Multi-parametric analysis and registration of brain tumors: constructing statistical atlases and diagnostic tools of predictive value

Annu Int Conf IEEE Eng Med Biol Soc. 2011:2011:6979-81. doi: 10.1109/IEMBS.2011.6091764.

Abstract

We discuss computer-based image analysis algorithms of multi-parametric MRI of brain tumors, aiming to assist in early diagnosis of infiltrating brain tumors, and to construct statistical atlases summarizing population-based characteristics of brain tumors. These methods combine machine learning, deformable registration, multi-parametric segmentation, and biophysical modeling of brain tumors.

Publication types

  • Research Support, N.I.H., Extramural

MeSH terms

  • Algorithms
  • Artificial Intelligence
  • Biophysics / methods
  • Brain / pathology
  • Brain Mapping / methods
  • Brain Neoplasms / pathology*
  • Data Mining
  • Glioma / pathology*
  • Humans
  • Image Interpretation, Computer-Assisted / methods
  • Magnetic Resonance Imaging / methods*
  • Neoplasm Metastasis
  • Pattern Recognition, Automated / methods
  • Predictive Value of Tests
  • Prognosis
  • Reproducibility of Results