, Schmutzler R K, Leutner C C et al. Breast MR imaging screening in 192 women proved or suspected to be carriers of a breast cancer susceptibility gene: preliminary results.  Radiology. 2000;  215 267-279
    Google Scholar
  • 49 Moy L, Elias K, Patel V et al. Is breast MRI helpful in the evaluation of inconclusive mammographic findings?.  Am J Roentgenol. 2009;  193 986-993
    Google Scholar
  • 50 Vassiou K, Kanavou T, Vlychou M et al. Characterization of breast lesions with CE-MR multimodal morphological and kinetic analysis: comparison with conventional mammography and high-resolution ultrasound.  Eur J Radiol. 2009;  70 69-76
    Google Scholar
  • 51 Hrung J M, Sonnad S S, Schwartz J S, Langlotz C P. Accuracy of MR imaging in the work-up of suspicious breast lesions: a diagnostic meta-analysis.  Acad Radiol. 1999;  6 387-397
    Google Scholar
  • 52 Wood C. Computer Aided Detection (CAD) for breast MRI.  Technol Cancer Res Treat. 2005;  4 49-53
    Google Scholar
  • 53 Dorrius M D, Jansen-van der Weide M C, van Ooijen P MA et al. Computer-aided detection in breast MRI: a systematic review and meta-analysis.  Eur Radiol. 2011;  21 1600-1608
    Google Scholar
  • 54 Renz D M, Baltzer P A, Kullnig P E et al. Clinical value of computer-assisted analysis in MR mammography. A comparison between two systems and three observers with different levels of experience.  Fortschr Röntgenstr. 2008;  180 968-976
    Google Scholar
  • 55 Meyer-Baese A, Schlossbauer T, Lange O, Wismueller A. Small lesions evaluation based on unsupervised cluster analysis of signal-intensity time courses in dynamic breast MRI.  Int J Biomed Imaging. 2009;  Article ID 326 924
    Google Scholar
  • 56 Baltzer P A, Renz D M, Kullnig P E et al. Application of computer-aided diagnosis (CAD) in MR-mammography (MRM): do we really need whole lesion time curve distribution analysis?.  Acad Radiol. 2009;  16 435-442
    Google Scholar
  • 57 Baltzer P A, Freiberg C, Beger S et al. Clinical MR-mammography: are computer-assisted methods superior to visual or manual measurements for curve type analysis? A systematic approach.  Acad Radiol. 2009;  16 1070-1076
    Google Scholar
  • 58 Baltzer P A, Dietzel M, Vag T et al. Can Color-Coded Parametric Maps Improve Dynamic Enhancement Pattern Analysis in MR Mammography?.  Fortschr Röntgenstr. 2010;  182 254-260
    Google Scholar
  • 59 Kurz K D, Steinhaus D, Klar V et al. Assessment of three different software systems in the evaluation of dynamic MRI of the breast.  Eur J Radiol. 2009;  69 300-307
    Google Scholar
  • 60 Cho N, Kim S M, Park J S et al. Contralateral lesions detected by preoperative MRI in patients with recently diagnosed breast cancer: application of MR CAD in differentiation of benign and malignant lesions.  Eur J Radiol. 2011;  DOI: 10.1016/j.ejrad.2011.03.060
    Google Scholar
  • 61 Arazi-Kleinman T, Causer P A, Jong R A et al. Can breast MRI computer-aided detection (CAD) improve radiologist accuracy for lesions detected at MRI screening and recommended for biopsy in a high-risk population?.  Clin Radiol. 2009;  64 1166-1174
    Google Scholar
  • 62 Hauth E A, Jaeger H, Maderwald S et al. Quantitative parametric analysis of contrast enhanced lesions in dynamic MR mammography.  Radiologe. 2008;  48 593-600
    Google Scholar
  • 63 Kelcz F, Furman-Haran E, Grobgeld D, Degani H. Clinical testing of high-spatial-resolution parametric contrast enhanced MR imaging of the breast.  Am J Roentgenol. 2002;  179 1485-1492
    Google Scholar
  • 64 Meeuwis C, van de Ven S M, Stapper G et al. Computer aided detection (CAD) for breast MRI: evaluation of efficacy at 3.0 T.  Eur Radiol. 2009;  20 522-528
    Google Scholar
  • 65 Veltman J, Mann R M, Meijer F J et al. The additional value of three time point color coding in dynamic contrast-enhanced MRI of the breast for inexperienced and experienced readers.  Eur J Radiol. 2010;  74 514-518
    Google Scholar

Prof. Dr. Silvia Obenauer

Leiterin Bereich Frauenklinik
Heinrich-Heine-Universität Düsseldorf Medizinische Fakultät
Institut für Diagnostische und Interventionelle Radiologie

Moorenstraße 5
40225 Düsseldorf

Phone: 0211 811-6466

Fax: 0211 811-7522

Email: silvia.obenauer@med.uni-duesseldorf.de

      >