A modified fuzzy C-means method for segmenting MR images using non-local information.

BACKGROUND In recent years, MR images have been increasingly used in therapeutic applications such as image-guided radiotherapy (IGRT). However, images with low contrast values and noises present challenges for image segmentation. OBJECTIVE The objective of this study is to develop a robust method based on fuzzy C-means (FCM) method which can segment MR images polluted with Gaussian noise. METHODS A modified FCM algorithm accommodating non-local pixel information via Hausdorff distance was developed for segmenting MR images. The membership and objective functions were modified accordingly. Segmentations with different weights of the Hausdorff distance were compared. RESULTS Segmentation tests using synthetic and MR images showed that the proposed algorithm was better at resolving boundaries and more robust to Gaussian noise. By segmenting a sample MR image of a tumor, we further showed the capability of the method in capturing the centroid of the target region. CONCLUSIONS The modified FCM algorithm with neighboring information can be used to segment blurry images with potential applications in segmenting motion MR images in image-guided radiotherapy (IGRT).

[1]  James M. Keller,et al.  A possibilistic fuzzy c-means clustering algorithm , 2005, IEEE Transactions on Fuzzy Systems.

[2]  Khizar Hayat,et al.  MRI Segmentation through Wavelets and Fuzzy C-Means , 2011 .

[3]  Aly A. Farag,et al.  A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data , 2002, IEEE Transactions on Medical Imaging.

[4]  Caroline Petitjean,et al.  A review of segmentation methods in short axis cardiac MR images , 2011, Medical Image Anal..

[5]  Dzung L. Pham,et al.  Spatial Models for Fuzzy Clustering , 2001, Comput. Vis. Image Underst..

[6]  Nicholas Slevin,et al.  Evaluation of an automatic segmentation algorithm for definition of head and neck organs at risk , 2014, Radiation oncology.

[7]  James M. Keller,et al.  Improvements to the relational fuzzy c-means clustering algorithm , 2014, Pattern Recognit..

[8]  S. Delorme,et al.  MR-guidance – a clinical study to evaluate a shuttle- based MR-linac connection to provide MR-guided radiotherapy , 2014, Radiation oncology.

[9]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Pengfei Wang,et al.  Genetic FCMS Clustering Algorithm for Image Segmentation , 2012 .

[11]  Yan Wang,et al.  Adaptive Multi-cluster Fuzzy C-Means Segmentation of Breast Parenchymal Tissue in Digital Mammography , 2011, MICCAI.

[12]  Sasa Mutic,et al.  Respiratory amplitude guided 4-dimensional magnetic resonance imaging. , 2013, International journal of radiation oncology, biology, physics.

[13]  L O Hall,et al.  Review of MR image segmentation techniques using pattern recognition. , 1993, Medical physics.

[14]  Lequan Min,et al.  Novel modified fuzzy c-means algorithm with applications , 2009, Digit. Signal Process..

[15]  Colin Studholme,et al.  A non-local fuzzy segmentation method: Application to brain MRI , 2009, Pattern Recognit..

[16]  Korris Fu-Lai Chung,et al.  Robust fuzzy clustering-based image segmentation , 2009, Appl. Soft Comput..

[17]  Parag J. Parikh,et al.  The Dawn of a New Era: First Ever MR-IGRT Treatments – Initial Experiences and Future Implications , 2014 .

[18]  Sim Heng Ong,et al.  Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation , 2011, Comput. Biol. Medicine.

[19]  Daoqiang Zhang,et al.  Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation , 2007, Pattern Recognit..

[20]  Hongbao Cao,et al.  Segmentation of M-FISH Images for improved classification of chromosomes with an adaptive fuzzy c-means clustering algorithm , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[21]  Sivapalan Selvadurai,et al.  Ethnic attitudes, political preferences and the politics of stability , 2011 .

[22]  Xiangyang Wang,et al.  A fast and robust image segmentation using FCM with spatial information , 2010, Digit. Signal Process..

[23]  Rongchun Zhao,et al.  Image segmentation by clustering of spatial patterns , 2007, Pattern Recognit. Lett..

[24]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[25]  Van den Berg,et al.  MR guidance in radiotherapy , 2014 .

[26]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[27]  S Mutic,et al.  TH-C-141-05: A Simulation Study to Investigate the Potential of Using Magnetic Resonance Elastography (MRE) to Differentiate Recurrent Tumor and Radiation Necrosis. , 2013, Medical physics.

[28]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[29]  James V. Miller,et al.  GBM Volumetry using the 3D Slicer Medical Image Computing Platform , 2013, Scientific Reports.

[30]  Thomas A. Runkler,et al.  Alternating cluster estimation: a new tool for clustering and function approximation , 1999, IEEE Trans. Fuzzy Syst..

[31]  R. Devi,et al.  Robust kernel FCM in segmentation of breast medical images , 2011, Expert Syst. Appl..

[32]  Song Guo,et al.  Green Communications and Computing Networks , 2016, IEEE Commun. Mag..