Random walk and graph cut based active contour model for three-dimension interactive pituitary adenoma segmentation from MR images

Accurate volume measurements of pituitary adenoma are important to the diagnosis and treatment for this kind of sellar tumor. The pituitary adenomas have different pathological representations and various shapes. Particularly, in the case of infiltrating to surrounding soft tissues, they present similar intensities and indistinct boundary in T1-weighted (T1W) magnetic resonance (MR) images. Then the extraction of pituitary adenoma from MR images is still a challenging task. In this paper, we propose an interactive method to segment the pituitary adenoma from brain MR data, by combining graph cuts based active contour model (GCACM) and random walk algorithm. By using the GCACM method, the segmentation task is formulated as an energy minimization problem by a hybrid active contour model (ACM), and then the problem is solved by the graph cuts method. The region-based term in the hybrid ACM considers the local image intensities as described by Gaussian distributions with different means and variances, expressed as maximum a posteriori probability (MAP). Random walk is utilized as an initialization tool to provide initialized surface for GCACM. The proposed method is evaluated on the three-dimensional (3-D) T1W MR data of 23 patients and compared with the standard graph cuts method, the random walk method, the hybrid ACM method, a GCACM method which considers global mean intensity in region forces, and a competitive region-growing based GrowCut method planted in 3D Slicer. Based on the experimental results, the proposed method is superior to those methods.

[1]  Leo Grady,et al.  Random Walks for Image Segmentation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Qiang Zheng,et al.  Modified localized graph cuts based active contour model for local segmentation with surrounding nearby clutter and intensity inhomogeneity , 2013, Signal Process..

[3]  P. Snyder,et al.  Silent (clinically nonfunctioning) pituitary adenomas , 2014, Journal of Neuro-Oncology.

[4]  Tetsuro Oshika,et al.  Vision-related quality of life after transsphenoidal surgery for pituitary adenoma. , 2010, Investigative ophthalmology & visual science.

[5]  S. Melmed,et al.  2004 World Health Organization classification of pituitary tumors: what is new? , 2005, Acta Neuropathologica.

[6]  Adel Said Elmaghraby,et al.  A graph cut based active contour without edges with relaxed homogeneity constraint , 2008, 2008 19th International Conference on Pattern Recognition.

[7]  Cui Hua,et al.  Geodesic active contour, inertia and initial speed , 2008, Pattern Recognit. Lett..

[8]  Christopher Nimsky,et al.  Pituitary Adenoma Segmentation , 2011, ArXiv.

[9]  J Kawamura,et al.  Pituitary adenomas and normal pituitary tissue: enhancement patterns on gadopentetate-enhanced MR imaging. , 1990, Radiology.

[10]  C. Lueck,et al.  A mechanical theory to account for bitemporal hemianopia from chiasmal compression. , 2005, Journal of neuro-ophthalmology : the official journal of the North American Neuro-Ophthalmology Society.

[11]  Xue-Cheng Tai,et al.  Graph Cut Optimization for the Piecewise Constant Level Set Method Applied to Multiphase Image Segmentation , 2009, SSVM.

[12]  Noel E. O'Connor,et al.  A comparative evaluation of interactive segmentation algorithms , 2010, Pattern Recognit..

[13]  Horst K. Hahn,et al.  Accuracy and reproducibility of a novel semi-automatic segmentation technique for MR volumetry of the pituitary gland , 2011, Neuroradiology.

[14]  A M McNicol,et al.  Pituitary adenomas , 1987, Histopathology.

[15]  S. Asa,et al.  The 2004 World Health Organization classification of pituitary tumors: What is new? , 2005, Acta Neuropathologica.

[16]  M. Monteiro,et al.  Predictive factors for the development of visual loss in patients with pituitary macroadenomas and for visual recovery after optic pathway decompression. , 2010, Canadian journal of ophthalmology. Journal canadien d'ophtalmologie.

[17]  Adel Said Elmaghraby,et al.  A graph cut based active contour for multiphase image segmentation , 2008, 2008 15th IEEE International Conference on Image Processing.

[18]  L.-K. Shark,et al.  Medical Image Segmentation Using New Hybrid Level-Set Method , 2008, 2008 Fifth International Conference BioMedical Visualization: Information Visualization in Medical and Biomedical Informatics.

[19]  Bernd Freisleben,et al.  Segmentation of pituitary adenoma: A graph-based method vs. a balloon inflation method , 2013, Comput. Methods Programs Biomed..

[20]  M. Losa,et al.  Prognostic factors of visual field improvement after trans-sphenoidal approach for pituitary macroadenomas: review of the literature and analysis by quantitative method , 2012, Neurosurgical Review.

[21]  C. Soh,et al.  Assessing size of pituitary adenomas: a comparison of qualitative and quantitative methods on MR , 2016, Acta neurochirurgica.

[22]  Christopher Nimsky,et al.  Pituitary Adenoma Volumetry with 3D Slicer , 2012, PloS one.

[23]  Wenbing Tao.  Iterative Narrowband-Based Graph Cuts Optimization for Geodesic Active Contours With Region Forces (GACWRF) , 2012, IEEE Transactions on Image Processing.

[24]  Vladimir Kolmogorov,et al.  Computing geodesics and minimal surfaces via graph cuts , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[25]  Ashish Suri,et al.  Treatment of Giant Pituitary Adenomas , 2007 .

[26]  J. Ho,et al.  The Influence of Pituitary Adenoma Size on Vision and Visual Outcomes after Trans-Sphenoidal Adenectomy: A Report of 78 Cases , 2015, Journal of Korean Neurosurgical Society.

[27]  M. Mallar Chakravarty,et al.  Estimating volumes of the pituitary gland from T1-weighted magnetic-resonance images: Effects of age, puberty, testosterone, and estradiol , 2014, NeuroImage.

[28]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

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

[30]  Qiang Zheng,et al.  Graph cuts based active contour model with selective local or global segmentation , 2012 .

[31]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Ning Xu,et al.  Object segmentation using graph cuts based active contours , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..