RUcore Resource Object
RUcore Resource Object
PDF-1(943.10 KB)
TitleConcurrent segmentation of the prostate on MRI and CT
via linked statistical shape models for radiotherapy
planning
NameChowdhury, A.K. Najeebullah (author), Madabhushi, Anant (chair), Ganesan, Shridar (internal member), Papathomas, Thomas (internal member), Rutgers University, Graduate School - New Brunswick,
Degree Date2011-10
Date Created2011
SubjectBiomedical Engineering,
Prostate--Cancer—Radiotherapy,
Prostate—Magnetic resonance imaging,
Prostate—Cross-sectional imaging
DescriptionProstate gland segmentation is a critical step in prostate radiotherapy planning, where dose plans are typically formulated on CT. Pre-treatment MRI is now beginning to be acquired at several medical centers. Delineation of the prostate on MRI is acknowledged as being significantly simpler to do compared to CT. In this work, we present a novel framework for building a linked statistical shape model (LSSM), a statistical shape model (SSM) that links the shape variation of a structure of interest (SOI) across multiple imaging modalities. We apply the LSSM in the context of multi-modal prostate segmentation for radiotherapy planning, where the prostate is concurrently segmented on MRI and CT. First, we utilize multi-modal registration of MRI and CT to map 2D boundary delineations of the prostate from MRI onto corresponding CT, for a set of training studies. Hence, our scheme obviates the need for expert prostate delineations on CT for explicitly constructing a SSM for prostate CT segmentation on CT. The delineations of the prostate gland on MRI and CT allows for 3D reconstruction of the prostate shape which facilitates the building of the LSSM. In order to perform concurrent prostate MRI and CT segmentation using the LSSM, we employ a region-based level-set approach where we deform the evolving prostate boundary to simultaneously fit to MRI and CT images in which voxels are classified to be either part of the prostate or outside the prostate. The classification is facilitated by using a combination of MRI-CT probabilistic spatial atlases and a random forest classifier, driven by gradient and Haar features. We acquire a total of 20 MRI-CT patient studies and use the leave-one-out strategy to train and evaluate four different LSSMs. Firstly, a fusion-based LSSM (fLSSM) is built using expert ground truth delineations of the prostate on MRI alone, where the ground truth for the gland on CT is obtained via coregistration of the corresponding MRI and CT slices. We compare the fLSSM against another idealized LSSM (xLSSM), where expert delineations of the gland on both MRI and CT are employed in the model building. We also compare the fLSSM against a CT-based SSM (ctSSM), built from expert delineations of the gland on CT alone. In addition, 2 LSSMs trained using trainee delineations (tLSSM) on CT are compared with the fLSSM. Our results indicate that the xLSSM, tLSSMs and the fLSSM perform equivalently, all of them out-performing the ctSSM. The fLSSM provides an accurate alternative to SSMs that require careful expert delineations of the SOI that may be difficult or laborious to obtain. Additionally the fLSSM has the added benefit of providing concurrent segmentations of the SOI on multiple imaging modalities.
NoteM. S.
NoteIncludes bibliographical references
NoteIncludes vita
Noteby A.K. Najeebullah Chowdhury
Genretheses
Persistent URLhttp://hdl.rutgers.edu/1782.1/rucore10001600001.ETD.000063357
Languageeng
CollectionGraduate School - New Brunswick Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.