New Region Growing based on Thresholding Technique Applied to MRI Data

This paper proposes an optimal region growing threshold for the segmentation of magnetic resonance images (MRIs). The proposed algorithm combines local search procedure with thresholding region growing to achieve better generic seeds and optimal thresholds for region growing method. A procedure is used to detect the best possible seeds from a set of data distributed all over the image as a high accumulator of the histogram. The output seeds are fed to the local search algorithm to extract the best seeds around initial seeds. Optimal thresholds are used to overcome the limitations of region growing algorithm and to select the pixels sequentially in a random walk starting at the seed point. The proposed algorithm works automatically without any predefined parameters. The proposed algorithm is applied to the challenging application "gray matter/white matter" segmentation datasets. The experimental results compared with other segmentation techniques show that the proposed algorithm produces more accurate and stable results.

[1]  Hong Yan,et al.  Current Methods in the Automatic Tissue Segmentation of 3D Magnetic Resonance Brain Images , 2006 .

[2]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[3]  Jiazheng Shi,et al.  A top-down region dividing approach for image segmentation , 2008, Pattern Recognit..

[4]  Ahmed S. Ghiduk,et al.  A novel approach based on genetic algorithms and region growing for magnetic resonance image (MRI) segmentation , 2013, Comput. Sci. Inf. Syst..

[5]  S. Rossitti.  Introduction to Functional Magnetic Resonance Imaging, Principles and Techniques , 2002 .

[6]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Jie Yang,et al.  A hybrid region-boundary model for cerebral cortical segmentation in MRI , 2006, Comput. Medical Imaging Graph..

[8]  Zikuan Chen.  Histogram partition and interval thresholding for volumetric breast tissue segmentation , 2008, Comput. Medical Imaging Graph..

[9]  Andrew Mehnert,et al.  An improved seeded region growing algorithm , 1997, Pattern Recognit. Lett..

[10]  Jianping Fan,et al.  Seeded region growing: an extensive and comparative study , 2005, Pattern Recognit. Lett..

[11]  Donald W. Chakeres,et al.  Fundamentals of Magnetic Resonance Imaging , 1991 .

[12]  C. Chellamuthu,et al.  An efficient approach for brain tumour detection based on modified region growing and neural network in MRI images , 2012, 2012 International Conference on Computing, Electronics and Electrical Technologies (ICCEET).

[13]  Marcelo J. Vénere,et al.  Computerized Medical Imaging and Graphics a Combined Region Growing and Deformable Model Method for Extraction of Closed Surfaces in 3d Ct and Mri Scans , 2022 .

[14]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[15]  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.

[16]  Funatomi Takuya,et al.  New region growing segmentation technique for MR images with weak boundaries (医用画像) , 2010 .

[17]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[18]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[19]  Carlos S. Mendoza,et al.  Fast parameter-free region growing segmentation with application to surgical planning , 2010, Machine Vision and Applications.

[20]  Henry Völzke,et al.  A fully automatic three-step liver segmentation method on LDA-based probability maps for multiple contrast MR images. , 2010, Magnetic resonance imaging.