Binary classification of brain tumours using a Discrete Wavelet Transform and energy criteria

The accurate diagnosis of human brain tumours is a sensitive medical task, for which radiology experts often must rely on indirect signal measurements. There is thus a need for developing computer-based decision support tools to assist doctors in their diagnostic task. The experiments in this brief paper address such problem in the form of binary classification, for which the pre-processing of the Magnetic Resonance Spectroscopy (MRS) signal is a most relevant data analysis stage. A combination of the Discrete Wavelet Transform (DWT) for signal decomposition and an energy criterion for signal reconstruction is used to pre-process the MRS data prior to the feature selection and classification with Bayesian Neural Networks.

[1]  W. Hall.  The safety and efficacy of stereotactic biopsy for intracranial lesions , 1998, Cancer.

[2]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[3]  J. Schramm,et al.  Experimental spinal cord injury produced by slow, graded compression. Alterations of cortical and spinal evoked potentials. , 1979, Journal of neurosurgery.

[4]  Nathalie Japkowicz,et al.  The Class Imbalance Problem: Significance and Strategies , 2000 .

[5]  Enrique Romero,et al.  Frequency Selection for the Diagnostic Characterization of Human Brain Tumours , 2009, CCIA.

[6]  Bashar A. Rajoub.  An efficient coding algorithm for the compression of ECG signals using the wavelet transform , 2002, IEEE Transactions on Biomedical Engineering.

[7]  J. Taha,et al.  An Analysis of the Respective Risks of Hematoma Formation in 361 Consecutive Morphological and Functional Stereotactic Procedures , 2002, Neurosurgery.

[8]  Mohammad Reza Karami Mollaei,et al.  ECG Compression with Thresholding of 2-D Wavelet Transform Coefficients and Run Length Coding , 2009 .

[9]  M. Julià-Sapé,et al.  A Multi-Centre, Web-Accessible and Quality Control-Checked Database of in vivo MR Spectra of Brain Tumour Patients , 2006, Magnetic Resonance Materials in Physics, Biology and Medicine.

[10]  Witham,et al.  Comprehensive assessment of hemorrhage risks and outcomes after stereotactic brain biopsy. , 2001, Journal of neurosurgery.

[11]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[12]  David J. C. MacKay,et al.  The Evidence Framework Applied to Classification Networks , 1992, Neural Computation.

[13]  Christophe Ludovic,et al.  Pattern Recognition Techniques for the Study of Magnetic Resonance Spectra of Brain Tumours , 2003 .

[14]  Alfredo Vellido Alcacena,et al.  Discriminating glioblastomas from metastases in a SV1H-MRS brain tumour database , 2009 .