SpectraClassifier (SC) is a Java solution for designing and implementing Magnetic Resonance Spectroscopy (MRS)-based classifiers. The main goal of SC is to allow users with minimum background knowledge of multivariate statistics to perform a fully automated pattern recognition analysis. SC incorporates feature selection (greedy stepwise approach, either forward or backward), and feature extraction (PCA). Fisher Linear Discriminant Analysis is the method of choice for classification. Classifier evaluation is performed through various methods: display of the confusion matrix of the training and testing datasets; K-fold crossvalidation, leave-one-out and bootstrapping as well as Receiver Operating Characteristic (ROC) curves.
SC is composed of the following modules: Classifier design, Data exploration, Data visualisation, Classifier evaluation, Reports, and Classifier history. It is able to read low resolution in-vivo MRS (single-voxel and multi-voxel) and high resolution tissue MRS (HRMAS) processed with existing tools (jMRUI, INTERPRET, 3DiCSI or TopSpin). In addition, to facilitate exchanging data between applications, a standard format capable of storing all the information needed for a dataset was developed.
SC is a user-friendly software designed to fulfil the needs of potential users in the MRS community.
Availability and requirements
Project name: SpectraClassifier (SC)
Project home page: http://gabrmn.uab.es/sc
Operating system(s): Platform independent
Programming language: Java
Other requirements: Java 1.6.0 or higher
License: Available free of charge, subject to the signature of a disclaimer and user agreement text
SpectraClassifier 3.0.09 release note
SpectraClassifier 3.0.09 contains some useful tools, such as the BER curve to evaluate the performance of the classifier. The balanced error rate are shown, either training or testing datasets. Please, see the help and manual of version 3.0.09 for details.
Downloads and documentation
|Version||Date||Disclaimer link||Documentation (in PDF)|
|1.0||2009-09-08||help and manual|
|2.0||2010-05-11||help and manual|
|3.0,06||2011-06-15||help and manual|
|3.0.08||2011-11-17||help and manual|
|3.0.09||2012-05-15||help and manual|
If you have any problem downloading the software, please contact to: sc at gabrmn dot uab dot es.
If you made a request to download any version of SpectraClassifier, and you have not received any response in more than three working days, please do not hesitate to directly contact to sc at gabrmn dot uab dot es.
We would appreciate from you to acknowledge SpectraClassifier in every instance where it has been used. It could be referenced by the following citation:
SpectraClassifier 1.0: a user friendly, automated MRS-based classifier-development system
Sandra Ortega-Martorell, Ivan Olier, Margarida Julia-Sape and Carles Arus
BMC Bioinformatics 2010, 11:106. doi:10.1186/1471-2105-11-106
Published: 24 February 2010