Curvilinear Structure Analysis by Ranking the Orientation Responses of Path Operators

The analysis of thin curvilinear objects in 3D images is a complex and challenging task. In this article, we introduce a new, non-linear operator, called RORPO (Ranking the Orientation Responses of Path Operators). Inspired by the multidirectional paradigm currently used in linear filtering for thin structure analysis, RORPO is built upon the notion of path operator from mathematical morphology. This operator, unlike most operators commonly used for 3D curvilinear structure analysis, is discrete, non-linear and non-local. From this new operator, two main curvilinear structure characteristics can be estimated: an intensity feature, that can be assimilated to a quantitative measure of curvilinearity; and a directional feature, providing a quantitative measure of the structure's orientation. We provide a full description of the structural and algorithmic details for computing these two features from RORPO, and we discuss computational issues. We experimentally assess RORPO by comparison with three of the most popular curvilinear structure analysis filters, namely Frangi Vesselness, Optimally Oriented Flux, and Hybrid Diffusion with Continuous Switch. In particular, we show that our method provides up to 8 percent more true positive and 50 percent less false positives than the next best method, on synthetic and real 3D images.

[1]  Isabelle E. Magnin,et al.  Advances of blood vessel morphology analysis in 3D magnetic resonance images , 2000 .

[2]  Odyssée Merveille,et al.  RORPO: A morphological framework for curvilinear structure analysis. Application to the filtering and segmentation of blood vessels. (RORPO: Une méthode morphologique pour l'analyse des structures curvilignes; Application au filtrage et à la segmentation de vaisseaux sanguins) , 2016 .

[3]  Max A. Viergever,et al.  Vessel enhancing diffusion: A scale space representation of vessel structures , 2006, Medical Image Anal..

[4]  Charles A. Taylor,et al.  Computational fluid dynamics applied to cardiac computed tomography for noninvasive quantification of fractional flow reserve: scientific basis. , 2013, Journal of the American College of Cardiology.

[5]  J. Bigun,et al.  Optimal Orientation Detection of Linear Symmetry , 1987, ICCV 1987.

[6]  Hugues Talbot,et al.  Curvilinear Structure Enhancement with the Polygonal Path Image - Application to Guide-Wire Segmentation in X-Ray Fluoroscopy , 2012, MICCAI.

[7]  Pierre Soille,et al.  Recursive Implementation of Erosions and Dilations Along Discrete Lines at Arbitrary Angles , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Jürgen Weese,et al.  Multi-scale line segmentation with automatic estimation of width, contrast and tangential direction in 2D and 3D medical images , 1997, CVRMed.

[9]  Hugues Talbot,et al.  Ranking Orientation Responses of Path Operators: Motivations, Choices and Algorithmics , 2015, ISMM.

[10]  Jocelyn Chanussot,et al.  Efficient Robust d-Dimensional Path Operators , 2012, IEEE Journal of Selected Topics in Signal Processing.

[11]  D. Parker,et al.  Vessel enhancement filtering in three‐dimensional MR angiography , 1995, Journal of magnetic resonance imaging : JMRI.

[12]  Frédéric Zana,et al.  Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation , 2001, IEEE Trans. Image Process..

[13]  Michael H. F. Wilkinson.  Hyperconnectivity, Attribute-Space Connectivity and Path Openings: Theoretical Relationships , 2009, ISMM.

[14]  Max A. Viergever,et al.  Noise Reduction in Computed Tomography Scans Using 3-D Anisotropic Hybrid Diffusion With Continuous Switch , 2009, IEEE Transactions on Medical Imaging.

[15]  Jean Stawiaski.  Optimal Path: Theory and Models for Vessel Segmentation , 2011, ISMM.

[16]  Luc Vincent,et al.  Minimal path algorithms for the robust detection of linear features in gray images , 1998 .

[17]  Brian E. Chapman,et al.  3D multi-scale vessel enhancement filtering based on curvature measurements: application to time-of-flight MRA , 2005, Medical Image Anal..

[18]  Hugues Talbot,et al.  Flexible Linear Openings and Closings , 2000, ISMM.

[19]  Dominique Jeulin,et al.  3-D Extraction of Fibres from Microtomographic Images of Fibre-Reinforced Composite Materials , 2009, ISMM.

[20]  Örjan Smedby,et al.  Gradient-based enhancement of tubular structures in medical images , 2015, Medical Image Anal..

[21]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Brett D. Thackray,et al.  Semi-automatic segmentation of vascular network images using a rotating structuring element (ROSE) with mathematical morphology and dual feature thresholding , 1993, IEEE Trans. Medical Imaging.

[23]  Michael H. F. Wilkinson,et al.  Mask-Based Second-Generation Connectivity and Attribute Filters , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Joachim Weickert,et al.  Anisotropic diffusion in image processing , 1996 .

[25]  Hugues Talbot,et al.  A variational model for thin structure segmentation based on a directional regularization , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[26]  Max W. K. Law,et al.  Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux , 2008, ECCV.

[27]  Bart M. ter Haar Romeny,et al.  A Novel 3D Multi-scale Lineness Filter for Vessel Detection , 2007, MICCAI.

[28]  Ghassan Hamarneh,et al.  VascuSynth: Simulating vascular trees for generating volumetric image data with ground-truth segmentation and tree analysis , 2010, Comput. Medical Imaging Graph..

[29]  Hugues Talbot,et al.  Tubular Structure Filtering by Ranking Orientation Responses of Path Operators , 2014, ECCV.

[30]  Guido Gerig,et al.  3D Multi-scale line filter for segmentation and visualization of curvilinear structures in medical images , 1997, CVRMed.

[31]  L. Cohen,et al.  Segmentation of 3D tubular objects with adaptive front propagation and minimal tree extraction for 3D medical imaging , 2007, Computer methods in biomechanics and biomedical engineering.

[32]  Nicolas Passat,et al.  Magnetic resonance angiography: From anatomical knowledge modeling to vessel segmentation , 2006, Medical Image Anal..

[33]  Hugues Talbot,et al.  Filtering and segmentation of 3D angiographic data: Advances based on mathematical morphology , 2013, Medical Image Anal..

[34]  Hugues Talbot,et al.  Path Openings and Closings , 2005, Journal of Mathematical Imaging and Vision.

[35]  Etienne Decencière,et al.  Efficient Geodesic Attribute Thinnings Based on the Barycentric Diameter , 2012, Journal of Mathematical Imaging and Vision.

[36]  Martin Styner,et al.  Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms , 2009, Medical Image Anal..

[37]  Nicolas Passat,et al.  Grey-level hit-or-miss transforms - part II: Application to angiographic image processing , 2007, Pattern Recognit..

[38]  Laurent D. Cohen,et al.  Geodesic voting for the automatic extraction of tree structures. Methods and applications , 2013, Comput. Vis. Image Underst..

[39]  Johan H. C. Reiber,et al.  A strain energy filter for 3D vessel enhancement with application to pulmonary CT images , 2011, Medical Image Anal..

[40]  Isabelle Bloch,et al.  A review of 3D vessel lumen segmentation techniques: Models, features and extraction schemes , 2009, Medical Image Anal..

[41]  Guido Gerig,et al.  Multiscale detection of curvilinear structures in 2-D and 3-D image data , 1995, Proceedings of IEEE International Conference on Computer Vision.

[42]  Philippe Salembier,et al.  Antiextensive connected operators for image and sequence processing , 1998, IEEE Trans. Image Process..

[43]  Michael H. F. Wilkinson,et al.  Shape Preserving Filament Enhancement Filtering , 2001, MICCAI.

[44]  Pascal Fua,et al.  Steerable Features for Statistical 3D Dendrite Detection , 2009, MICCAI.

[45]  Hugues Talbot,et al.  Curvilinear morpho-Hessian filter , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[46]  Yaonan Wang,et al.  Multiscale Bi-Gaussian Filter for Adjacent Curvilinear Structures Detection With Application to Vasculature Images , 2013, IEEE Transactions on Image Processing.

[47]  Qingfen Lin,et al.  Efficient Detection of Second-Degree Variations in 2D and 3D Images , 2001, J. Vis. Commun. Image Represent..

[48]  B. Burgeth,et al.  Determination of the fibre orientation in composites using the structure tensor and local X-ray transform , 2010 .

[49]  Hugues Talbot,et al.  Directional Morphological Filtering , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[50]  Etienne Decencière,et al.  Parsimonious Path Openings and Closings , 2014, IEEE Transactions on Image Processing.

[51]  Nicolas Passat,et al.  3D segmentation of coronary arteries based on advanced mathematical morphology techniques , 2010, Comput. Medical Imaging Graph..

[52]  Hugues Talbot,et al.  Mathematical Morphology: from theory to applications , 2013 .

[53]  Nicholas Ayache,et al.  Model-Based Detection of Tubular Structures in 3D Images , 2000, Comput. Vis. Image Underst..

[54]  Konstantinos G. Derpanis,et al.  Three-dimensional nth derivative of Gaussian separable steerable filters , 2005, IEEE International Conference on Image Processing 2005.

[55]  Horst Bischof,et al.  A Novel Approach for Detection of Tubular Objects and Its Application to Medical Image Analysis , 2008, DAGM-Symposium.

[56]  Hugues Talbot,et al.  Efficient complete and incomplete path openings and closings , 2007, Image Vis. Comput..

[57]  Hugues Talbot,et al.  Spatially-Variant Morpho-Hessian Filter: Efficient Implementation and Application , 2009, ISMM.

[58]  Yongchao Xu,et al.  Two Applications of Shape-Based Morphology: Blood Vessels Segmentation and a Generalization of Constrained Connectivity , 2013, ISMM.

[59]  Hugues Talbot,et al.  Directed Connected Operators: Asymmetric Hierarchies for Image Filtering and Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[60]  Cris L. Luengo Hendriks,et al.  Constrained and Dimensionality-Independent Path Openings , 2010, IEEE Transactions on Image Processing.

[61]  Nicolas Passat,et al.  Segmentation of Complex Images Based on Component-Trees: Methodological Tools , 2009, ISMM.

[62]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.