La radiologia medica

, Volume 116, Issue 7, pp 1039–1049 | Cite as

Size assessment of breast lesions by means of a computer-aided detection (CAD) system for magnetic resonance mammography

  • G. Levrini
  • R. SghedoniEmail author
  • C. Mori
  • A. Botti
  • R. Vacondio
  • A. Nitrosi
  • M. Iori
  • F. Nicoli
Breast Radiology / Senologia



The aim of this study was to investigate the efficacy of a dedicated software tool for automated volume measurement of breast lesions in contrast-enhanced (CE) magnetic resonance mammography (MRM).

Material and methods

The size of 52 breast lesions with a known histopathological diagnosis (three benign, 49 malignant) was automatically evaluated using different techniques. The volume of all lesions was measured automatically (AVM) from CE 3D MRM examinations by means of a computer-aided detection (CAD) system and compared with the size estimates based on maximum diameter measurement (MDM) on MRM, ultrasonography (US), mammography and histopathology.


Compared with histopathology as the reference method, AVM understimated lesion size by 4% on average. This result was similar to MDM (3% understimation, not significantly different) but significantly better than US and mammographic lesion measurements (24% and 33% size underestimation, respectively).


AVM is as accurate as MDM but faster. Both methods are more accurate for size assessment of breast lesions compared with US and mammography.


Magnetic resonance mammography CAD Dynamic contrast enhancement 

Valutazione della dimensione di lesioni mammarie con un sistema di CAD per risonanza magnetica mammografica



Scopo di questo studio è stato studiare le prestazioni di un software dedicato per la misura automatica del volume di lesioni identificate dalla risonanza magnetica della mammella (MRM) con utilizzo di mezzo di contrasto paramagnetico (CE).

Materiali e metodi

Le dimensioni di 52 lesioni mammarie con diagnosi istopatologica nota (3 benigne, 49 maligne) sono state valutate automaticamente tramite diverse tecniche. Le dimensioni delle lesioni sono state stimate automaticamente (AVM) da esami CE 3D MRM, utilizzando un sistema di computed aided diagnosis (CAD) e confrontate con stime delle dimensioni basate sulla misura del diametro massimo (MDM) in MRM, ecografia, mammografia ed anatomia patologica.


Confrontata con il reperto istopatologico come metodo di riferimento, AVM ha sottostimato la dimensione della lesione del 4% in media. Questo risultato è analogo a MDM (sottostima del 3%, differenza non significativa), ma significativamente migliore della misura della lesione ottenuta dallo studio ecografico o mammografico (sottostima del 24% e del 33% rispettivamente).


La valutazione dimensionale ottenuta con AVM è accurata tanto quanto MDM, ma più veloce. Entrambi i metodi ottengono nella stima della dimensione per lesioni alla mammella valori più vicini allo standard costituito dalla misura su pezzo operatorio rispetto ad ecografia e mammografia.

Parole chiave

Risonanza magnetica mammografica CAD Mezzo di contrasto paramagnetico 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kuhl C (2007) The current status of breast MR imaging. Part I. Choice of technique, image interpretation, diagnostic accuracy, and transfer to clinical practice. Radiology 244:356–378PubMedCrossRefGoogle Scholar
  2. 2.
    Kuhl C (2007) The current status of breast MR imaging. Part II. Clinical applications. Radiology 244:672–691PubMedCrossRefGoogle Scholar
  3. 3.
    Guidi AJ, Fischer L, Harris JR et al (1994) Microvesseldensity and distribution in ductal carcinoma in situ of the breast. J Natl Cancer Inst 86:614–619PubMedCrossRefGoogle Scholar
  4. 4.
    Oshida K, Nagashima T, Ueda T et al (2005) Pharmacokinetic analysis of ductal carcinoma in situ of the breast using dynamic MR mammography. Eur Radiol 15:1353–1360PubMedCrossRefGoogle Scholar
  5. 5.
    Gilles R, Zafrani B, Guinebretiere J-M et al (1995) Ductal carcinoma in situ: MR imaging-histopathological correlation. Radiology 196:415–419PubMedGoogle Scholar
  6. 6.
    Lehman CD, Peacock S, DeMartini WB, Chen X (2006) A new automated software system to evaluate breast MR examinations: improved specificity without decrease sensitivity. AJR Am J Roentgenol 187:51–56PubMedCrossRefGoogle Scholar
  7. 7.
    Belli P, Costantini M, Malaspina C et al (2006) MRI accuracy in residual disease evaluation in breast cancer patients treated with neoadjuvant chemotherapy. Clin Radiol 61:946–953PubMedCrossRefGoogle Scholar
  8. 8.
    Partridge SC, Gibbs JE, Lu Y et al (2002) Accuracy of MR imaging for revealing residual breast cancer in patients who have undergone neoadjuvant chemotherapy. AJR Am J Roentgenol 179:1193–1199PubMedGoogle Scholar
  9. 9.
    Akazawa K, Tamaki Y, Taguchi T et al (2006) Preoperative evaluation of residual tumour extent by three-dimensional magnetic resonance imaging in breast cancer patients treated with neoadjuvant chemotherapy. Breast J 12:130–137PubMedCrossRefGoogle Scholar
  10. 10.
    Partridge SC, Gibbs JE, Lu Y et al (2005) MRI measurements of breast tumour volume predict response to neoadjuvant chemotherapy and recurrent free survival. AJR Am J Roentgenol 184:1174–1781Google Scholar
  11. 11.
    James K, Eisenhauer E, Christian M et al (1999) Measuring response in solid tumours: unidimensional versus bidimensional measurements. J Natl Cancer Inst 91:523–528PubMedCrossRefGoogle Scholar
  12. 12.
    Kaste SC, Liu T, Billups CA et al (2004) Tumour size as a predictor of outcome in pediatric non-metastatic osteosarcoma of the extremity. Pediatr Blood Cancer 43:723–728PubMedCrossRefGoogle Scholar
  13. 13.
    Soutter WB, Hanoch J, D’Arcy T et al (2004) Pretreatment tumour volume measurement on high-resolution magnetic resonance imaging as a predictor of survival in cervical cancer. BJOG 111:741–747PubMedCrossRefGoogle Scholar
  14. 14.
    Nicolet V, Carignan L, Bourdon F et al (2000) MR imaging of cervical carcinoma: a practical staging approach. Radiographics 20:1539–1549PubMedGoogle Scholar
  15. 15.
    Levrini G, Mori CA, Vacondio R et al (2008) MRI patterns of invasive lobular cancers: T1 and T2 features. Radiol Med 113:1110–1115PubMedCrossRefGoogle Scholar
  16. 16.
    Sardanelli F, Boetes C, Borisch B et al (2010) Magnetic resonance imaging of the breast: recommendation from the EUSOMA working group. Eur J Cancer 46:1296–1316PubMedCrossRefGoogle Scholar
  17. 17.
    Sardanelli F, Giuseppetti M, Canavese G et al (2008) Indications for Breast Magnetic Resonance Imaging, Consensus Document “Attualità in senologia”, Florence 2007, Radiol Med 113:1085–1095PubMedCrossRefGoogle Scholar
  18. 18.
    Arazi-Kleinman T, Causer P, Jong R et al (2009) 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 64:1166–1174PubMedCrossRefGoogle Scholar
  19. 19.
    Baltzer P, Freiberg C, Beger S et al (2009) Clinical MR-mammography: are computer-assisted methods superior to visual or manual measurements for curve type analysis? A systematic approach. Acad Radiol 16:1070–1076PubMedCrossRefGoogle Scholar
  20. 20.
    Meeuwis C, van de Ven, Stapper G et al (2010) Computer-aided detection (CAD) for breast MRI: evaluation of efficacy at 3.0 T. Eur Radiol 20:522–528PubMedCrossRefGoogle Scholar
  21. 21.
    Berg W, Gutierrez L, NessAiver M (2004) Diagnostic accuracy of mammography, clinical examination, US, and MR imaging in preoperative assessment of breast cancer. Radiology 233:830–849PubMedCrossRefGoogle Scholar
  22. 22.
    Solin LJ, Orel SG, Hwang W-T et al (2008) Relationship of breast magnetic resonance imaging to outcome after breast-conservation treatment with radiation for women with early-stage invasive breast carcinoma or ductal carcinoma in situ. J Clin Oncol 26:386–391PubMedCrossRefGoogle Scholar
  23. 23.
    Heywang-Kobrunner SH, Bick U, Bradley WG Jr et al (2001) International investigation of breast MRI: results of a multicentre study (11 sites) concerning diagnostic parameters for contrast-enhanced MRI based on 519 histopathologically correlated lesions. Eur Radiol 11:531–546PubMedCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Italia 2011

Authors and Affiliations

  • G. Levrini
    • 1
  • R. Sghedoni
    • 2
    Email author
  • C. Mori
    • 1
  • A. Botti
    • 2
  • R. Vacondio
    • 1
  • A. Nitrosi
    • 2
  • M. Iori
    • 2
  • F. Nicoli
    • 1
  1. 1.Diagnostic Imaging DepartmentArcispedale S. Maria NuovaReggio EmiliaItaly
  2. 2.Medical Physics DepartmentArcispedale S. Maria NuovaReggio EmiliaItaly

Personalised recommendations