Prostate Volume Segmentation in TRUS Using Hybrid Edge-Bhattacharyya Active Surfaces

Objective: We present a new hybrid edge and region-based parametric deformable model, or active surface, for prostate volume segmentation in transrectal ultrasound (TRUS) images. Methods: Our contribution is threefold. First, we develop a new edge detector derived from the radial bas-relief approach, allowing for better scalar prostate edge detection in low contrast configurations. Second, we combine an edge-based force derived from the proposed edge detector with a new region-based force driven by the Bhattacharyya gradient flow and adapted to the case of parametric active surfaces. Finally, we develop a quasi-automatic initialization technique for deformable models by analyzing the profiles of the proposed edge detector response radially to obtain initial landmark points toward which an initial surface model is warped. Results: We validate our method on a set of 36 TRUS images for which manual delineations were performed by two expert radiation oncologists, using a wide variety of quantitative metrics. The proposed hybrid model achieved state-of-the-art segmentation accuracy. Conclusion: Results demonstrate the interest of the proposed hybrid framework for accurate prostate volume segmentation. Significance: This paper presents a modular framework for accurate prostate volume segmentation in TRUS, broadening the range of available strategies to tackle this open problem.

[1]  Allen R. Tannenbaum,et al.  Localizing Region-Based Active Contours , 2008, IEEE Transactions on Image Processing.

[2]  Nico Blodow,et al.  Towards 3D Point cloud based object maps for household environments , 2008, Robotics Auton. Syst..

[3]  J. Sethian,et al.  Motion by intrinsic Laplacian of curvature , 1999 .

[4]  Josef Pauli,et al.  MRI Hip Joint Segmentation: A Locally Bhattacharyya Weighted Hybrid 3D Level Set Approach , 2017, VCBM.

[5]  Aldo Cumani,et al.  Edge detection in multispectral images , 1991, CVGIP Graph. Model. Image Process..

[6]  Fernando Arámbula Cosío,et al.  Automatic initialization of an active shape model of the prostate , 2008, Medical Image Anal..

[7]  Denis Friboulet,et al.  Prostate segmentation in echographic images: A variational approach using deformable super-ellipse and rayleigh distribution , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[8]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[9]  Septimiu E. Salcudean,et al.  Semi-automatic segmentation for prostate interventions , 2011, Medical Image Anal..

[10]  A. Yezzi,et al.  On the relationship between parametric and geometric active contours , 2000, Conference Record of the Thirty-Fourth Asilomar Conference on Signals, Systems and Computers (Cat. No.00CH37154).

[11]  Aaron Fenster,et al.  Prostate segmentation algorithm using dyadic wavelet transform and discrete dynamic contour. , 2004, Physics in medicine and biology.

[12]  Jianchao Zeng,et al.  Segmentation of prostate ultrasound images using an improved snakes model , 2004, Proceedings 7th International Conference on Signal Processing, 2004. Proceedings. ICSP '04. 2004..

[13]  S Nag,et al.  The American Brachytherapy Society recommendations for permanent prostate brachytherapy postimplant dosimetric analysis. , 2000, International journal of radiation oncology, biology, physics.

[14]  Aaron Fenster,et al.  Rotational-Slice-Based Prostate Segmentation Using Level Set with Shape Constraint for 3D End-Firing TRUS Guided Biopsy , 2012, MICCAI.

[15]  A. Fenster,et al.  Three-dimensional prostate segmentation using level set with shape constraint based on rotational slices for 3D end-firing TRUS guided biopsy. , 2013, Medical physics.

[16]  Hanif M. Ladak,et al.  Prostate segmentation from 2D ultrasound images , 2000, Proceedings of the 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (Cat. No.00CH37143).

[17]  Irène Buvat,et al.  Variational Segmentation of Vector-Valued Images With Gradient Vector Flow , 2014, IEEE Transactions on Image Processing.

[18]  Douglas L. Jones,et al.  Line and boundary detection in speckle images , 1998, IEEE Trans. Image Process..

[19]  Magdy M. A. Salama,et al.  Information tracking approach to segmentation of ultrasound imagery of the prostate , 2009, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[20]  H. C. Lim,et al.  Computerised prostate boundary estimation of ultrasound images using radial bas-relief method , 2006, Medical and Biological Engineering and Computing.

[21]  Benjamín Castañeda,et al.  Semi-automated segmentation of the prostate gland boundary in ultrasound images using a machine learning approach , 2008, SPIE Medical Imaging.

[22]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  D. Ash,et al.  ESTRO/EAU/EORTC recommendations on permanent seed implantation for localized prostate cancer. , 2000, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[24]  Julien Mille,et al.  Narrow band region-based active contours and surfaces for 2D and 3D segmentation , 2009, Comput. Vis. Image Underst..

[25]  Jean-Christophe Olivo-Marin,et al.  3-D Active Meshes: Fast Discrete Deformable Models for Cell Tracking in 3-D Time-Lapse Microscopy , 2011, IEEE Transactions on Image Processing.

[26]  Hong Zhang,et al.  Interactive prostate shape reconstruction from 3D TRUS images , 2014, J. Comput. Des. Eng..

[27]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[28]  Aaron Fenster,et al.  Prostate boundary segmentation from 3D ultrasound images. , 2003, Medical physics.

[29]  Joachim Weickert,et al.  Anisotropic diffusion in image processing , 1996 .

[30]  P. Grimm,et al.  American Brachytherapy Society (ABS) recommendations for transperineal permanent brachytherapy of prostate cancer. , 1999, International journal of radiation oncology, biology, physics.

[31]  Max A. Viergever,et al.  A discrete dynamic contour model , 1995, IEEE Trans. Medical Imaging.

[32]  Desire Sidibé,et al.  A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography images , 2012, Comput. Methods Programs Biomed..

[33]  N.N. Kachouie,et al.  An Elliptical Level Set Method for Automatic TRUS Prostate Image Segmentation , 2006, 2006 IEEE International Symposium on Signal Processing and Information Technology.

[34]  Yongjian Yu,et al.  Segmentation of the prostate from suprapubic ultrasound images. , 2004, Medical physics.

[35]  Yimin Chen,et al.  Fully automatic prostate segmentation from transrectal ultrasound images based on radial bas-relief initialization and slice-based propagation , 2016, Comput. Biol. Medicine.

[36]  Mark Meyer,et al.  Implicit fairing of irregular meshes using diffusion and curvature flow , 1999, SIGGRAPH.

[37]  Mariano Alcañiz Raya,et al.  Outlining of the prostate using snakes with shape restrictions based on the wavelet transform , 1999, Pattern Recognit..

[38]  Xu Li,et al.  Segmentation of prostate from ultrasound images using level sets on active band and intensity variation across edges. , 2016, Medical physics.

[39]  J. Alison Noble,et al.  Ultrasound image segmentation: a survey , 2006, IEEE Transactions on Medical Imaging.

[40]  M. Bolla,et al.  Management of prostate cancer : a multidisciplinary approach , 2012 .

[41]  Yogesh Rathi,et al.  Image Segmentation Using Active Contours Driven by the Bhattacharyya Gradient Flow , 2007, IEEE Transactions on Image Processing.

[42]  Aaron Fenster,et al.  Prostate Segmentation: An Efficient Convex Optimization Approach With Axial Symmetry Using 3-D TRUS and MR Images , 2014, IEEE Transactions on Medical Imaging.

[43]  Bing Li,et al.  3D Segmentation of the Prostate via Poisson Inverse Gradient Initialization , 2007, 2007 IEEE International Conference on Image Processing.

[44]  S. Osher,et al.  Algorithms Based on Hamilton-Jacobi Formulations , 1988 .

[45]  Huazhong Shu,et al.  Prostate Segmentation in HIFU Therapy , 2011, IEEE Transactions on Medical Imaging.

[46]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[47]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[48]  Keck Voon Ling,et al.  Automatic 3d Prostate Surface Detection From Trus With Level Sets , 2004, Int. J. Image Graph..

[49]  James A. Sethian,et al.  Flow under Curvature: Singularity Formation, Minimal Surfaces, and Geodesics , 1993, Exp. Math..

[50]  U. Rajendra Acharya,et al.  Segmentation of prostate contours for automated diagnosis using ultrasound images: A survey , 2017, J. Comput. Sci..

[51]  Bingbing Liu,et al.  Robust Prostate Segmentation Using Intrinsic Properties of TRUS Images , 2015, IEEE Transactions on Medical Imaging.

[52]  Aaron Fenster,et al.  Semiautomatic three-dimensional segmentation of the prostate using two-dimensional ultrasound images. , 2003, Medical physics.

[53]  F F Yin,et al.  A three-dimensional deformable model for segmentation of human prostate from ultrasound images. , 2001, Medical physics.

[54]  Sheng Xu,et al.  Discrete Deformable Model Guided by Partial Active Shape Model for TRUS Image Segmentation , 2010, IEEE Transactions on Biomedical Engineering.