Localization of hemorrhage site in stroke patients using multichannel microwave measurements.

Microwave measurements from an antenna array placed around the head can be used to detect changes in dielectric properties of the brain. In this paper an algorithm is developed to provide localization information of the site of an intra cerebral hemorrhage. The algorithm is based in the hypothesis that scattering parameters for an antenna pair close to the site of the bleeding will undergo larger changes. The change is measured using a feature derived from the scattering measurements using higher order singular value decomposition and is compared with the feature derived from measurements from a control group of healthy subjects. The proposed algorithm is evaluated on clinical data and the result is compared with computed tomography images of the patients.

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

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.