FAME-a flexible appearance modeling environment

Combined modeling of pixel intensities and shape has proven to be a very robust and widely applicable approach to interpret images. As such the active appearance model (AAM) framework has been applied to a wide variety of problems within medical image analysis. This paper summarizes AAM applications within medicine and describes a public domain implementation, namely the flexible appearance modeling environment (FAME). We give guidelines for the use of this research platform, and show that the optimization techniques used renders it applicable to interactive medical applications. To increase performance and make models generalize better, we apply parallel analysis to obtain automatic and objective model truncation. Further, two different AAM training methods are compared along with a reference case study carried out on cross-sectional short-axis cardiac magnetic resonance images and face images. Source code and annotated data sets needed to reproduce the results are put in the public domain for further investigation.

[1]  Bjarne Kjær Ersbøll,et al.  Extending and Applying Active Appearance Models for Automated, High Precision Segmentation* , 2001 .

[2]  Mikkel B. Stegmann,et al.  Fast Registration of Cardiac Perfusion MRI , 2003 .

[3]  Hans Henrik Thodberg.  Hands-on experience with active appearance models , 2002, SPIE Medical Imaging.

[4]  Christopher J. Taylor,et al.  Wavelet Compression of Active Appearance Models , 1999, MICCAI.

[5]  Timothy F. Cootes,et al.  Comparing Active Shape Models with Active Appearance Models , 1999, BMVC.

[6]  Milan Sonka,et al.  3-D active appearance models: segmentation of cardiac MR and ultrasound images , 2002, IEEE Transactions on Medical Imaging.

[7]  J. Horn.  A rationale and test for the number of factors in factor analysis , 1965, Psychometrika.

[8]  Jörgen Ahlberg.  Model-based coding : extraction, coding, and evaluation of face model parameters , 2002 .

[9]  Mikkel B. Stegmann,et al.  Motion-Compensation of Cardiac Perfusion MRI Using a Statistical Texture Ensemble , 2003, FIMH.

[10]  Timothy F. Cootes,et al.  Statistical models of appearance for medical image analysis and computer vision , 2001, SPIE Medical Imaging.

[11]  Mikkel B. Stegmann,et al.  Analysis and segmentation of face images using point annotations and linear subspace techniques, in , 2002 .

[12]  Timothy F. Cootes,et al.  A Unified Framework for Atlas Matching Using Active Appearance Models , 1999, IPMI.

[13]  Mikkel B. Stegmann,et al.  Automated Analysis of Corpora Callosa , 2003 .

[14]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[15]  Timothy F. Cootes,et al.  Constrained active appearance models , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[16]  Milan Sonka,et al.  Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images , 2001, IEEE Transactions on Medical Imaging.

[17]  Timothy F. Cootes,et al.  Statistical models of appearance for computer vision , 1999 .

[18]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[19]  Timothy F. Cootes,et al.  Comparing Variations on the Active Appearance Model Algorithm , 2002, BMVC.

[20]  Michael Jones,et al.  Multidimensional Morphable Models: A Framework for Representing and Matching Object Classes , 2004, International Journal of Computer Vision.

[21]  Timothy F. Cootes,et al.  Combining Elastic and Statistical Models of Appearance Variation , 2000, ECCV.

[22]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[23]  Milan Sonka,et al.  Shape- and appearance-based segmentation of volumetric medical images , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[24]  Milan Sonka,et al.  Active appearance motion model segmentation , 2001, Proceedings Second International Workshop on Digital and Computational Video.

[25]  Mikkel B. Stegmann,et al.  Corpus callosum analysis using MDL-based sequential models of shape and appearance , 2004, SPIE Medical Imaging.

[26]  Milan Sonka,et al.  Segmentation of cardiac MR volume data using 3D active appearance models , 2002, SPIE Medical Imaging.

[27]  Rasmus Larsen,et al.  A Noise Robust Statistical Texture Model , 2002, MICCAI.

[28]  Mikkel B. Stegmann,et al.  Object tracking using active appearance models , 2001 .

[29]  Milan Sonka,et al.  Fully automated endocardial contour detection in time sequences of echocardiograms by three-dimensional active appearance models , 2002, SPIE Medical Imaging.

[30]  Milan Sonka,et al.  Active appearance motion models for endocardial contour detection in time sequences of echocardiograms , 2001, SPIE Medical Imaging.

[31]  Jens C. Pruessner,et al.  Appearance-based modelling and segmentation of the hippocampus from MR images , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[32]  Milan Sonka,et al.  Time-continuous segmentation of cardiac MR image sequences using active appearance motion models , 2001, SPIE Medical Imaging.

[33]  Soren Forchhammer,et al.  On exploiting wavelet bases in statistical region-based segmentation , 2002 .

[34]  Alejandro F. Frangi,et al.  Three-dimensional modeling for functional analysis of cardiac images, a review , 2001, IEEE Transactions on Medical Imaging.

[35]  Mikkel B. Stegmann,et al.  Automated Segmentation of Cardiac Magnetic Resonance Images , 2001 .

[36]  J. Gower.  Generalized procrustes analysis , 1975 .

[37]  Milan Sonka,et al.  Fully automated endocardial contour detection in time sequences of echocardiograms by active appearance motion models , 2001, Computers in Cardiology 2001. Vol.28 (Cat. No.01CH37287).

[38]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[39]  Timothy F. Cootes,et al.  Interpreting face images using active appearance models , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[40]  Peter Hammond,et al.  Dense surface point distribution models of the human face , 2001, Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA 2001).

[41]  Milan Sonka,et al.  Segmentation of cardiac MR images: an active appearance model approach , 2000, Medical Imaging: Image Processing.

[42]  Milan Sonka,et al.  Time continuous segmentation of cardiac MR images using Active Appearance Motion Models , 2001, CARS.

[43]  Milan Sonka,et al.  Diaphragm dome surface segmentation in CT data sets: a 3D active appearance model approach , 2002, SPIE Medical Imaging.