Optimizing a Medical Image Analysis System Using Mixed-Integer Evolution Strategies

We will discuss Mixed-Integer Evolution Strategies (MIES) and their application to the optimization of control parameters of a semi-automatic image analysis system for Intravascular Ultrasound (IVUS) images. IVUS is a technique used to obtain real-time high-resolution tomographic images from the inside of coronary vessels and other arteries. The IVUS image feature detectors used in the analysis system are expert-designed and the default parameters are calibrated manually so far. The new approach, based on MIES, can automatically find good parameterizations for sets of images, which provide in better results than manually tuned parameters. From the algorithmic point of view, the difficulty is designing a blackbox optimization strategy that can deal with nonlinear functions and different types of parameters, including integer, nominal discrete and continuous variables. MIES turns out to be well suited for this task. The results presented in this contribution will summarize and extend recent studies on benchmark functions and the IVUS image analysis optimization problem.

[1]  A. Newell.  Unified Theories of Cognition , 1990 .

[2]  Thomas Bäck,et al.  Towards Dynamic Fitness Based Partitioning for IntraVascular UltraSound Image Analysis , 2009, EvoWorkshops.

[3]  K. Furie,et al.  Heart disease and stroke statistics--2008 update: a report from the American Heart Association Statistics Committee and Stroke Statistics Subcommittee. , 2007, Circulation.

[4]  Thomas Bäck,et al.  Evolutionary Algorithms in Theory and Practice , 1996 .

[5]  Michael T. M. Emmerich,et al.  Mixed-integer optimization of coronary vessel image analysis using evolution strategies , 2006, GECCO '06.

[6]  Thomas Bäck,et al.  Optimizing Computed Tomographic Angiography Image Segmentation Using Fitness Based Partitioning , 2008, EvoWorkshops.

[7]  Thomas Bäck,et al.  Mixed-Integer Evolution Strategies and Their Application to Intravascular Ultrasound Image Analysis , 2006, EvoWorkshops.

[8]  Martin Schütz,et al.  Application of Parallel Mixed-Integer Evolution Strategies with Mutation Rate Pooling , 1996, Evolutionary Programming.

[9]  Rolf Drechsler,et al.  Applications of Evolutionary Computing , 2004, Lecture Notes in Computer Science.

[10]  Yiannis Kompatsiaris,et al.  Automated IVUS Contour Detection Using Intesity Features and Radial Basis Function Approximation , 2007, Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07).

[11]  Günter Rudolph,et al.  An Evolutionary Algorithm for Integer Programming , 1994, PPSN.

[12]  Johan H. C. Reiber,et al.  Multi-agent segmentation of IVUS images , 2004, Pattern Recognit..

[13]  Lucia Ballerini,et al.  Genetic Optimization of Morphological Filters with Applications in Breast Cancer Detection , 2004, EvoWorkshops.

[14]  Frank Hoffmeister,et al.  Problem-Independent Handling of Constraints by Use of Metric Penalty Functions , 1996, Evolutionary Programming.

[15]  Hans-Georg Beyer,et al.  The Theory of Evolution Strategies , 2001, Natural Computing Series.

[16]  Johan H. C. Reiber,et al.  User-Agent Cooperation in Multiagent IVUS Image Segmentation , 2009, IEEE Transactions on Medical Imaging.

[17]  Reinhard Männer,et al.  Parallel Problem Solving from Nature — PPSN III , 1994, Lecture Notes in Computer Science.

[18]  Hans-Paul Schwefel,et al.  Evolution and optimum seeking , 1995, Sixth-generation computer technology series.

[19]  David Moratal,et al.  Automatic segmentation and 3D reconstruction of intravascular ultrasound images for a fast preliminar evaluation of vessel pathologies , 2007, Comput. Medical Imaging Graph..

[20]  Michael Emmerich,et al.  Mixed-Integer Evolution Strategy for Chemical Plant Optimization with Simulators , 2000 .