Hide metadata

dc.date.accessioned2016-07-04T12:56:54Z
dc.date.available2016-07-04T12:56:54Z
dc.date.created2016-06-29T20:53:13Z
dc.date.issued2016
dc.identifier.urihttp://hdl.handle.net/10852/50558
dc.description.abstractCardiac ultrasound is a key component in modern cardiology, and is widely used to assess and quantify the heart’s anatomy and function. In the past two decades, real-time 3-dimensional ultrasound has emerged as a promising modality, allowing a more accurate appreciation of the heart’s complex geometry, compared to the more conventional 2-dimensional ultrasound. However, the huge increases in information within volumetric images demand accurate and efficient methods for automatically analyzing and quantifying the heart. One of the fundamental problems in the processing of cardiac images is segmentation; the process of extracting a geometric model from the image, describing the shape and motion of an anatomical structure. A framework has previously been proposed for solving this problem in 3D ultrasound images, in which the segmentation is expressed as a state-estimation problem and solved with a Kalman filter. This framework is generic, and allows for incorporating different surface representations, image measurements and prior information on shape and motion, and it has been applied to the left ventricle. The main goal of this thesis has been to apply the existing Kalman filter segmentation framework to different anatomical structures, in particular the aortic root and right ventricle, and to develop a method for biventricular segmentation. Four main contributions have been made. Firstly, a method providing fully automatic quantification of the aortic valve size from 3D ultrasound images has been developed and its feasibility demonstrated. This is a key measurement to be made prior to procedures on diseased valves, and performing manual measurements is time-consuming and subject to inter-observer variation. Secondly, two methods have been developed for automated segmentation of the Right Ventricle (RV). Historically, the importance of the RV has been underestimated. Although the RV’s role in cardiovascular diseases has been more widely recognized in recent years, few methods for segmentation of the RV have been proposed. Because the RV has a more complex and asymmetrical shape compared to the left ventricle, the existing segmentation framework is not immediately applicable to the RV. Therefore, the method was extended with a geometric model learned from statistical analysis on a set of manual segmentations, as well as prior information on the appearance of the ultrasound images. Thirdly, one of the two RV methods uses a novel geometric surface representation to simultaneously segment the endocardial and epicardial borders of both ventricles. The surface is parameterized such that myocardial volume conservation is used within the Kalman filter segmentation process, which leads to a much more complete model of the heart and allows one to study the interaction between the ventricles. Finally, a robust and fully automatic method for spatio-temporal fusion of two ultrasound images has been developed. This is important as it is unrealistic to capture both ventricles in the same imaging sector. Furthermore, the method is able to perform the spatial registration with no assumption on the relationship between the recordings.en_US
dc.languageEN
dc.language.isoenen_US
dc.publisherUniversitetet i Oslo
dc.relation.haspartPaper I Automatic Measurement of Aortic Annulus Diameter in 3-Dimensional Transoesophageal Echocardiography. Jørn Bersvendsen, Jan O. Beitnes, Stig Urheim, Svend Aakhus and Eigil Samset. BMC Medical Imaging, 2014, 14:31. The published version is available in DUO: http://urn.nb.no/URN:NBN:no-46998
dc.relation.haspartPaper II Automated Segmentation of the Right Ventricle in 3D Echocardiography: A Kalman Filter State Estimation Approach. Jørn Bersvendsen, Fredrik Orderud, Richard J.Massey, Kristian Fosså, Olivier Gerard, Stig Urheimand Eigil Samset, IEEE Transactions onMedical Imaging, 2016, 35:1. © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: http://dx.doi.org/10.1109/TMI.2015.2453551
dc.relation.haspartPaper III Automated Bi-Ventricular Segmentation in 3-Dimensional Echocardiography by Coupled Deformable Surfaces. Jørn Bersvendsen, Fredrik Orderud, Øyvind Lie, Richard J. Massey, Kristian Fosså, Raúl San José Estépar, Stig Urheimand Eigil Samset. To be published. The paper is removed from the thesis in DUO awaiting publishing.
dc.relation.haspartPaper IV Robust Spatio-Temporal Registration of 4D Cardiac Ultrasound Sequences. Jørn Bersvendsen, Matthew Toews, Adriyana Danudibroto, William M.Wells III, Raúl San José Estépar, Stig Urheim and Eigil Samset. Proc. SPIE 9790, Medical Imaging 2016: Ultrasonic Imaging and Tomography. The published version is available at: http://dx.doi.org/10.1117/12.2217005
dc.relation.urihttp://urn.nb.no/URN:NBN:no-46998
dc.relation.urihttp://dx.doi.org/10.1109/TMI.2015.2453551
dc.relation.urihttp://dx.doi.org/10.1117/12.2217005
dc.titleSegmentation of cardiac structures in 3-dimensional echocardiographyen_US
dc.typeDoctoral thesisen_US
dc.creator.authorBersvendsen, Jørn
cristin.unitcode185,15,0,0
cristin.unitnameDet matematisk-naturvitenskapelige fakultet
cristin.ispublishedtrue
cristin.fulltextoriginal
dc.identifier.cristin1365113
dc.identifier.urnURN:NBN:no-54101
dc.type.documentDoktoravhandlingen_US
dc.identifier.fulltextFulltext https://www.duo.uio.no/bitstream/handle/10852/50558/4/PhD-Bersvendsen-DUO.pdf


Files in this item

Appears in the following Collection

Hide metadata