Immunological Approach for Full NURBS Reconstruction of Outline Curves from Noisy Data Points in Medical Imaging

Curve reconstruction from data points is an important issue for advanced medical imaging techniques, such as computer tomography (CT) and magnetic resonance imaging (MRI). The most powerful fitting functions for this purpose are the NURBS (non-uniform rational B-splines). Solving the general reconstruction problem with NURBS requires computing all free variables of the problem (data parameters, breakpoints, control points, and their weights). This leads to a very difficult non-convex, nonlinear, high-dimensional, multimodal, and continuous optimization problem. Previous methods simplify the problem by guessing the values for some variables and computing only the remaining ones. As a result, unavoidable approximations errors are introduced. In this paper, we describe the first method in the literature to solve the full NURBS curve reconstruction problem in all its generality. Our method is based on a combination of two techniques: an immunological approach to perform data parameterization, breakpoint placement, and weight calculation, and least squares minimization to compute the control points. This procedure is repeated iteratively (until no further improvement is achieved) for higher accuracy. The method has been applied to reconstruct some outline curves from MRI brain images with satisfactory results. Comparative work shows that our method outperforms the previous related approaches in the literature for all instances in our benchmark.

[1]  Yue Hong Sun,et al.  B-Spline Curve Fitting Based on Adaptive Particle Swarm Optimization Algorithm , 2010 .

[2]  Andrés Iglesias,et al.  Efficient particle swarm optimization approach for data fitting with free knot B-splines , 2011, Comput. Aided Des..

[3]  Gang Zhao,et al.  Adaptive knot placement in B-spline curve approximation , 2005, Comput. Aided Des..

[4]  Michel Bercovier,et al.  Spline Curve Approximation and Design by Optimal Control Over the Knots , 2004, Computing.

[5]  Ling Jing,et al.  Fitting B-spline curves by least squares support vector machines , 2005, 2005 International Conference on Neural Networks and Brain.

[6]  Andrés Iglesias,et al.  Functional networks for B-spline surface reconstruction , 2004, Future Gener. Comput. Syst..

[7]  Janez Brest,et al.  A Brief Review of Nature-Inspired Algorithms for Optimization , 2013, ArXiv.

[8]  Alan S. Perelson,et al.  Self-nonself discrimination in a computer , 1994, Proceedings of 1994 IEEE Computer Society Symposium on Research in Security and Privacy.

[9]  Anath Fischer,et al.  Parameterization and Reconstruction from 3D Scattered Points Based on Neural Network and PDE Techniques , 2001, IEEE Trans. Vis. Comput. Graph..

[10]  Andrés Iglesias,et al.  Hybridizing mesh adaptive search algorithm and artificial immune systems for discrete rational Bézier curve approximation , 2015, The Visual Computer.

[11]  Toshinobu Harada,et al.  Automatic knot placement by a genetic algorithm for data fitting with a spline , 1999, Proceedings Shape Modeling International '99. International Conference on Shape Modeling and Applications.

[12]  Dipankar Dasgupta,et al.  Immunological Computation: Theory and Applications , 2008 .

[13]  Ralph R. Martin,et al.  Reverse engineering of geometric models - an introduction , 1997, Comput. Aided Des..

[14]  Xin-She Yang,et al.  Nature-Inspired Metaheuristic Algorithms , 2008 .

[15]  Gerald Farin,et al.  Curves and surfaces for cagd , 1992 .

[16]  Hyungjun Park,et al.  An error-bounded approximate method for representing planar curves in B-splines , 2004, Comput. Aided Geom. Des..

[17]  Andrés Iglesias,et al.  A new iterative mutually coupled hybrid GA-PSO approach for curve fitting in manufacturing , 2013, Appl. Soft Comput..

[18]  Jerne Nk.  Towards a network theory of the immune system. , 1974 .

[19]  Leandro Nunes de Castro,et al.  Artificial Immune Systems: Part I-Basic Theory and Applications , 1999 .

[20]  Jonathan Timmis,et al.  Application areas of AIS: The past, the present and the future , 2008, Appl. Soft Comput..

[21]  Andrés Iglesias,et al.  Particle-based meta-model for continuous breakpoint optimization in smooth local-support curve fitting , 2016, Appl. Math. Comput..

[22]  Helmut Pottmann,et al.  Fitting B-spline curves to point clouds by curvature-based squared distance minimization , 2006, TOGS.

[23]  Andrés Iglesias,et al.  From Nonlinear Optimization to Convex Optimization through Firefly Algorithm and Indirect Approach with Applications to CAD/CAM , 2013, TheScientificWorldJournal.

[24]  Andrés Iglesias,et al.  New memetic self-adaptive firefly algorithm for continuous optimisation , 2016 .

[25]  Muhammad Sarfraz,et al.  Capturing outline of fonts using genetic algorithm and splines , 2001, Proceedings Fifth International Conference on Information Visualisation.

[26]  Ahmet Arslan,et al.  Automatic knot adjustment using an artificial immune system for B-spline curve approximation , 2009, Inf. Sci..

[27]  Toshinobu Harada,et al.  Data fitting with a spline using a real-coded genetic algorithm , 2003, Comput. Aided Des..

[28]  Xue Yan,et al.  Neural network approach to the reconstruction of freeform surfaces for reverse engineering , 1995, Comput. Aided Des..

[29]  Julie Greensmith,et al.  Artificial Dendritic Cells: Multi-faceted Perspectives , 2009, Human-Centric Information Processing Through Granular Modelling.

[30]  Andrés Iglesias,et al.  Particle swarm optimization for non-uniform rational B-spline surface reconstruction from clouds of 3D data points , 2012, Inf. Sci..

[31]  Andrés Iglesias,et al.  Iterative two-step genetic-algorithm-based method for efficient polynomial B-spline surface reconstruction , 2012, Inf. Sci..

[32]  Hyungjun Park,et al.  B-spline curve fitting based on adaptive curve refinement using dominant points , 2007, Comput. Aided Des..

[33]  Nicholas M. Patrikalakis,et al.  Shape Interrogation for Computer Aided Design and Manufacturing , 2002, Springer Berlin Heidelberg.

[34]  Xin-She Yang.  Nature-Inspired Computation in Engineering , 2016, Nature-Inspired Computation in Engineering.

[35]  D. Dasgupta.  Artificial Immune Systems and Their Applications , 1998, Springer Berlin Heidelberg.

[36]  Martin J Murphy,et al.  Optimized knot placement for B-splines in deformable image registration. , 2011, Medical physics.

[37]  Andrés Iglesias,et al.  Elitist clonal selection algorithm for optimal choice of free knots in B-spline data fitting , 2015, Appl. Soft Comput..

[38]  A. Iglesias,et al.  Firefly Algorithm for Explicit B-Spline Curve Fitting to Data Points , 2013 .

[39]  Carl de Boor,et al.  A Practical Guide to Splines , 1978, Applied Mathematical Sciences.

[40]  Miklós Hoffmann.  Numerical control of kohonen neural network for scattered data approximation , 2004, Numerical Algorithms.

[41]  Weiyin Ma,et al.  Parameterization of randomly measured points for least squares fitting of B-spline curves and surfaces , 1995, Comput. Aided Des..

[42]  Fernando José Von Zuben,et al.  Learning and optimization using the clonal selection principle , 2002, IEEE Trans. Evol. Comput..

[43]  D. Jupp.  Approximation to Data by Splines with Free Knots , 1978 .

[44]  F. Azuaje.  Artificial Immune Systems: A New Computational Intelligence Approach , 2003 .

[45]  Jonathan Timmis,et al.  Theoretical advances in artificial immune systems , 2008, Theor. Comput. Sci..

[46]  Robert E. Barnhill,et al.  Geometry Processing for Design and Manufacturing , 1992 .

[47]  Erkan Ülker.  B-Spline Curve Approximation Using Pareto Envelope- Based Selection Algorithm - PESA , 2013 .

[48]  Leandro Nunes de Castro,et al.  The Clonal Selection Algorithm with Engineering Applications 1 , 2000 .

[49]  Paul Dierckx,et al.  Curve and surface fitting with splines , 1994, Monographs on numerical analysis.