{"id":{"repo_id":"soton","oai_identifier":"oai:eprints.soton.ac.uk:194557"},"canonical_url":"https://search.dev.ndltd.org/etd/soton/oai:eprints.soton.ac.uk:194557","repository":{"repo_id":"soton","name":"University of Southampton","base_url":"https://eprints.soton.ac.uk/cgi/oai2"},"display":{"title":"Image processing in echography and MRI","abstract":"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.","abstract_html":"This work deals with image processing for three medical imaging applications: speckle&lt;br/&gt;detection in 3D ultrasound, left ventricle detection in cardiac magnetic resonance imaging&lt;br/&gt;(MRI) and flow feature visualisation in velocity MRI.&lt;br/&gt;&lt;br/&gt;For speckle detection, a learning from data approach was taken using pattern recognition&lt;br/&gt;principles and low-level image features, including signal-to-noise ratio, co-occurrence&lt;br/&gt;matrix, asymmetric second moment, homodyned k-distribution and a proposed specklet&lt;br/&gt;detector. For left ventricle detection, template matching was used. Forvortex detection,&lt;br/&gt;a data processing framework is presented that consists of three main steps: restoration,&lt;br/&gt;abstraction and tracking. This thesis addresses the first two problems, implementing&lt;br/&gt;restoration with a total variation first order Lagrangian method, and abstraction with&lt;br/&gt;clustering and local linear expansion.","abstract_has_math":false,"creators":["Carmo, Bernardo S."],"institution":"University of Southampton","degree_name":"Ph.D.","degree_level":"doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Prugel-Bennett, Adam"],"committee_chairs":[],"committee_members":[],"year":2005,"date_issued":"2005-04","date_published":"2005-04","updated_at":"2026-07-24T04:36:32Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Prugel-Bennett, Adam"]},{"key":"dc:creator","label":"Author","values":["Carmo, Bernardo S."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2005-04"]},{"key":"dc:date.issued","label":"Date","values":["2005-04"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Electronics & Computer Science (pre 2011 reorg)","School of Electronics and Computer Science"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Southampton"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://eprints.soton.ac.uk/194557/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["Ph.D."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://eprints.soton.ac.uk/194557/1/00302041.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:format","label":"Dc Format","values":["text"]},{"key":"dc:title","label":"Title","values":["Image processing in echography and MRI"]}]}],"canonical_facts":{"dc:contributor.advisor":["Prugel-Bennett, Adam"],"dc:creator":["Carmo, Bernardo S."],"dc:date":["2005-04"],"dc:date.issued":["2005-04"],"dc:description.abstract":["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."],"dc:format":["text"],"dc:identifier.uri":["https://eprints.soton.ac.uk/194557/1/00302041.pdf"],"dc:publisher.department":["Electronics & Computer Science (pre 2011 reorg)","School of Electronics and Computer Science"],"dc:publisher.institution":["University of Southampton"],"dc:relation.isreferencedby":["https://eprints.soton.ac.uk/194557/"],"dc:title":["Image processing in echography and MRI"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["doctoral"],"dc:type.qualificationname":["Ph.D."]},"updated_at":"2026-07-24T04:36:32Z"}