Adaptive Segmentation of Multi-modal 3D Data Using Robust Level Set Techniques

Farag, Aly A.; Hassan, Hossam S.

doi:10.1007/978-3-540-30135-6_18

Cited by 19 publications

(30 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic seed initialization is used based on the region parameters estimated by the SEM. A similar approach to that in [10] but the contour seeds are decided based on the Bayesian decision rule. The contour evolves and reaches the steady state to mark the object region boundaries.…”

Section: Resultsmentioning

confidence: 99%

“…We characterize each region by a Gaussian distribution with adaptive parameters. Expressions for the prior probability and the Gaussian parameters are found in [10].…”

Section: Level Sets and Intensity Segmentationmentioning

confidence: 99%

“…where δ ε is added to reduce the complexity of the problem as shown in [10] where ε is the width parameter of the band around the shape contour. It is straightforward to show that the given measure r satisfies the relation: r ≤ (sφ α (X) − φ β (A)) where s = max(s x , s y ).…”

Section: Dissimilarity Measure and Energy Functionmentioning

confidence: 99%

“…Then we will obtain identical optimization parameters for both E 1 and E. Gradient descent is used to handle the optimization to estimate the transformation parameters. [10]) is used to get a smooth transition around the line s x = s y and hence the function is differentiable everywhere. The function derivatives will be directly calculated as follows …”

Section: Dissimilarity Measure and Energy Functionmentioning

confidence: 99%

See 3 more Smart Citations

A kidney segmentation approach from DCE-MRI using level sets

Abdelmunim

Farag

Miller

et al. 2008

2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

“…We characterize each region by a Gaussian distribution with adaptive parameters. Expressions for the prior probability and the Gaussian parameters are found in [10].…”

Section: Level Sets and Intensity Segmentationmentioning

confidence: 99%

Section: Dissimilarity Measure and Energy Functionmentioning

confidence: 99%

Section: Dissimilarity Measure and Energy Functionmentioning

confidence: 99%

See 2 more Smart Citations

A kidney segmentation approach from DCE-MRI using level sets

Abdelmunim

Farag

Miller

et al. 2008

2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

show abstract

“…Traditional approaches such as thresholding [19][20][21][22] using only the gray level information will not work to solve the noise problem. Edge-and-contour based variational methods [10,11,[23][24][25] and spatially discrete optimization methods [26][27][28][29] using only the existing information (intensity and/ or spatial interaction) may work well to solve the noise problem. However, these methods will not be able to obtain desired segmentation when there is occlusion problem in the image.…”

Section: Minimizing -Log P(l Lflmentioning

confidence: 99%

Probabilistic and geometric shape based segmentation methods.

Aslan¹

View full text Add to dashboard Cite

Aslan, Melih Seref, "Probabilistic and geometric shape based segmentation methods." (2012 Image segmentation is one of the most important problems in image processing, object recognition, computer vision, medical imaging, etc. In general, the objective of the segmentation is to partition the image into the meaningful areas using the existing (low level) information in the image and prior (high level) information which can be obtained using a number of features of an object. As stated in [1,2], the human vision system aims to extract and use as much information as possible in the image including but not limited to the intensity, possible motion of the object (in sequential images), spatial relations (interaction) as the existing information, and the shape of the object which is learnt from the experience as the prior information. The main objective of this dissertation is to couple the prior information with the existing information since the machine vision system cannot predict the prior information unless it is given.To label the image into meaningful areas, the chosen information is modelled to fit progressively in each of the regions by an optimization process. The intensity and spatial interaction (as the existing information) and shape (as the prior information) are modelled to obtain the optimum segmentation in this study.The intensity information is modelled using the Gaussian distribution. Spatial inv teraction that describes the relation between neighboring pixels/voxels is modeled by assuming that the pixel intensity depends on the intensities of the neighboring pixels. The shape model is obtained using occurrences of histogram of training shape pixels or voxels. The main objective is to capture the shape variation of the object of interest. Each pixel in the image will have three probabilities to be an object and a background class based on the intensity, spatial interaction, and shape models. These probabilistic values will guide the energy (cost) functionals in the optimization process.This dissertation proposes segmentation frameworks which has the following properties: i) original to solve some of the existing problems, ii) robust under various segmentation challenges, and iii) fast enough to be used in the real applications. In this dissertation, the models are integrated into different methods to obtain the optimum segmentation: 1) variational (can be considered as the spatially continuous), and 2) statistical (can be considered as the spatially discrete) methods.The proposed segmentation frameworks start with obtaining the initial segmentation using the intensity / spatial interaction models. The shape model, which is obtained using the training shapes, is registered to the image domain. Finally, the optimal segmentation is obtained using the optimization of the energy functionals. Experiments show that the use of the shape prior improves considerably the accuracy of the alternative methods which use only existing or both information in the image. The proposed methods are tested on the syntheti...

show abstract

Validation Framework of the Finite Element Modeling of Liver Tissue

Shi

Fahmi

Farag

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this work, we aim at validating some soft tissue deformation models using high resolution Micro Computed Tomography (Micro-CT) and medium resolution Cone-Beam CT (CBCT) images. These imaging techniques play a key role in detecting the tissue deformation details in the contact region between the tissue and the surgical tool (probe) even for small force loads, and provide good capabilities for creating accurate 3D models of tissues. Surgical simulations rely on accurate representation of the mechanical response of soft tissues subjected to surgical manipulations. Several finite element (F.E.) models have been suggested to characterize soft tissues. However, validating these models for specific tissues still remains a challenge. For our validation, ex vivo lamb liver is chosen to validate the linear elastic model (LEM), the linear viscoelastic model (LVEM), and the neo-Hooke hyperelastic model (NHM). We found that the LEM is more applicable to lamb liver than the LVEM for small force loads (< 40g) and that the NHM is closer to reality than the LVEM for this same range of force loads.

show abstract

Adaptive Segmentation of Multi-modal 3D Data Using Robust Level Set Techniques

Cited by 19 publications

References 18 publications

A kidney segmentation approach from DCE-MRI using level sets

A kidney segmentation approach from DCE-MRI using level sets

Probabilistic and geometric shape based segmentation methods.

Validation Framework of the Finite Element Modeling of Liver Tissue

Contact Info

Product

Resources

About