Curvilinear structure analysis is the foundation of a wide range of applications, for instance image enhancement, centerline detection, vascular segmentation and surface reconstruction. Specifically in medical imaging, the appearance, morphology and topology of curvilinear objects are important indicators of many vascular disease and systemic disorders. As such, the analysis of curvilinear structure is valuable for pathology quantification, disease diagnosis and surgery planning.

In this thesis, we first review the existing techniques for curvilinear structure analysis. The descriptor - conventional Optimally Oriented Flux (OOF) is then introduced and enhanced for three dimensional curvilinear structure analysis, namely inter-scale OOF analysis. OOF attempts to find an optim...[ Read more ]

Curvilinear structure analysis is the foundation of a wide range of applications, for instance image enhancement, centerline detection, vascular segmentation and surface reconstruction. Specifically in medical imaging, the appearance, morphology and topology of curvilinear objects are important indicators of many vascular disease and systemic disorders. As such, the analysis of curvilinear structure is valuable for pathology quantification, disease diagnosis and surgery planning.

In this thesis, we first review the existing techniques for curvilinear structure analysis. The descriptor - conventional Optimally Oriented Flux (OOF) is then introduced and enhanced for three dimensional curvilinear structure analysis, namely inter-scale OOF analysis. OOF attempts to find an optimal axis along which the image gradients are projected prior to quantifying the amount of gradient flows. To solve the overshooting problem in conventional OOF, in the proposed method, responses obtained in different radii are competed to eliminate the disturbances introduced from the nearby non-curvilinear structures. The performance of conventional OOF also suffers from the circular cross-sectional assumption. Therefore, we propose to acquire the residual responses separately along the object normal and tangent spaces in order to benefit the analysis of eccentric structures. Further, local orientation coherence is enforced to generated a more consistent OOF vector field. With the inter-scale OOF analysis, three important characteristics of curvilinear structure can be estimated simultaneously: curvilinearity, dimension and orientation. We experimentally demonstrate that the new descriptor delivers more accurate and stable detection responses under the interference of adjacent high-contrast structures and exhibits extraordinary noise robustness.

Vascular segmentation is one important application of curvilinear structure analysis. In order to evaluate the capability of inter-scale OOF and to reversely facilitate the curvilinear structure analysis in the understanding of vasculatures, we then propose to feed it into two existing general segmentation frameworks, which are Random Walks and Continuous Max-Flow, for three dimensional vascular segmentation. The proposed methods have been evaluated on public available databases and comparable segmenting results have been achieved.