Classification of phosphorus magnetic resonance spectroscopic imaging of brain tumors using support vector machine and logistic regression at 3T

Annu Int Conf IEEE Eng Med Biol Soc. 2014;2014:2392-5. doi: 10.1109/EMBC.2014.6944103.

Abstract

This study aims classification of phosphorus magnetic resonance spectroscopic imaging ((31)P-MRSI) data of human brain tumors using machine-learning algorithms. The metabolite peak intensities and ratios were estimated for brain tumor and healthy (31)P MR spectra acquired at 3T. The spectra were classified based on metabolite characteristics using logistic regression and support vector machine. This study showed that machine learning could be successfully applied for classification of (31)P-MR spectra of brain tumors. Future studies will measure the performance of classification algorithms for (31)P-MRSI of brain tumors in a larger patient cohort.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Adult
  • Brain Neoplasms / diagnosis*
  • Female
  • Humans
  • Logistic Models
  • Magnetic Resonance Imaging / methods*
  • Magnetic Resonance Spectroscopy / methods*
  • Middle Aged
  • Phosphorus*
  • ROC Curve
  • Support Vector Machine*

Substances

  • Phosphorus