Deformable meshes for medical image segmentation accurate automatic segmentation of anatomical structures Dagmar Kainmueller

Format:

Book

Author/Creator:

Kainmueller, Dagmar, author.

Series:

Aktuelle Forschung Medizintechnik

Language:

English

Subjects (All):

Image segmentation.

Diagnostic imaging--Digital techniques.

Diagnostic imaging.

Computer vision.

Diagnostic Imaging.

nomeshx.

Medical Subjects:

Diagnostic Imaging.

nomeshx.

Physical Description:

1 online resource

illustration

polychrome

Place of Publication:

Wiesbaden Springer Vieweg [2014]

System Details:

Mode of access: World Wide Web.

text file

Summary:

? Segmentation of anatomical structures in medical image data is an essential task in clinical practice. Dagmar Kainmueller introduces methods for accurate fully automatic segmentation of anatomical structures in 3D medical image data. The author's core methodological contribution is a novel deformation model that overcomes limitations of state-of-the-art Deformable Surface approaches, hence allowing for accurate segmentation of tip- and ridge-shaped features of anatomical structures. As for practical contributions, she proposes application-specific segmentation pipelines for a range of anatom

Contents:

Preface by the Series Editor; Foreword; Acknowledgments; Abstract; Contents; Chapter 1 Introduction; 1.1 Motivation; 1.1.1 Segmentation of Medical Image Data; 1.1.2 Automation of the Segmentation Task; 1.1.3 Segmentation Accuracy; 1.2 Scope of this Thesis; 1.2.1 Automated Segmentation with Deformable Models; 1.2.2 Selection of Anatomical Structures and Imaging Modalities; 1.2.3 Contribution; 1.2.4 Topics Not Discussed; 1.3 Structure of this Thesis; Part I The Segmentation Framework; Chapter 2 Basic Terms and Notation; 2.1 Images, Segmentations, and Surface Meshes

2.1.1 Three-dimensional Medical Images2.1.2 Segmentations of Three-dimensional Medical Images; 2.1.3 Triangle Surface Meshes; 2.1.4 From Segmentations to Surface Meshes and Back; 2.2 Deformable Surface Meshes; 2.2.1 Displacement Fields and Sets of Candidate Displacements; 2.2.2 Appearance Cost; Chapter 3 Deformable Meshes for Automatic Segmentation; 3.1 Statistical Shape Models (SSMs) for Segmentation; 3.1.1 Generation of SSMs; 3.1.2 Prerequisites: Shape Correspondences and Alignment; 3.1.3 Image Segmentation via SSM Deformation; 3.1.4 Initial Shape Detection

3.1.5 Lack of Image Features: SSMs for Extrapolation3.2 A Simple Heuristic Appearance Model; 3.2.1 Appearance Cost Function; 3.2.2 Intensity Parameter Estimation; 3.3 Local Search for Appearance Match; 3.3.1 Unidirectional Displacements; 3.3.2 Optimal Displacement Fields; 3.3.3 Intensity Profiles; 3.4 Shape-constrained Free Mesh Deformations; 3.4.1 Free Deformation within a Narrow Band; 3.4.2 Free Deformation with Bounded Displacement Differences; 3.5 Simultaneous Free Deformations of Multiple Meshes; 3.5.1 Multi-object Graph-based Deformation of Coupled Meshes

3.5.2 Coupling Adjacent Surface Meshes3.6 Conclusion; Chapter 4 Omnidirectional Displacements for Deformable Surfaces (ODDS); 4.1 The Visibility Problem; 4.2 ODDS: Free Mesh Deformations with All-around Visibility; 4.2.1 Omnidirectional Displacements; 4.2.2 The Mesh Deformation Problem; 4.2.3 Optimal Mesh Deformation via MRF Energy Minimization; 4.2.4 Refined Regularization; 4.2.5 Proof of Concept Synthetic Experiments; 4.3 FastODDS; 4.3.1 Where to use Omnidirectional Displacements; 4.3.2 The Hybrid Mesh Deformation Problem; 4.3.3 Optimal Hybrid Mesh Deformation; 4.3.4 Multi-object FastODDS

4.3.5 Appendix: Automatic Ridge Detection4.4 Conclusion; Chapter 5 From Surface Mesh Deformations to Volume Deformations; 5.1 Mesh-based Extrapolation; 5.1.1 Introduction; 5.1.2 Affine Transformations; 5.1.3 Polyaffine Transformations; 5.1.4 Mean Value Coordinates; 5.2 Atlas-based Segmentation; 5.2.1 Image-to-image Registration; 5.2.2 Application of Volume Deformations to Atlases; 5.3 Conclusion; Part IIApplications to Medical Image Data; Chapter 6 Fundamentals of Quantitative Evaluation; 6.1 Measures of Segmentation Accuracy; 6.2 Presentation of Results; 6.3 Comparison of Methods

Notes:

"Dissertation University of Lübeck, 2013"

Includes bibliographical references

Online resource; title from PDF title page (SpringerLink, viewed September 3, 2014)

Other Format:

Print version Kainmueller, Dagmar. Deformable Meshes for Medical Image Segmentation : Accurate Automatic Segmentation of Anatomical Structures

ISBN:

9783658070151

3658070153

3658070145

9783658070144

OCLC:

889865112

Access Restriction:

Restricted for use by site license