Title: A Generic Framework for Vessel Tree Segmentation. Introducing High-Level Physiological Knowledge into the Segmentation Process (Een algemeen raamwerk voor de segmentatie van bloedvatenbomen. De introductie van hoog-niveau fysiologische kennis in het segmentatieproces)
Other Titles: A Generic Framework for Vessel Tree Segmentation. Introducing High-Level Physiological Knowledge into the Segmentation Process
Authors: Bruyninckx, Pieter
Issue Date: 8-Apr-2011
Abstract: IntroductionMultiple organs in the human body feature vascular trees; by the aid of imaging techniques such as CT and MR, they can be visualised in 3D. The segmentation of these structures can benefit many applications ultimately leading to better diagnosis and treatment, such as navigation within the organ, which allows to retrieve a certain pathology on another image or during surgery, or the careful removal of a part of the organ that is perfused by a single vessel tree. The statistical analysis of the segmented tree might also lead towards an automated analysis and novel insights. However, manual segmentation of these structures is tedious and time-consuming, hence there is a need for automated segmentation.A variety of methods to segment vascular structures has been proposed. However, none of these methods explicitly look for a plausible vessel tree structure.This work is the first to present a framework for the segmentation of tree-like structures that includes high-level knowledge, such as Murray's physiological model, which is presented below, into the segmentation process. ModelIn homogeneous organs, such as the liver and the lungs, the vasculature shows certain regularities, e.g. it constitutes a fractal-like tree shape and features certain relations between the radii and angles in a bifurcation. In 1926 Murray was able to explain these characteristics by applying the principle of minimum work, which postulates that biological systems have evolved to be the most efficient, onto the flow of blood vessels. Using the principles of fluid dynamics, he deduced a set of mathematical equations describing the properties of the vasculature: the cube of the radius of a vessel segment is proportional to the flow, and the total blood volume is minimal while still perfusing the entire organ.The combination of these principles with a homogeneous organ in which the tree structure can develop freely, yields the mentioned fractal-like tree structure.The physiological model is complemented by an intensity model. The intensity model assumes a constant intensity distribution for the vasculature and for the surrounding tissue. Additionally it approximates the intensities in a CT scan by including partial volume effects, a point spread function, and spatially correlated noise. MethodThe proposed framework for vessel tree segmentation uses a bottom-up approach while incorporating high level knowledge, i.e. the vessel tree model that was described in the previous section. The method looks for a vascular tree structure that fits the image while (virtually) perfusing the organ with minimal work. It consists of three consecutive steps. First, a large set of candidate bifurcation locations is determined. Subsequently, individual vessel segments of varying diameter are constructed between each two candidate bifurcation locations. This way, a graph is constructed consisting of the candidate bifurcation location as nodes and the candidate vessel segments as edges. Finally,an overall vessel tree is found by selecting the subset of these segments and nodes that perfuses the whole organ, while trying to minimise an objective function containing a data term, and physiology-based volume and flow terms. The data term, based upon the intensity model, measures how well the detected vessel tree fits to the image, the volume term measures the total amount of blood in the vasculature, and the flow term measures the compliance of the segments' radii with their estimated flow. The selection of the optimal subset of vessel segments into a single vessel tree is an NP-hard combinatorial optimization problem, which is approximated with an approach inspired by ant colony optimisation. ValidationThe algorithm has been validated on artificial 2D images mimicking liver CT scans, and clinical 3D liver CT scans. For the artificial images there was a significant p<1e-5) improvement when the physiological terms were included in a topologically corrected Dice coefficient, which measures the overlap while taking the topology into account, thus illustrating the beneficial effect of the included physiological model. Regarding the clinical images the validation showed that the proposed methods yields results(Dice overlap from 0.41 to 0.71 without physiological terms and from 0.5 to 0.7 with physiological terms) that are similar to those of the state of the art, and that the inclusion of the physiological tree model increases the robustness of the segmentation algorithm. ConclusionThis thesis proposes a novel bottom-up vessel tree segmentation framework that uses high-level knowledge, i.e. Murray's physiological model. The proposed method is the first to include such high-level tree knowledge at the heart of the segmentation method. The method has been validated, showing that the results are comparable to the state of the art, and that the inclusion of the physiological model improves the robustness. This way, we hope we have opened the way towards image analysis applications incorporating advanced knowledge about the vessel tree.
Description: Bruyninckx P., ''A generic framework for vessel tree segmentation. Introducing high-level physiological knowledge into the segmentation process'', Proefschrift voorgedragen tot het behalen van het doctoraat in de ingenieurswetenschappen, K.U.Leuven, April 2011, Leuven, Belgium.
Table of Contents: 1 Introduction
1.1 Introduction
1.2 Context
1.2.1 History
1.2.2 Cardiovascular System
1.2.3 Imaging Modalities
1.2.4 Common Pathologies and Interesting Features
Vessels an sich
3D Vessel Trees in Homogeneous Organs: Lung and Liver
2D Vessel Trees: Retina
1.3 Computer Aided Segmentation
1.3.1 Need for (Automated) Segmentation
1.3.2 State of the Art
Vessel Filters
Path-finding Methods
Minimum Cost Path
Region Growing, Front Propagation, and Level sets
Global Methods
Voxel-based Approach
Symbolic Approach
1.4 Proposed Method
1.5 Contribution to the Field
2 Model
2.1 Introduction
2.2 Physiological Model
2.2.1 Historical Introduction
2.2.2 Derivation
2.2.3 From Bifurcations through Fractals to Trees
2.2.4 Application Domain
2.2.5 Validation
2.2.6 Extensions
2.2.7 Applications
2.3 Vessel Intensity Model
2.4 Conclusion
3 Method
3.1 Introduction
3.2 Motivation
3.3 Overview
3.4 Vessel Potential
3.5 Candidate Bifurcation Locations
3.6 Candidate Vessel Segments
3.7 Solution Constraints
3.8 Cost Function
3.9 Optimisation
3.10 Conclusion
4 Validation
4.1 Introduction
4.2 Validation Data
4.3 Vessel Potential
4.3.1 Artificial Images
4.3.2 Clinical Images
4.3.3 Discussion
4.4 Candidate Bifurcation Locations
4.4.1 Artificial Images
4.4.2 Clinical Images
4.4.3 Discussion
4.5 Candidate Vessel Segments
4.5.1 Artificial Images
4.5.2 Clinical Images
4.5.3 Discussion
4.6 Vessel Tree Segmentation
4.6.1 Artificial Images
4.6.2 Clinical Images
4.6.3 Comparison with Heuristic Methods
4.6.4 Discussion
4.7 Conclusion
5 Discussion
5.1 Discussion
5.2 Afterthought
5.2.1 General Approach
5.2.2 Vessel Potential
5.2.3 Cost Function
5.2.4 Optimisation
6 Future Work
6.1 Introduction
6.2 Algorithm Improvements
6.2.1 Vessel Potential
6.2.2 Candidate Bifurcation Locations
6.2.3 Candidate Vessel Segments
6.2.4 Vessel Tree Segmentation
6.3 Alternative Vessel Configurations
6.3.1 Multiple Trees
6.3.2 Trees in Non-homogeneous Organs
6.3.3 Networks
6.4 Introducing Feedback Loops
6.5 Algorithm Applications
6.5.1 Labelling of Liver Segments & Lung Lobes
6.5.2 Basic Statistics
6.5.3 Registration
6.5.4 Atlas and Anatomical Labelling
6.5.5 Analysis and Diagnosis
ISBN: 978-94-6018-339-3
Publication status: published
KU Leuven publication type: TH
Appears in Collections:ESAT - PSI, Processing Speech and Images

Files in This Item:
File Status SizeFormat
thesis.pdf Published 32279KbAdobe PDFView/Open Request a copy

These files are only available to some KU Leuven Association staff members


All items in Lirias are protected by copyright, with all rights reserved.