A multidimensional signal processing approach for classification of microwave measurements with application to stroke type diagnosis

Hamed Yousefi Mesri; Masoud Khazaeli Najafabadi; Tomas McKelvey

doi:10.1109/IEMBS.2011.6091596

A multidimensional signal processing approach for classification of microwave measurements with application to stroke type diagnosis

Annu Int Conf IEEE Eng Med Biol Soc. 2011:2011:6465-9. doi: 10.1109/IEMBS.2011.6091596.

Authors

Hamed Yousefi Mesri¹, Masoud Khazaeli Najafabadi, Tomas McKelvey

Affiliation

¹ Department of Signals and Systems, Chalmers University of Technology, Gothenburg, Sweden. mesri@student.chalmers.se

PMID: 22255819
DOI: 10.1109/IEMBS.2011.6091596

Abstract

A multidimensional signal processing method is described for detection of bleeding stroke based on microwave measurements from an antenna array placed around the head of the patient. The method is data driven and the algorithm uses samples from a healthy control group to calculate the feature used for classification. The feature is derived using a tensor approach and the higher order singular value decomposition is a key component. A leave-one-out validation method is used to evaluate the properties of the method using clinical data.

MeSH terms

Algorithms
Artificial Intelligence
Cerebral Hemorrhage / diagnosis*
Decision Support Systems, Clinical
Decision Support Techniques
Electromagnetic Radiation
Equipment Design
Humans
Microwaves
Models, Statistical
Models, Theoretical
Scattering, Radiation
Signal Processing, Computer-Assisted*
Stroke / diagnosis*