PDF herunterladen
Methods Inf Med 2003; 42(01): 89-98
DOI: 10.1055/s-0038-1634213
Original article
Schattauer GmbH

On the Design of Active Contours for Medical Image Segmentation

A Scheme for Classification and Construction
T.M. Lehmann
1   Institute of Medical Informatics, Aachen University of Technology, Aachen, Germany
,
J. Bredno
1   Institute of Medical Informatics, Aachen University of Technology, Aachen, Germany
,
K. Spitzer
1   Institute of Medical Informatics, Aachen University of Technology, Aachen, Germany
› Institutsangaben
Weitere Informationen

Publikationsverlauf

Received: 16. Januar 2002

Accepted: 24. Juni 2002

Publikationsdatum:
07. Februar 2018 (online)

    Lizenzen und Reprints

Summary

Objectives: To provide a comprehensive bottom-up categorization of model-based segmentation techniques that allows to select, implement, and apply well-suited active contour models for segmentation of medical images, where major challenges are the high variability in shape and appearance of objects, noise, artifacts, partial occlusions of objects, and the required reliability and correctness of results.

Methods: We consider the general purpose of segmentation, the dimension of images, the object representation within the model, image and contour influences, as well as the solution and the parameter selection of the model. Potentials and limits are characterized for all instances in each category providing essential information for the application of active contours to various purposes in medical image processing. Based on prolaps surgery planning, we exemplify the use of the scheme to successfully design robust 3D-segmentation.

Results: The construction scheme allows to design robust segmentation methods, which, in particular, should avoid any gaps of dimension. Such gaps result from different image domains and value ranges with respect to the applied model domain and the dimension of relevant subsets for image influences, respectively.

Conclusions: A general segmentation procedure with sufficient robustness for medical applications is still missing. It is shown that in almost every category, novel techniques are available to improve the initial snake model, which was introduced in 1987.

Keywords

Image processing - computer-assisted (tree number L01.700.568.110.308) - algorithms (tree number L01.700.568.110.050) - finite element analysis (tree number H01.548.350)
 

  • References

  • 1 Undrill PE, Delibasis K, Cameron GG. An application of genetic algorithms to geometric model-guided interpretation of brain anatomy. Pattern Recognition 1997; 30 (Suppl. 02) 217-27.
    CrossrefPubMedGoogle Scholar
  • 2 Kass M, Witkin A, Terzopoulos D. Snakes: active contour models. Int J Comput Vision 1978; 1 (Suppl. 04) 321-31.
    PubMedGoogle Scholar
  • 3 Liang J, McInerney T, Terzopoulos D. Interactive medical image segmentation with united snakes. Lecture Notes Comput Science 1999; 1679: 116-27.
    PubMedGoogle Scholar
  • 4 Gunn SR, Nixon MS. Improving snake performance via a dual active contour. Lecture Notes Comput Science 1995; 970: 600-5.
    PubMedGoogle Scholar
  • 5 Yang GZ, Burger P, Panting J, Gatehouse PD, Rueckert D, Pennell DJ, Firmin DN. Motion and deformation tracking for short-axis echo-planar myocardial perfusion imaging. Med Image Analysis 1998; 2 (Suppl. 03) 285-302.
    CrossrefPubMedGoogle Scholar
  • 6 Chalana V, Hodgdon JA, Haynor DR. Unified data structures in a software environment for medical image segmentation. Proceedings SPIE 1998; 3338: 947-58.
    PubMedGoogle Scholar
  • 7 Sebbahi A, Herment A, De Cesare A, Mousseaux E. Multimodality cardiovascular image segmentation using a deformable contour model. Comput Med Imaging Graphics 1997; 21 (Suppl. 02) 79-89.
    CrossrefPubMedGoogle Scholar
  • 8 Kang DJ. A fast and stable snake algorithm for medical images. Pattern Recognition Letters 1999; 20 (Suppl. 05) 507-12.
    CrossrefPubMedGoogle Scholar
  • 9 McInerney T, Terzopoulos D. Deformable models in medical image analysis: a survey. Med Image Analysis 1996; 1 (Suppl. 02) 91-108.
    CrossrefPubMedGoogle Scholar
  • 10 Jain AK, Zhong Y, Dubuisson-Jolly MP. Deformable template models: a review. Signal Processing 1998; 71 (Suppl. 02) 109-29.
    CrossrefPubMedGoogle Scholar
  • 11 Xu C, Pham DL, Prince JL. Image Segmentation using deformable models. In: Sonka M, Fitzpatrick JM. editors. Handbook of Medical Imaging, Part 2: Medical Image Processing and Analysis. Bellingham: SPIE Press; 2000
    Google Scholar
  • 12 Lai KF, Chin RT. Deformable contours: modeling and extraction. IEEE Transactions on Pattern Analysis and Machine Intelligence 1995; 17 (Suppl. 11) 1084-90.
    CrossrefPubMedGoogle Scholar
  • 13 Cootes TF, Taylor CJ, Cooper DH, Graham J. Active shape models: their training and application. Comput Vision Image Understanding 1995; 61 (Suppl. 01) 38-59.
    CrossrefPubMedGoogle Scholar
  • 14 Staib LH, Duncan JS. Boundary finding with parametrically deformable models. IEEE Transactions on Pattern Analysis Machine Intelligence 1992; 14 (Suppl. 11) 1061-75.
    CrossrefPubMedGoogle Scholar
  • 15 Vemuri BC, Guo Y. Snake pedals: compact and versatile geometric models with physics-based control. IEEE Transactions Pattern Analysis Machine Intelligence 2000; 22 (Suppl. 05) 445-59.
    CrossrefPubMedGoogle Scholar
  • 16 Cinque L, Romangnoli R, Levialdi S, Nguyen PTA, Guan L. Self-organizing map for segmenting 3D biological images. Proceedings Int Conference Pattern Recognition ICPR’98 (vol 1). 1998: 471-3.
    PubMedGoogle Scholar
  • 17 Agbinya JI, Rees D. Multi-object tracking in video. Real-Time Imaging 1999; 5 (Suppl. 05) 295-304.
    PubMedGoogle Scholar
  • 18 Daesik J, Hyung-Il C. Moving object tracking by optimizing active models. Proceedings Int Conference Pattern Recognition ICPR’98 (vol 1). 1998: 738-40.
    PubMedGoogle Scholar
  • 19 Falcão AX, Udupa JK, Samarasekera S, Sharma S, Hirsch BE, de Lotufo RA. User-steered image segmentation paradigms: live wire and live lane. Graphical Models Image Processing 1998; 60 (Suppl. 04) 233-60.
    CrossrefPubMedGoogle Scholar
  • 20 Lynch JA, Zaim S, Zhao J, Stork A, Peterfy CG, Genant HK. Cartilage segmentation of 3D MRI scans of the osteoarthritic knee combining user knowledge and active contours. Proceedings SPIE 2000; 3979: 925-35.
    PubMedGoogle Scholar
  • 21 Malassiotis S, Strintzis MG. Tracking the left ventricle in echocardiographic images by learning heart dynamics. IEEE Transactions Med Imaging 1999; 18 (Suppl. 03) 282-90.
    PubMedGoogle Scholar
  • 22 Duncan JS, Ayache N. Medical image analysis: Progress over two decades and the challenges ahead. IEEE Transactions Pattern Analysis Machine Intelligence 2000; 22 (Suppl. 01) 85-106.
    CrossrefPubMedGoogle Scholar
  • 23 Blake A, Isard M, Reynard D. Learning to track the visual motion of contours. Artificial Intelligence 1995; 78 1–2 179-212.
    CrossrefPubMedGoogle Scholar
  • 24 Peterfreund N. The velocity snake: deformable contour for tracking in spatio-velocity space. Comput Vision Image Understanding 1999; 73 (Suppl. 03) 346-56.
    CrossrefPubMedGoogle Scholar
  • 25 Cohen LD, Cohen I. Finite-element methods for active contour models and balloons for 2-D and 3-D images. IEEE Transactions Pattern Analysis Machine Intelligence 1993; 15 (Suppl. 11) 1131-47.
    CrossrefPubMedGoogle Scholar
  • 26 Huang J, Abendschein D, Davila-Roman VG, Amini AA. Spatio-temporal tracking of myocardial deformations with a 4-D B-spline model from tagged MRI. IEEE Transactions Med Imaging 1999; 18 (Suppl. 10) 957-72.
    PubMedGoogle Scholar
  • 27 Yudong Z, Pelc NJ. A spatiotemporal model of cyclic kinematics and its application to analyzing nonrigid motion with MR velocity images. IEEE Transactions Med Imaging 1999; 18 (Suppl. 07) 557-69.
    PubMedGoogle Scholar
  • 28 Bredno J, Lehmann TM, Spitzer K. General finite element model for segmentation in 2, 3, and 4 dimensions. Proceedings SPIE 2000; 3979: 1174-84.
    PubMedGoogle Scholar
  • 29 Geiger D, Gupta A, Costa LA, Vlontzos J. Dynamic programming for detecting, tracking, and matching deformable contours. IEEE Transactions Pattern Analysis Machine Intelligence 1995; 17 (Suppl. 03) 294-302.
    CrossrefPubMedGoogle Scholar
  • 30 Ranganath S. Contour extraction from cardiac MRI studies using snakes. IEEE Transactions Med Imaging 1995; 14 (Suppl. 02) 328-38.
    PubMedGoogle Scholar
  • 31 Leymarie F, Levine MD. Tracking deformable objects in the plane using an active contour model. IEEE Transactions Pattern Analysis Machine Intelligence 1993; 15 (Suppl. 06) 617-34.
    CrossrefPubMedGoogle Scholar
  • 32 Denzler J, Niemann H. Active-rays: Polar-transformed active contours for real-time contour tracking. Real-Time Imaging 1999; 5 (Suppl. 03) 203-13.
    PubMedGoogle Scholar
  • 33 Kucera D, Martin RW. Segmentation of sequences of echocardiographic images using a simplified 3D active contour model with region-based external forces. Comput Med Imaging Graphics 1997; 21 (Suppl. 01) 1-21.
    CrossrefPubMedGoogle Scholar
  • 34 Kauffmann C, Godbout B, de Guise JA. Simplified active contour model applied to bone structure segmentation in digital radiographs. Proceedings SPIE 1998; 3338: 663-72.
    PubMedGoogle Scholar
  • 35 Bulpitt AJ, Berry E. Spiral CT of abdominal aortic aneurysms: comparison of segmentation with an automatic 3D deformable model and interactive segmentation. Proceedings SPIE 1998; 3338: 938-46.
    PubMedGoogle Scholar
  • 36 Vilariño DL, Brea VM, Cabello D, Pardo JM. Discrete-time CNN for image segmentation by active contours. Pattern Recognition Letters 1998; 19 (Suppl. 08) 721-34.
    CrossrefPubMedGoogle Scholar
  • 37 Lam CL, Yuen SY. An unbiased active contour algorithm for object tracking. Pattern Recognition Letters 1998; 19 5–6 491-8.
    CrossrefPubMedGoogle Scholar
  • 38 Akgul YS, Kambhamettu C, Stone M. Automatic extraction and tracking of the tongue contours. IEEE Transactions Med Imaging 1999; 18 (Suppl. 10) 1035-45.
    PubMedGoogle Scholar
  • 39 Pentland A, Horowitz B. Recovery of nonrigid motion and structure. IEEE Transactions Pattern Analysis Machine Intelligence 1991; 13 (Suppl. 07) 730-42.
    CrossrefPubMedGoogle Scholar
  • 40 Shekhar R, Cothren RM, Vince DG, Chandra S, Thomas JD, Cornhill JF. Three-dimensional segmentation of luminal and adventitial borders in serial intravascular ultrasound images. Comput Med Imaging Graphics 1999; 23 (Suppl. 06) 299-309.
    CrossrefPubMedGoogle Scholar
  • 41 Ghanei A, Soltanian-Zadeh H, Windham JP. Segmentation of the hippocampus from brain MRI using deformable contours. Comput Med Imaging Graphics 1998; 22 (Suppl. 03) 203-16.
    CrossrefPubMedGoogle Scholar
  • 42 Kobbelt LP. Discrete fairing and variational subdivision for freeform surface design. Visual Comput 2000; 16 3–4 142-58.
    CrossrefPubMedGoogle Scholar
  • 43 Juarez EL, Dumont C, Abidi MA. Object modeling in multiple-object 3D scenes using deformable simplex meshes. Proceedings SPIE 2000; 3958: 144-52.
    PubMedGoogle Scholar
  • 44 Rueckert D, Burger P, Forbat SM, Mohiaddin RD, Yang GZ. Automatic tracking of the aorta in cardiovascular MR images using deformable models. IEEE Transactions Med Imaging 1997; 16 (Suppl. 05) 581-90.
    PubMedGoogle Scholar
  • 45 McInerney T, Terzopoulos D. A dynamic finite element surface model for segmentation and tracking in multidimensional medical images with application to cardiac 4D image analysis. Comput Med Imaging Graphics 1995; 19 (Suppl. 01) 69-83.
    CrossrefPubMedGoogle Scholar
  • 46 Malladi R, Sethian JA, Vemuri BC. Shape modeling with front propagation: a level set approach. IEEE Transactions Pattern Analysis Machine Intelligence 1995; 17 (Suppl. 02) 158-75.
    CrossrefPubMedGoogle Scholar
  • 47 Grzeszczuk RP, Levin DN. Brownian strings: Segmenting images with stochastically deformable contours. IEEE Transactions Pattern Analysis Machine Intelligence 1997; 19 (Suppl. 10) 1100-14.
    CrossrefPubMedGoogle Scholar
  • 48 Zhong Y, Jain AK, Dubuisson-Jolly MP. Object tracking using deformable templates. IEEE Transactions Pattern Analysis Machine Intelligence 2000; 22 (Suppl. 05) 544-9.
    CrossrefPubMedGoogle Scholar
  • 49 Ngoi KP, Jia JC. An active contour model for colour region extraction in natural scenes. Image Vision Comput 1999; 17 (Suppl. 13) 955-66.
    CrossrefPubMedGoogle Scholar
  • 50 Bowden R, Mitchell TA, Sarhadi M. Non-linear statistical models for the 3D reconstruction of human pose and motion from monocular image sequences. Image Vision Comput 2000; 18 (Suppl. 09) 729-37.
    CrossrefPubMedGoogle Scholar
  • 51 Ivins J, Porrill J. Constrained active region models for fast tracking in color image sequences. Comput Vision Image Understanding 1998; 72 (Suppl. 01) 54-71.
    CrossrefPubMedGoogle Scholar
  • 52 Zhu SC, Lee TS, Yuille AL. Region competition: unifying snakes, region growing, energy/ Bayes/MDL for multi-band image segmentation. IEEE Transactions Pattern Analysis Machine Intelligence 1996; 18: 884-900.
    CrossrefPubMedGoogle Scholar
  • 53 Bredno J, Lehmann TM, Spitzer K. Automatic parameter setting for balloon models. Proceedings SPIE 2000; 3979: 1185-94.
    PubMedGoogle Scholar
  • 54 Xu C, Prince JL. Snakes, shapes, and gradient vector flow. IEEE Transactions Image Processing 1998; 7 (Suppl. 03) 359-69.
    CrossrefPubMedGoogle Scholar
  • 55 Pardo JM, Cabello D, Heras J. A snake for model-based segmentation of biomedical images. Pattern Recognition Letters 1997; 18 (Suppl. 14) 1529-38.
    CrossrefPubMedGoogle Scholar
  • 56 Ronfard R. Region-based strategies for active contour models. Int J Comput Vision 1994; 13 (Suppl. 02) 229-51.
    CrossrefPubMedGoogle Scholar
  • 57 Horritt MS. A statistical active contour model for SAR image segmentation. Image Vision Comput 1999; 17 3–4 213-24.
    CrossrefPubMedGoogle Scholar
  • 58 Boyer KL, Sarkar S. Perceptual organization in computer vision: status, challenges and potential. Comput Vision Image Understanding 1999; 76 (Suppl. 01) 1-5.
    CrossrefPubMedGoogle Scholar
  • 59 Cagnoni S, Dobrzeniecki AB, Poli R, Yanch JC. Genetic algorithm-based interactive segmentation of 3D medical images. Image Vision Computing 1999; 17 (Suppl. 12) 881-95.
    CrossrefPubMedGoogle Scholar
  • 60 Metzler V, Bredno J, Lehmann TM, Spitzer K. A deformable membrane for the segmentation of cytological samples. Proceedings SPIE 1998; 3338: 1246-57.
    PubMedGoogle Scholar
  • 61 von Klinski S, Derz C, Weese D, Tolxdorff T. Model-based image processing using snakes and mutual information. Proceedings SPIE 2000; 3979: 1053-64.
    PubMedGoogle Scholar
  • 62 Schreckenberg M, von Dziembowski G, Ziermann O, Meyer-Ebrecht D. Automatische Objekterkennung in 3D-Echokardiographiesequenzen auf der Basis aktiver Oberflächenmodelle und modellgekoppelter Merkmalsextraktion. In: Lehmann TM. et al., eds. Bildverarbeitung für die Medizin 1998. Berlin: Springer; 1997: 328-32 (in German)
    Google Scholar
  • 63 Terzopoulos D. Regularization of inverse visual problems involving discontinuities. IEEE Transactions Pattern Analysis Machine Intelligence 1986; 8 (Suppl. 04) 413-24.
    PubMedGoogle Scholar
  • 64 Lürig C, Kobbelt L, Ertl T. Hierarchical solutions for the deformable surface problem in visualization. Graphical Models 2000; 62 (Suppl. 01) 2-18.
    CrossrefPubMedGoogle Scholar
  • 65 McInerney T, Terzopoulos D. Topology adaptive deformable surfaces for medical image volume segmentation. IEEE Transactions Medical Imaging 1999; 18 (Suppl. 10) 840-50.
    CrossrefPubMedGoogle Scholar
  • 66 Lobregt S, Viergever MA. A discrete dynamic contour model. IEEE Transactions Medical Imaging 1995; 14 (Suppl. 01) 12-24.
    CrossrefPubMedGoogle Scholar
  • 67 Davatzikos C, Prince JL. Convexity analysis of active contour problems. Image Vision Comput 1999; 17 (Suppl. 01) 27-36.
    CrossrefPubMedGoogle Scholar
  • 68 Williams DJ, Shah M. A fast algorithm for active contours and curvature estimation. CVGIP-Image Understanding 1992; 55 (Suppl. 01) 14-26.
    PubMedGoogle Scholar
  • 69 Wang J, Li X. A system for segmenting ultra-sound images. Proceedings International Conference Pattern Recognition ICPR’98.; 1998: 456-61.
    Google Scholar
  • 70 Neuenschwander W, Fua P, Székely G, Kübler O. Velcro surfaces: fast initialization of deformable models. Comput Vision Image Understanding 1997; 65 (Suppl. 02) 237-45.
    CrossrefPubMedGoogle Scholar
  • 71 Kelemen A, Székely G, Gerig G. Elastic model-based segmentation of 3-D neuroradiological data sets. IEEE Transactions Med Imaging 1999; 18 (Suppl. 10) 828-39.
    PubMedGoogle Scholar
  • 72 Coppini G, Poli R, Valli G. Recovery of the 3-D shape of the left ventricle from echocardiographic images. IEEE Transactions Med Imaging 1995; 14 (Suppl. 02) 301-17.
    PubMedGoogle Scholar
  • 73 Giachetti A. Online analysis of echocardiographic image sequences. Med Image Analysis 1998; 2 (Suppl. 03) 162-284.
    PubMedGoogle Scholar
  • 74 Nastar C, Ayache N. Non-rigid motion analysis in medical images: a physically based approach. Lecture Notes Comput Science 1993; 687: 17-32.
    PubMedGoogle Scholar
  • 75 Lehmann TM, Bredno J, Spitzer K. Texture-adaptive active contour models. Lecture Notes Computer Science 2001; 2013: 387-96.
    PubMedGoogle Scholar
  • 76 Garrido A, De La Blanca NP. Physically-based active shape models: initialization and optimization. Pattern Recognition 1998; 31 (Suppl. 08) 1003-17.
    CrossrefPubMedGoogle Scholar
  • 77 Gang X, Segawa E, Tsuji S. Robust active contours with insensitive parameters. Pattern Recognition 1994; 27 (Suppl. 07) 879-84.
    CrossrefPubMedGoogle Scholar
  • 78 Loncaric S, Kovacevic D, Sorantin E. Semi-automatic active contour approach to segmentation of computed tomography values. Proceedings SPIE 2000; 3979: 917-24.
    PubMedGoogle Scholar
  • 79 Xu X, Pham DL, Rettmann ME, Yu DN, Prince JL. Reconstruction of the human cerebral cortex from magnetic resonance images. IEEE Transactions Med Imaging 1999; 18 (Suppl. 06) 467-80.
    PubMedGoogle Scholar
  • 80 Levienaise-Obadia B, Gee A. Adaptive segmentation of ultrasound images. Image Vision Comput 1999; 17 (Suppl. 08) 583-8.
    CrossrefPubMedGoogle Scholar
  • 81 Chen DH, Sun YN. A self-learning contour finding algorithm for echocardiac analysis. Proceedings SPIE 1998; 3338: 971-81.
    PubMedGoogle Scholar
  • 82 Gennert MA, Yuille AL. Determining the optimal weights in multiple objective function optimization. Proceedings 2nd International Conference Comput Vision.; 1988: 87-9.
    Google Scholar
  • 83 Barequet G, Shapiro D, Tal A. Multilevel sensitive reconstruction of polyhedral surfaces from parallel slices. Visual Comput 2000; 16 (Suppl. 02) 116-33.
    CrossrefPubMedGoogle Scholar
  • 84 Chalana V, Sannella M, Haynor DR. General-purpose software tool for serial segmentation of stacked images. Proceedings SPIE 2000; 3979: 192-203.
    PubMedGoogle Scholar
  • 85 Heigl B, Paulus D, Niemann H. Tracking points in sequences of color images. Pattern Recognition Image Analysis 1999; 9 (Suppl. 04) 648-53.
    PubMedGoogle Scholar
  • 86 Chan S, Ngo CW, Lai KF. Motion tracking of human mouth by generalized deformable models. Pattern Recognition Letters 1999; 20 (Suppl. 09) 879-87.
    CrossrefPubMedGoogle Scholar
  • 87 Chakraborty A, Staib LH, Duncan JS. An integrated approach for surface finding in medical images. Proceedings IEEE Workshop Mathematical Methods in Biomedical Image Analysis; 1996. 1996: 253-62.
    Google Scholar
  • 88 Tek H, Kimia BB. Volumetric segmentation of medical images by three-dimensional bubbles. Comput Vision Image Understanding 1997; 65 (Suppl. 02) 246-58.
    CrossrefPubMedGoogle Scholar
  • 89 Bulpitt AJ, Efford ND. An efficient 3D deformable model with a self-optimising mesh. Image Vision Comput 1996; 14 (Suppl. 08) 573-80.
    CrossrefPubMedGoogle Scholar