Facial soft tissue segmentation in mri using unlabeled

Download
index.pdf
2011
Rezaeitabar, Yousef
Show full item record
116
views
98
downloads
Segmentation of individual facial soft tissues has received relatively little attention in the literature due to the complicated structures of these tissues. There is a need to incorporate the prior information, which is usually in the form of atlases, in the segmentation process. In this thesis we performed several segmentation methods that take advantage of prior knowledge for facial soft tissue segmentation. An atlas based method and three expectation maximization – Markov random field (EM-MRF) based methods are tested for two dimensional (2D) segmentation of masseter muscle in the face. Atlas based method uses the manually labeled atlases as prior information. We implemented EM-MRF based method in different manners; without prior information, with prior information for initialization and with using labeled atlas as prior information. The differences between these methods and the influence of the prior information are discussed by comparing the results. Finally a new method based on EM-MRF is proposed in this study. In this method we aim to use prior information without performing manual segmentation, which is a very complicated and time consuming task. 10 MRI sets are used as experimental data in this study and leave-one-out technique is used to perform segmentation for all sets. The test data is modeled as a Markov Random Field where unlabeled training data, i.e., other 9 sets, are used as prior information. The model parameters are estimated by the Maximum Likelihood approach when the Expectation Maximization iterations are used to handle hidden labels. The performance of all segmentation methods are computed and compared to the manual segmented ground truth. Then we used the new 2D segmentation method for three dimensional (3D) segmentation of two masseter and two temporalis tissues in each data set and visualize the segmented tissue volumes.
Human anatomy, Biomedical engineering.
http://etd.lib.metu.edu.tr/upload/12613546/index.pdf
https://hdl.handle.net/11511/21016
Graduate School of Natural and Applied Sciences, Thesis

Suggestions

Interdependence of pulsed ultrasound and shear stress effects on cell morphology and gene expression
Mccormick, Susan M.; Saini, Vikas; Yazıcıoğlu, Yiğit; Demou, Zoe N.; Royston, Thomas J. (Springer Science and Business Media LLC, 2006-03-01)
Fluid shear stress is a key biomechanical regulatory factor in a several biological systems including bone tissue. Bone cells are also regulated by exogenous acoustic vibration, which has therapeutic benefits. In this study, we determined the effects of shear stress and pulsed ultrasound (US), alone and in series on osteoblast morphology and gene expression. We observed that shear stress (19 dyne/cm(2)) elongated SaOS-2 cells at 3, 6, 24, and 48 h decreasing their shape index from control values of 0.51 +/-...
GENERATION AND CHARACTERIZATION OF HYDROGEL MICRODROPLETS AS BIOINK FOR BIOPRINTING APPLICATIONS
Sucularlı, Ferah; Yıldırım, Ender; Arıkan, Mehmet Ali Sahir (null; 2019-04-11)
In this study, we present a technique for generation of hydrogel microdroplets as bioink for droplet deposition of tissues and organs. We also characterized the size and dispersion of the microdroplets. For this purpose, we designed a flow-focusing droplet generator chip in which uncured hydrogel flowing through a 120 µm wide channel was pinched at two sides of the stream of oil flowing along 300 µm wide channels. The chip was fabricated by ultrasonically embossing the features on polymethylmethacrylate (PM...
Nonlinear viscoelastic material property estimation of lower extremity residual limb tissues
Tönük, Ergin (ASME International, 2004-04-01)
Axisymmetric nonlinear finite-element analysis was used to simulate force-relaxation and creep data obtained during in vivo indentation of the residual limb sofa tissues of six individuals with trans-tibial amputation [1]. The finite-element models facilitated estimation of an appropriate set of nonlinear viscoelastic material coefficients of extended James-Green-Simpson material formulation for bulk soft tissue at discrete, clinically relevant test locations. The results indicate that over 90% of the exper...
Fabrication of functionalized citrus pectin/silk fibroin scaffolds for skin tissue engineering
Türkkan, Sibel; Atila, Deniz; Akdağ, Akın; Tezcaner, Ayşen (Wiley, 2018-10-01)
In this study, novel porous three-dimensional (3D) scaffolds from silk fibroin (SF) and functionalized (amidated and oxidized) citrus pectin (PEC) were developed for skin tissue engineering applications. Crosslinking was achieved by Schiff's reaction in borax presence as crosslinking coordinating agent and CaCl2 addition. After freeze-drying and methanol treatment, plasma treatment (10 W, 3 min) was applied to remove surface skin layer formed on scaffolds. 3D matrices had high porosity (83%) and interconnec...
Improving Current Density Recovery and Magnetic Flux Density Imaging in Diffusion Tensor Magnetic Resonance Electrical Impedance Tomography Applications
Açıkgöz, Berk Can; Eyüboğlu, Behçet Murat; Department of Electrical and Electronics Engineering (2021-8-10)
The electrical conductivity of biological tissues incorporates crucial information regarding the tissues' physiological status. Therefore, there have been many studies for probing the electrical conductivity of biological tissues through Magnetic Resonance Imaging (MRI). Diffusion Tensor Magnetic Resonance Electrical Impedance Tomography (DT-MREIT) is an emerging modality that utilizes a linear relationship between the diffusion tensor and the conductivity tensor and the current density distribution through...
Citation Formats
Y. Rezaeitabar, “Facial soft tissue segmentation in mri using unlabeled,” M.S. - Master of Science, Middle East Technical University, 2011.
METU IIS - Integrated Information Service open@metu.edu.tr