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).
PetitjeanC. and DacherJ.-N., A review of segmentation methods in short axis cardiac MR images. Medical Image Analysis15, 169 (2011).
2.
LiB.N., ChuiC.K., ChangS. and OngS.H., Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation. Computers in Biology and Medicine41, 1 (2011).
3.
EggerJ., KapurT., FedorovA., PieperS., MillerJ.V., VeeraraghavanH., FreislebenB., GolbyA.J., NimskyC. and KikinisR., GBM volumetry using the 3D Slicer medical image computing platform. Scientific Reports3, 1364 (2013).
4.
HuY., CaruthersS.D., LowD.A., ParikhP.J. and MuticS., Respiratory Amplitude Guided 4-Dimensional Magnetic Resonance Imaging. Int J Radiat Oncol86, 198 (2013).
5.
LagendijkJ.J.W., RaaymakersB.W., Van den BergC.A.T., MoerlandM.A., PhilippensM.E. and van VulpenM., MR guidance in radiotherapy. Phys Med Biol59, R349 (2014).
6.
MuticS., ParikhP.J., BradleyJ.D., HallahanD.E., HuY., KashaniR., KawrakowI., LiH., MichalskiJ.M., OlsenJ.R., RobinsonC.G., RodriguezV., SantanamL., TanderupK., VictoriaJ., WootenH.O., YangD., ZoberiI., GreenO.L. and DempseyJ.F., The Dawn of a New Era: First Ever MR-IGRT Treatments - Initial Experiences and Future Implications. Int J Radiat Oncol90, S94 (2014).
7.
ThomsonD., BoylanC., LiptrotT., AitkenheadA., LeeL., YapB., SykesA., RowbottomC. and SlevinN., Evaluation of an automatic segmentation algorithm for definition of head and neck organs at risk. Radiat. Oncol.9, 12 (2014).
8.
BezdekJ.C., HallL.O. and ClarkeL.P., Review of MR Image Segmentation Techniques Using Pattern-Recognition. Med Phys20, 1033 (1993).
9.
BezdekJ.C., Pattern Recognition with Fuzzy Objective Function Algorithms, Kluwer Academic Publishers (1981).
10.
BezdekJ.C., EhrlichR. and FullW., FCM: The fuzzy C-means clustering algorithm. Computers & Geosciences10, 191 (1984).
11.
FengY., BaylyP.V., HuangJ., RobinsonC., DuD., MuticS., ShimonyJ.S., LeuthardtE.C., OkamotoR.J. and HuY., A simulation study to investigate the potential of using Magnetic Resonance Elastography (MRE) to differentiate recurrent tumor and radiation necrosis. Medical Physics40, 540 (2013).
12.
WangX.Y. and BuJ.A., A fast and robust image segmentation using FCM with spatial information. Digit Signal Process20, 1173 (2010).
13.
JainA.K., MurtyM.N. and FlynnP.J., Data clustering: a review. ACM Computing Surveys31, 264 (1999).
14.
PhamD.L., Spatial models for fuzzy clustering. Comput Vis Image Und84, 285 (2001).
15.
KannanS.R., RamathilagamS., DeviR. and SathyaA., Robust kernel FCM in segmentation of breast medical images. Expert Systems with Applications38, 4382 (2011).
16.
ZhangC., WangP. and LiuC., Green Communications and Networks, edited by Y. Yang and M. Ma, Springer Netherlands (2012), pp. 219-226.
17.
NoreenN., HayatK. and MadaniS.A., MRI segmentation through wavelets and fuzzy C-means. World Applied Sciences Journal13, 34 (2011).
18.
KellerB., NathanD., WangY., ZhengY., GeeJ., ConantE. and KontosD., Adaptive Multi-cluster Fuzzy C-Means Segmentation of Breast Parenchymal Tissue in Digital Mammography. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2011, edited by G. Fichtinger, A. Martel and T. Peters, Springer Berlin Heidelberg (2011), pp. 562-569.
19.
PalN.R., PalK., KellerJ.M. and BezdekJ.C., A possibilistic fuzzy C-means clustering algorithm. IEEE Transactions on Fuzzy Systems13, 517 (2005).
20.
KhaliliaM.A., BezdekJ., PopescuM. and KellerJ.M., Improvements to the relational fuzzy C-means clustering algorithm. Pattern Recogn47, 3920 (2014).
21.
CaldairouB., PassatN., HabasP.A., StudholmeC. and RousseauF., A non-local fuzzy segmentation method: Application to brain MRI. Pattern Recogn44, 1916 (2011).
22.
KangJ.Y., MinL.Q., LuanQ.X., LiX. and LiuJ.Z., Novel modified fuzzy C-means algorithm with applications. Digit Signal Process19, 309 (2009).
CaiW.L., ChenS.C. and ZhangD.Q., Fast and robust fuzzy C-means clustering algorithms incorporating local information for image segmentation. Pattern Recogn40, 825 (2007).
25.
XiaY., FengD.G., WangT.J., ZhaoR.C. and ZhangY.N., Image segmentation by clustering of spatial patterns. Pattern Recogn Lett28, 1548 (2007).
26.
AhmedM.N., YamanyS.M., MohamedN., FaragA.A. and MoriartyT., A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data. IEEE T Med Imaging21, 193 (2002).
27.
CaoH., DengH. and WangY., Segmentation of M-FISH images for improved classification of chromosomes with an adaptive fuzzy C-means clustering algorithm. IEEE Transactions on Fuzzy Systems20, 1 (2012).
28.
AstolaL., FusterA. and FlorackL., A Riemannian scalar measure for diffusion tensor images. Pattern Recogn44, 1885 (2011).
29.
HuttenlocherD.P., KlandermanG.A. and RucklidgeW.J., Comparing images using the Hausdorff distance. IEEE Transactions on Pattern Analysis and Machine Intelligence15, 850 (1993).
30.
RunklerT.A. and BezdekJ.C., Alternating cluster estimation: A new tool for clustering and function approximation. IEEE Transactions on Fuzzy Systems7, 377 (1999).
