Multiscale analysis of MR-mammography data

Z Med Phys. 2007;17(3):166-71. doi: 10.1016/j.zemedi.2006.11.009.

Abstract

In this work we propose a method for automatically discriminating between different types of tissue in MR mammography datasets. This is accomplished by employing a wavelet-based multiscale analysis. After the data has been wavelet-transformed unsupervised machine learning methods are employed to identify typical patterns in the wavelet domain. To demonstrate the potential of the proposed approach we apply a filtering procedure that extracts the wavelet-based image information related to tumour tissue. In this way we obtain a robust segmentation of suspicious tissue in the MR image.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Breast Neoplasms / diagnostic imaging*
  • Education, Medical, Continuing
  • Female
  • Humans
  • Image Processing, Computer-Assisted
  • Magnetic Resonance Imaging*
  • Mammography / methods*
  • Reproducibility of Results