Automated classification of brain tumours from short echo time in vivo MRS data using Gaussian Decomposition and Bayesian Neural Networks

作者：

Highlights：

• The paper describes a method for brain tumour type discrimination from MRS signal.

• The method combines Gaussian Decomposition, dimensionality reduction and classification using Artificial Neural Networks.

• The experiments yield encouraging brain tumour classification results, a difficult task even for expert radiologists.

摘要

•The paper describes a method for brain tumour type discrimination from MRS signal.•The method combines Gaussian Decomposition, dimensionality reduction and classification using Artificial Neural Networks.•The experiments yield encouraging brain tumour classification results, a difficult task even for expert radiologists.

论文关键词：Brain tumour diagnosis,Magnetic Resonance Spectroscopy,Moving Window and Variance Analysis,Bayesian Neural Networks

论文评审过程：Available online 3 March 2014.

论文官网地址：https://doi.org/10.1016/j.eswa.2014.02.031