Automatic recognition and classification of cerebral microemboli in ultrasound images

Aim of this work was the definition of a method devoted to the automated recognition of different composition of cerebral microemboli. The developed diagnostic procedure makes use of a features-based analysis of ultrasonographic images containing the characteristic microembolic signals. The images were acquired with a Transcranial Doppler, and classified using a Hierarchical Neural Network. The proposed procedure has been tested on clinical cases selected by expert neurologists for their relevance and experimental results have showed its reliability.