Journal of Digital Imaging

, Volume 14, Supplement 1, pp 58–59 | Cite as

A use of a neural network to evaluate contrast enhancement curves in breast magnetic resonance images

Session 4: Image Acquistion and Processing


For the diagnosis of breast cancer using magnetic resonance imaging (MRI), one of the most important parameters is the analysis of contrast enhancement. A threedimensional MR sequence is applied before and five times after bolus injection of paramagnetic contrast medium (Gd-DTPA). The dynamics of absorption are described by a time/intensity enhancement curve, which reports the mean intensity of the MR signal in a small region of interest (ROI) for about 8 minutes after contrast injection. The aim of our study was to use an artificial neural network to automatically classify the enhancement curves as “benign” or “malignant.” We used a classic feed-forward back-propagation neural network, with three layers: five input nodes, two hidden nodes, and one output node. The network has been trained with 26 pathologic curves (10 invasive carcinoma [K], two carcinoma-in-situ [DCIS], and 14 benign lesion [B]). The trained network has been tested with 58 curves (36 K, one DCIS, 21 B). The network was able to correctly identify the test curves with a sensitivity of 76% and a specificity of 90%. For comparison, the same set of curves was analyzed separately by two radiologists (a breast MR expert and a resident radiologist). The first correctly interpreted the curves with a sensitivity of 76% and a specificity of 90%, while the second scored 59% for sensitivity and 90% for specificity. These results demonstrate that a trained neural network recognizes the pathologic curves at least as well as an expert radiologist. This algorithm can help the radiologist attain rapid and affordable screening of a large number of ROIs. A complete automatic computer-aided diagnosis support system should find a number of potentially interesting ROIs and automatically analyze the enhancement curves for each ROI by neural networks, reporting to the radiologist only the potentially pathologic ROIs for a more accurate, manual, repeated evaluation.


Neural Network Hide Node Input Node Breast Magnetic Resonance Image Trained Network 


  1. 1.
    Heywang-Kobrunner SH, Beck R: Contrast Enhanced MRI of the Breast (ed 2). Berlin, Germany, Springer-Verlag, 1996Google Scholar
  2. 2.
    Kühl CK, Mielcareck P, Klaschik S, et al: Dynamic breast MR imaging: Are signal intensity time course data useful for differential diagnosis of enhancing lesions? Radiology 211:5–7, 1999Google Scholar
  3. 3.
    Abdolmaleki P, Buadu LD, Murayama S, et al: Neural network analysis of breast cancer from MRI findings. Radiat Med 15:283–293, 1997PubMedGoogle Scholar
  4. 4.
    Fischer H, Henning J: Neural network-based analysis of MR time series. Magn Reson Med 41:124–131, 1999CrossRefPubMedGoogle Scholar
  5. 5.
    Rumelhart DE, Hinton GE, Williams RJ: Learning internal representations by back-propagation errors. Nature 332: 533–536, 1986CrossRefGoogle Scholar
  6. 6.
    Apolloni B, Ronchini G: Dynamic sizing of multilayer perceptions. Biol Cybernet 71:49–63, 1994CrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2001

Authors and Affiliations

  • D. Vergnaghi
    • 1
    • 2
    • 3
  • A. Monti
    • 1
    • 2
    • 3
  • E. Setti
    • 1
    • 2
    • 3
  • R. Musumeci
    • 1
    • 2
    • 3
  1. 1.Department of Images for Diagnosis and Therapy Radiodiagnostic Unit ANational Cancer InstituteMilan
  2. 2.Department of InformaticsUniversity of MilanMilanItaly
  3. 3.Unitá Operativa Radiodiagnostica AIstituto Nationale TumoriMilanoItaly

Personalised recommendations