scholarly journals Automatic Segmentation of Structures in CT Head and Neck Images using a Coupled Shape Model

2016 ◽  
Author(s):  
Florian Jung ◽  
Oliver Knapp ◽  
Stefan Wesarg
Keyword(s):  
Head And Neck ◽  
Automatic Segmentation ◽  
Data Sets ◽  
Model Adaptation ◽  
Shape Variation ◽  
Adaptation Algorithm ◽  
Shape Model ◽  
Training Samples ◽  
Statistical Shape ◽  
Multiple Structures

The common approach to do a fully automatic segmentation of multiple structures is an atlas or multi-atlas based solution. These already have proven to be suitable for the segmentation of structures in the head and neck area and provide very accurate segmentation results, but can struggle with challenging cases with unnatural postures, where the registration of the reference patient(s) is extremely difficult. Therefore, we propose an coupled shape model (CoSMo) algorithm for the segmentation relevant structures in parallel. The model adaptation to a test image is done with respect to the appearance of its items and the trained articulation space. Even on very challenging data sets with unnatural postures, which occur far more often than expected, the model adaptation algorithm succeeds. The approach is based on an articulated atlas , that is trained from a set of manually labeled training samples. Furthermore, we have combined the initial solution with statistical shape models to represent structures with high shape variation. CoSMo is not tailored to specific structures or regions. It can be trained from any set of given gold standard segmentations and makes it thereby very generic.

Probabilistic Study of a Lumbar Motion Segment: Sensitivity of Kinematics to Material and Anatomical Variability

2011 ◽  
Author(s):  
Kelli S. Barnes ◽  
Jeffrey R. Armstrong ◽  
Amit Agarwala ◽  
Anthony J. Petrella
Keyword(s):  
Statistical Shape Model ◽  
Single Subject ◽  
Shape Variation ◽  
Shape Model ◽  
Probabilistic Simulation ◽  
Motion Segment ◽  
Biomechanical Simulation ◽  
Statistical Shape ◽  
Probabilistic Study ◽  
Lumbar Motion

Finite element modeling of the lumbar spine has advanced significantly in the last decade [1] and become a relatively well established method for examining fundamental biomechanics as well as new spinal implants and procedures. However, most of these models only represent a single subject and do not account for normal subject-to-subject variation. This limitation can be addressed using a probabilistic simulation in which virtual specimens are used to represent a broad population of subjects. The greatest challenge to implementing probabilistic techniques in biomechanical simulation is parameterization of anatomy to capture normal variation across subjects. In the present study, shape variation was captured using a statistical shape model (SSM) and implemented in a probabilistic framework to evaluate biomechanics of a single motion segment. The Monte Carlo (MC) method is a common probabilistic simulation technique that is robust even for non-monotonic or highly non-linear systems. The purpose of this study was to perform a probabilistic study of a lumbar motion segment using MC simulation to determine the sensitivity of spinal rotations to changes in geometry and soft tissue material properties.

scholarly journals A Multi-atlas Approach for the Automatic Segmentation of Multiple Structures in Head and Neck CT Images

2016 ◽  
Author(s):  
Antong Chen ◽  
Benoit Dawant
Keyword(s):  
Head And Neck ◽  
Local Level ◽  
Automatic Segmentation ◽  
Ct Images ◽  
Training Dataset ◽  
Parotid Glands ◽  
Label Fusion ◽  
Qualitative And Quantitative ◽  
Segmentation Accuracy ◽  
Multiple Structures

A multi-atlas approach is proposed for the automatic segmentation of nine different structures in a set of head and neck CT images for radiotherapy. The approach takes advantage of a training dataset of 25 images to build average head and neck atlases of high-quality. By registering patient images with the atlases at the global level, structures of interest are aligned approximately in space, which allowed multi-atlas-based segmentations and correlation-based label fusion to be performed at the local level in the following steps. Qualitative and quantitative evaluations are performed on a set of 15 testing images. As shown by the results, mandible, brainstem and parotid glands are segmented accurately (mean volume DSC>0.8). The segmentation accuracy for the optic nerves is also improved over previously reported results (mean DSC above 0.61 compared with 0.52 for previous results).

Automatic segmentation of mandibular canal in cone beam CT images using conditional statistical shape model and fast marching

2016 ◽  
Vol 12 (4) ◽  
pp. 581-593 ◽  
Author(s):  
Fatemeh Abdolali ◽  
Reza Aghaeizadeh Zoroofi ◽  
Maryam Abdolali ◽  
Futoshi Yokota ◽  
Yoshito Otake ◽  
...  
Keyword(s):  
Cone Beam Ct ◽  
Automatic Segmentation ◽  
Mandibular Canal ◽  
Ct Images ◽  
Statistical Shape Model ◽  
Cone Beam ◽  
Fast Marching ◽  
Shape Model ◽  
Statistical Shape

Automatic segmentation of the fetal cerebellum on ultrasound volumes, using a 3D statistical shape model

2013 ◽  
Vol 51 (9) ◽  
pp. 1021-1030 ◽  
Author(s):  
Benjamín Gutiérrez-Becker ◽  
Fernando Arámbula Cosío ◽  
Mario E. Guzmán Huerta ◽  
Jesús Andrés Benavides-Serralde ◽  
Lisbeth Camargo-Marín ◽  
...  
Keyword(s):  
Automatic Segmentation ◽  
Statistical Shape Model ◽  
Shape Model ◽  
Statistical Shape
Sign in / Sign up

Export Citation Format

Share Document