Automatic segmentation of human facial tissue by MRI-CT fusion: A feasibility study

Date

2012-12-01

Author

Kale, Emre H.
Mumcuoğlu, Ünal Erkan
HAMCAN, Salih

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

266
views

0
downloads

The aim of this study was to develop automatic image segmentation methods to segment human facial tissue which contains very thin anatomic structures. The segmentation output can be used to construct a more realistic human face model for a variety of purposes like surgery planning, patient specific prosthesis design and facial expression simulation. Segmentation methods developed were based on Bayesian and Level Set frameworks, which were applied on three image types: magnetic resonance imaging (MRI), computerized tomography (CT) and fusion, in which case information from both modalities were utilized maximally for every tissue type. The results on human data indicated that fusion, thickness adaptive and postprocessing options provided the best muscle/fat segmentation scores in both Level Set and Bayesian methods. When the best Level Set and Bayesian methods were compared, scores of the latter were better. Number of algorithm parameters (to be trained) and computer run time measured were also in favour of the Bayesian method.

Subject Keywords

Medical image segmentation, Human facial tissue, Data fusion, Partial volume, Level Sets, Bayesian

URI

https://hdl.handle.net/11511/30823

Journal

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE

DOI

https://doi.org/10.1016/j.cmpb.2012.07.006

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

Bayesian segmentation of human facial tissue using 3D MR-CT information fusion, resolution enhancement and partial volume modelling Şener, Emre; Mumcuoğlu, Ünal Erkan; Hamcan, Salih (2016-02-01) Background: Accurate segmentation of human head on medical images is an important process in a wide array of applications such as diagnosis, facial surgery planning, prosthesis design, and forensic identification.
Automatic Bayesian segmentation of human facial tissue using 3D MR-CT fusion by incorporating models of measurement blurring, noise and partial volume Şener, Emre; Kanoğlu, Utku; Mumcuoğlu, Ünal Erkan; Department of Engineering Sciences (2012) Segmentation of human head on medical images is an important process in a wide array of applications such as diagnosis, facial surgery planning, prosthesis design, and forensic identification. In this study, a new Bayesian method for segmentation of facial tissues is presented. Segmentation classes include muscle, bone, fat, air and skin. The method incorporates a model to account for image blurring during data acquisition, a prior helping to reduce noise as well as a partial volume model. Regularization ba...
Fabrication and characterization of bilayered tissue scaffolds incorporating bioactive agents for skin tissue engineering applications Aktürk, Ömer; Keskin, Dilek; Bilici, Temel; Department of Engineering Sciences (2015) In this study, it was aimed to fabricate tissue scaffolds from different biological polymers (collagen, silk fibroin and sericin) for skin tissue engineering applications. For this purpose, bilayered scaffolds composed of epidermal (collagen/sericin films) and dermal (collagen sponges, collagen matrices or silk fibroin matrices) layers were produced with different biomaterial fabrication methods. Casting and solvent evaporation (film), lyophilization/freeze-drying (sponge) and dry/wet electro-spinning (micr...
Sequential BMP-2/BMP-7 delivery from polyester nanocapsules Yilgor, P.; Hasırcı, Nesrin; Hasırcı, Vasıf Nejat (2010-05-01) The aim of this study was to develop a nanosized, controlled growth factor release system to incorporate into tissue engineering scaffolds and thus activate the cells seeded in the scaffold. Nanocapsules of poly(lactic acid-co-glycolic acid) (PLGA) and poly(3-hydroxybutyrate-co-3-hydroxyvalerate) (PHBV) were loaded with the bone morphogenetic proteins BMP-2 and BMP-7, respectively, and with bovine serum albumin (BSA), the model protein. BSA-loading efficiency and release kinetics were used to determine the ...
Free standing layer-by-layer films of polyethyleneimine and poly(l-lysine) for potential use in corneal stroma engineering Altay, Gizem; Hasırcı, Vasıf Nejat; Khademhosseini, Ali; Department of Biomedical Engineering (2011) In this study we fabricated free standing multilayer films of polyelectrolyte complexes for potential use in tissue engineering of corneal stroma by using the layer-by-layer (LbL) approach. In the formation of these LbL films negatively charged, photocrosslinkable (methacrylated) hyaluronic acid (MA-HA) was used along with polycations polyethyleneimine (PEI) and poly(L-lysine) (PLL). Type I collagen (Col) was blended in with PLL for improving the water absorption and cell attachment properties of the films....

Citation Formats

E. H. Kale, Ü. E. Mumcuoğlu, and S. HAMCAN, “Automatic segmentation of human facial tissue by MRI-CT fusion: A feasibility study,” COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, pp. 1106–1120, 2012, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/30823.