A unified EM approach to bladder wall segmentation with coupled level-set constraints

Magnetic resonance (MR) imaging-based virtual cystoscopy (VCys), as a non-invasive, safe and cost-effective technique, has shown its promising virtue for early diagnosis and recurrence management of bladder carcinoma. One primary goal of VCys is to identify bladder lesions with abnormal bladder wall thickness, and consequently a precise segmentation of the inner and outer borders of the wall is required. In this paper, we propose a unified expectation-maximization (EM) approach to the maximum-a posteriori (MAP) solution of bladder wall segmentation, by integrating a novel adaptive Markov random field (AMRF) model and the coupled level-set (CLS) information into the prior term. The proposed approach is applied to the segmentation of T(1)-weighted MR images, where the wall is enhanced while the urine and surrounding soft tissues are suppressed. By introducing scale-adaptive neighborhoods as well as adaptive weights into the conventional MRF model, the AMRF model takes into account the local information more accurately. In order to mitigate the influence of image artifacts adjacent to the bladder wall and to preserve the continuity of the wall surface, we apply geometrical constraints on the wall using our previously developed CLS method. This paper not only evaluates the robustness of the presented approach against the known ground truth of simulated digital phantoms, but further compares its performance with our previous CLS approach via both volunteer and patient studies. Statistical analysis on experts' scores of the segmented borders from both approaches demonstrates that our new scheme is more effective in extracting the bladder wall. Based on the wall thickness calibrated from the segmented single-layer borders, a three-dimensional virtual bladder model can be constructed and the wall thickness can be mapped onto the model, where the bladder lesions will be eventually detected via experts' visualization and/or computer-aided detection.

[1]  Zhengrong Liang,et al.  An EM Approach to MAP Solution of Segmenting Tissue Mixtures: A Numerical Analysis , 2009, IEEE Transactions on Medical Imaging.

[2]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[3]  P. Mariappan,et al.  A surveillance schedule for G1Ta bladder cancer allowing efficient use of check cystoscopy and safe discharge at 5 years based on a 25-year prospective database. , 2005, The Journal of urology.

[4]  Zhengrong Liang,et al.  A new partial volume segmentation approach to extract bladder wall for computer-aided detection in virtual cystoscopy , 2004, SPIE Medical Imaging.

[5]  Ken D. Sauer,et al.  A local update strategy for iterative reconstruction from projections , 1993, IEEE Trans. Signal Process..

[6]  Qin Lin,et al.  An integrated electronic colon cleansing for CT colonoscopy via MAP-EM segmentation and scale-based scatter correction , 2012, Medical Imaging.

[7]  Zhengrong Liang,et al.  A Precise calculation of bladder wall thickness for detection of bladder abnormalities via MR cystography , 2011, 2011 IEEE Nuclear Science Symposium Conference Record.

[8]  A. Jemal,et al.  Cancer statistics, 2013 , 2013, CA: a cancer journal for clinicians.

[9]  Nikos Paragios,et al.  A Variational Approach for the Segmentation of the Left Ventricle in Cardiac Image Analysis , 2002, International Journal of Computer Vision.

[10]  Zhengrong Liang,et al.  Segmentation of multispectral bladder MR images with inhomogeneity correction for virtual cystoscopy , 2008, SPIE Medical Imaging.

[11]  Michael Brady,et al.  Segmentation of the bladder wall using coupled level set methods , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[12]  Zhengrong Liang,et al.  Tissue mixture-based inner bladder wall segmentation with applications in MRI-based virtual cystoscopy , 2009, Medical Imaging.

[13]  Thrasyvoulos N. Pappas.  An adaptive clustering algorithm for image segmentation , 1992, IEEE Trans. Signal Process..

[14]  J. Platt,et al.  Bladder tumor detection at virtual cystoscopy. , 2001, Radiology.

[15]  Hervé Delingette,et al.  Automatic Segmentation of Bladder and Prostate Using Coupled 3D Deformable Models , 2007, MICCAI.

[16]  Jayaram K. Udupa,et al.  Scale-based diffusive image filtering preserving boundary sharpness and fine structures , 2001, IEEE Transactions on Medical Imaging.

[17]  Ewout W Steyerberg,et al.  Microsatellite analysis of voided-urine samples for surveillance of low-grade non-muscle-invasive urothelial carcinoma: feasibility and clinical utility in a prospective multicenter study (Cost-Effectiveness of Follow-Up of Urinary Bladder Cancer trial [CEFUB]). , 2009, European urology.

[18]  Xuelong Li,et al.  Coupled Directional Level Set for MR Image Segmentation , 2012, 2012 11th International Conference on Machine Learning and Applications.

[19]  Robert T. Schultz,et al.  Segmentation and Measurement of the Cortex from 3D MR Images , 1998, MICCAI.

[20]  Alicia Samuels,et al.  Cancer Statistics, 2003 , 2003, CA: a cancer journal for clinicians.

[21]  Ali Kamen,et al.  Constrained Surface Evolutions for Prostate and Bladder Segmentation in CT Images , 2005, CVBIA.

[22]  H. Gudbjartsson,et al.  The rician distribution of noisy mri data , 1995, Magnetic resonance in medicine.

[23]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[24]  Robert T. Schultz,et al.  Segmentation and Measurement of the Cortex from 3D MR Images , 1998, MICCAI.

[25]  Marcus Settles,et al.  Reliability of MR imaging-based virtual cystoscopy in the diagnosis of cancer of the urinary bladder. , 2002, AJR. American journal of roentgenology.

[26]  Russell D. Wolfinger,et al.  SAS for Mixed Models, Second Edition , 2006 .

[27]  Zhengrong Liang,et al.  Volume-Based Features for Detection of Bladder Wall Abnormal Regions via MR Cystography , 2011, IEEE Transactions on Biomedical Engineering.

[28]  João Manuel R. S. Tavares,et al.  Novel Approach to Segment the Inner and Outer Boundaries of the Bladder Wall in T2-Weighted Magnetic Resonance Images , 2011, Annals of Biomedical Engineering.

[29]  Z. Liang,et al.  An image processing approach to compensate for the bladder wall motion and deformation in MR cystography , 2011, 2011 IEEE Nuclear Science Symposium Conference Record.

[30]  D. Lamm,et al.  Bladder cancer, 1996 , 1996, Ca.

[31]  Zhengrong Liang,et al.  An Adaptive Window-Setting Scheme for Segmentation of Bladder Tumor Surface via MR Cystography , 2012, IEEE Transactions on Information Technology in Biomedicine.

[32]  Alvin C. Goh,et al.  Application of new technology in bladder cancer diagnosis and treatment , 2009, World Journal of Urology.

[33]  Zhengrong Liang,et al.  A Coupled Level Set Framework for Bladder Wall Segmentation With Application to MR Cystography , 2010, IEEE Transactions on Medical Imaging.

[34]  Bin Li,et al.  Multiscan MRI-based virtual cystoscopy , 2000, Medical Imaging.

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

[36]  Zhengrong Liang,et al.  MRI volumetric analysis of multiple sclerosis: methodology and validation , 2003 .

[37]  Kyoung-Sik Cho,et al.  Comparison of virtual cystoscopy, multiplanar reformation, and source CT images with contrast material-filled bladder for detecting lesions. , 2005, AJR. American journal of roentgenology.

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