Statistical and Neuro-fuzzy approaches for emboli detection

Denis Kouamé (1, 2) , Mathieu Biard (1) , Jean-Marc Girault (1) , Aurore Bleuzen (3, 1) , François Tranquart (1) , Fabrice Patat (1)

1 LUSSI - Laboratoire Ultrasons Signaux et Instrumentation
2 IRIT-TCI - Traitement et Compréhension d’Images
3 CHRU Tours - Centre Hospitalier Régional Universitaire de Tours

Relation between cerebral emboli occurrence and stroke has been suggested these last years. Emboli detection has then become a constant concern while monitoring cerebral vascular pathologies. This detection is based on analysis of embolic TransCranial Doppler (TCD) signal. In practical experiments, most of detected emboli are big-size emboli ones, because of their easy-to-recognize signature in the TCD signal. The problem of small size emboli detection is an opened one and remains a challenge. Different approaches have been proposed to solve this problem. They use exclusively human expert knowledge or automatic collection of signal parameters. In this paper we propose to used both expert knowledge and automatic processing through neuro-fuzzy approach. Performances evaluation and comparison with high performance micro-emboli detection technique, namely Autoregressive (AR) modelling are provided, using in vitro in this work.

Mots clés: cerebral emboli occurrence; neuro-fuzzy approaches; statistical approaches; cerebral vascular pathology monitoring; embolic TransCranial Doppler signal detection; TCD signal detection; small size emboli detection; automatic signal parameter collection; human expert knowledge; performance evaluation; autoregressive modelling; AR modelling; high performance microemboli detection technique; stroke

Domaines: Traitement du signal et de l'image [eess.SP]; Imagerie médicale

Denis Kouamé, Mathieu Biard, Jean-Marc Girault, Aurore Bleuzen, François Tranquart, et al.. Statistical and Neuro-fuzzy approaches for emboli detection. 12th European Signal and Image Processing Conference (EUSPICO 2004), European Association for Signal Processing (EURASIP), Sep 2004, Vienna, Austria. pp.2211-2214. ⟨hal-03149794⟩