Feature selection and classification of breast cancer on dynamic Magnetic Resonance Imaging by using artificial neural networks

Farzaneh Keivanfard, Mohammad Teshnehlab, Mahdi Aliyari Shoorehdeli, Ke Nie, Min Ying Su

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations

Abstract

In this paper, a new feature selection and classification methods based on artificial neural network are applied to classify breast cancer on dynamic Magnetic Resonance Imaging (MRI). The database including benign and malignant lesions is specified to select the features and classify with proposed methods. It is collected from 2004 to 2006. A forward selection method is applied to find the best features for classification. Moreover, artificial neural networks such as Multilayer Preceptron (MLP) neural network, Probabilistic Neural Network (PNN) and Generalized Regression Neural Network (GRNN) are applied to classify breast cancer into two groups; benign and malignant lesions. Training and recalling neural networks are obtained with considering four-fold cross validation.

Original languageEnglish (US)
Title of host publication2010 17th Iranian Conference of Biomedical Engineering, ICBME 2010 - Proceedings
DOIs
StatePublished - 2010
Event17th Iranian Conference in Biomedical Engineering, ICBME 2010 - Isfahan, Iran, Islamic Republic of
Duration: Nov 3 2010Nov 4 2010

Publication series

Name2010 17th Iranian Conference of Biomedical Engineering, ICBME 2010 - Proceedings

Other

Other17th Iranian Conference in Biomedical Engineering, ICBME 2010
Country/TerritoryIran, Islamic Republic of
CityIsfahan
Period11/3/1011/4/10

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Physiology
  • Information Systems
  • Signal Processing

Keywords

  • Breast MRI
  • Forward selection
  • GRNN
  • MLP
  • Morphology and texture features
  • PNN

Fingerprint

Dive into the research topics of 'Feature selection and classification of breast cancer on dynamic Magnetic Resonance Imaging by using artificial neural networks'. Together they form a unique fingerprint.

Cite this