PUMA
Istituto di Scienza e Tecnologie dell'Informazione     
Barcaro U., Di Bona S., Fontanelli R., La Manna S., Orlandi G., Salvetti O., Sartucci F. Real-time Detection and Clinical Categorisation of Ultrasound High Intensity Transient Signals. In: WSEAS Transactions on Systems, vol. 2 (4) pp. 921 - 926. WSEAS, 2003.
 
 
Abstract
(English)
In this paper we address the problem of interpreting ultrasound images obtained from doppler devices in order to classify, and hence to distinguish, the dangerous cerebral microemboli from the innocuous ones. In order to obtain an automatic categorisation of the cerebral high intensity transient signal, a multilevel neural network based on a hierarchical architecture has been implemented for image processing and classification. The images, obtained by measuring the blood flow velocities in brain arteries and veins,have been acquired using the 'Multi Dop X4' ultrasound device by DWL. The approach proposed, applied to real clinical cases selected by expert neurologists for their peculiar characteristics, has shown to be a valid real-time support for the diagnosis of cerebral vascular diseases
Subject Hierarchical Neural Networks
Image Classification
Eco-Doppler
Imaging, Emboli Classification
I.2.10 Vision and Scene Understanding
I.5.2 Design Methodology
I.5.1 Models


Icona documento 1) Download Document PDF


Icona documento Open access Icona documento Restricted Icona documento Private

 


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional