Image processing in echography and MRI

This work deals with image processing for three medical imaging applications: speckle<br/>detection in 3D ultrasound, left ventricle detection in cardiac magnetic resonance imaging<br/>(MRI) and flow feature visualisation in velocity MRI.<br/><br/>For speckle detection, a learning from data approach was taken using pattern recognition<br/>principles and low-level image features, including signal-to-noise ratio, co-occurrence<br/>matrix, asymmetric second moment, homodyned k-distribution and a proposed specklet<br/>detector. For left ventricle detection, template matching was used. Forvortex detection,<br/>a data processing framework is presented that consists of three main steps: restoration,<br/>abstraction and tracking. This thesis addresses the first two problems, implementing<br/>restoration with a total variation first order Lagrangian method, and abstraction with<br/>clustering and local linear expansion.

Name dc:type.qualificationname

Ph.D.

Level dc:type.qualificationlevel

doctoral

Grantor dc:publisher.institution

University of Southampton

Year dc:date.issued

2005

Author dc:creator

• Carmo, Bernardo S.

Advisor dc:contributor.advisor

• Prugel-Bennett, Adam