Exploratory Characterization of Outliers in a Multi-centre 1H-MRS Brain Tumour Dataset
As part of the AIDTumour research project, the analysis of MRS data corresponding to various tumour pathologies is used to assist expert diagnosis. The high dimensionality of the MR spectra might obscure atypical aspects of the data that would jeopardize their automated classification and, as a result, the process of computer-based diagnostic assistance. In this paper, we put forward a method to overcome this potential problem that combines automatic outlier detection, visualization through dimensionality reduction, and expert opinion.
KeywordsProton Magnetic Resonance Spectroscopy Brain Tumours Outlier Detection Data exploration Data Visualization Dimensionality Reduction Medical Decision Support Systems
Unable to display preview. Download preview PDF.
- 1.Artificial Intelligence Decision Tools for Tumour diagnosis research project, http://www.lsi.upc.edu/~websoco/AIDTumour
- 6.KING visualization software, http://kinemage.biochem.duke.edu/software/king.php
- 8.Dickersin, K., Straus, S.E., Bero, L.A.: Evidence Based Medicine: Increasing, not Dictating. Choice. Brit. Med. J. 334(supl.1), s10 (2007)Google Scholar