Active shape model segmentation using a non-linear appearance model: application to 3D AAA segmentation

Active Shape Models (ASM) have proven to be an effective approach for image segmentation. In some applications, however, the linear model of gray level appearance around a contour that is used in ASM is not sufficient for accurate boundary localization. This report concerns one of those applications: segmenting the thrombus in CTA images of abdominal aortic aneurysms (AAA). A non-parametric appearance modeling scheme that effectively deals with a highly varying background is presented. In contrast with the conventional ASM approach, the new appearance model is trained on both true and false examples of boundary profiles. The probability that a given image profile belongs to the boundary is obtained using k nearest neighbor (kNN) probability density estimation. The performance of this scheme is compared to that of original ASMs, which minimize the Mahalanobis distance to the average true profile in the training set. A set of leave-one-out experiments is performed on 23 AAA datasets. Segmentation using the kNN appearance model significantly outperforms the original ASM scheme; average volume errors are 5.1% and 45% respectively.

[1]  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.

[2]  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).

[3]  Milan Sonka,et al.  Segmentation and interpretation of MR brain images. An improved active shape model , 1998, IEEE Transactions on Medical Imaging.

[4]  Nicolas Pérez de la Blanca,et al.  Physically-based active shape models: initialization and optimization , 1998, Pattern Recognit..

[5]  Sunil Arya,et al.  An optimal algorithm for approximate nearest neighbor searching fixed dimensions , 1998, JACM.

[6]  Michael Kohnen,et al.  Three-dimensional knowledge-based surface model for segmentation of organic structures , 2002, SPIE Medical Imaging.

[7]  Sven Loncaric,et al.  3D image analysis of abdominal aortic aneurysm , 2002, SPIE Medical Imaging.

[8]  Krishna Subramanyan,et al.  Automatic vessel extraction and abdominal aortic stent planning in multislice CT , 2002, SPIE Medical Imaging.

[9]  Krishna Subramanyan,et al.  Automatic aortic vessel tree extraction and thrombus detection in multislice CT , 2003, SPIE Medical Imaging.

[10]  Dorin Comaniciu,et al.  Vessel detection by mean shift based ray propagation , 2001, Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA 2001).

[11]  Ghassan Hamarneh,et al.  Deformable Spatio-Temporal Shape Models: Extending ASM to 2D+Time , 2001, BMVC.

[12]  Anil K. Jain,et al.  Deformable template models: A review , 1998, Signal Process..

[13]  Timothy F. Cootes,et al.  The Use of Active Shape Models for Locating Structures in Medical Images , 1993, IPMI.

[14]  Klaus D. Tönnies,et al.  A New Approach for Model-Based Adaptive Region Growing in Medical Image Analysis , 2001, CAIP.

[15]  Boudewijn P. F. Lelieveldt,et al.  Three-dimensional active shape model matching for left ventricle segmentation in cardiac CT , 2003, SPIE Medical Imaging.

[16]  Milan Sonka,et al.  Object localization and border detection criteria design in edge-based image segmentation: automated learning from examples , 2000, IEEE Transactions on Medical Imaging.

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

[18]  Max A. Viergever,et al.  Interactive shape models , 2003, SPIE Medical Imaging.

[19]  Paul Suetens,et al.  Evaluation of image features and search strategies for segmentation of bone structures in radiographs using Active Shape Models , 2002, Medical Image Anal..

[20]  D S Paik,et al.  Measurement of the aorta and its branches with helical CT. , 1998, Radiology.

[21]  Andrew J. Bulpitt,et al.  Spiral CT of abdominal aortic aneurysms: comparison of segmentation with an automatic 3D deformable model and interactive segmentation , 1998, Medical Imaging.

[22]  Max A. Viergever,et al.  Localization and segmentation of aortic endografts using marker detection , 2003, IEEE Transactions on Medical Imaging.

[23]  Christopher J. Taylor,et al.  Automatic measurement of vertebral shape using active shape models , 1997, Image Vis. Comput..

[24]  M. Schocke,et al.  Serial CT Volume Measurements after Endovascular Aortic Aneurysm Repair , 2001, Journal of endovascular therapy : an official journal of the International Society of Endovascular Specialists.

[25]  Jun Zheng,et al.  Segmentation of tibia bone in ultrasound images using active shape models , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[26]  Christopher J. Taylor,et al.  Model-Based Interpretation of 3D Medical Images , 1993, BMVC.

[27]  S. Travis,et al.  Endovascular AAA repair: classification of aneurysm sac volumetric change using spiral computed tomographic angiography. , 2002, Journal of endovascular therapy : an official journal of the International Society of Endovascular Specialists.

[28]  Max A. Viergever,et al.  Active-shape-model-based segmentation of abdominal aortic aneurysms in CTA images , 2002, SPIE Medical Imaging.

[29]  Gábor Székely,et al.  Model-Based Initialisation for Segmentation , 2000, ECCV.

[30]  Alejandro F. Frangi,et al.  Active shape model segmentation with optimal features , 2002, IEEE Transactions on Medical Imaging.

[31]  J. Blankensteijn,et al.  Maximal aneurysm diameter follow-up is inadequate after endovascular abdominal aortic aneurysm repair. , 2000, European journal of vascular and endovascular surgery : the official journal of the European Society for Vascular Surgery.

[32]  Kenneth R. Hoffmann,et al.  Computer-assisted diagnosis in CT angiography of abdominal aortic aneurysms , 1997, Medical Imaging.

[33]  Max A. Viergever,et al.  Fast delineation and visualization of vessels in 3-D angiographic images , 2000, IEEE Transactions on Medical Imaging.

[34]  Timothy F. Cootes,et al.  Use of active shape models for locating structures in medical images , 1994, Image Vis. Comput..

[35]  Derek R. Magee,et al.  Combining 3D Deformable Models and Level Set Methods for the Segmentation of Abdominal Aortic Aneurysms , 2001, BMVC.

[36]  Stan Sclaroff,et al.  Active blobs , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[37]  C J Taylor,et al.  The use of active shape models for making thickness measurements of articular cartilage from MR images , 1997, Magnetic resonance in medicine.

[38]  Andrea Giachetti,et al.  Reconstruction and web distribution of measurable arterial models , 2003, Medical Image Anal..

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

[40]  Jürgen Weese,et al.  Shape Constrained Deformable Models for 3D Medical Image Segmentation , 2001, IPMI.

[41]  Jim Graham,et al.  Robust Active Shape Model Search , 2002, ECCV.