Spatial Fuzzy Clustering and Level Set Segmentation

Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation

Description

The performance of the level set segmentation is subject to appropriate initialization and optimal configuration of controlling parameters, which require substantial manual intervention. A new fuzzy level set algorithm is proposed in this paper to facilitate medical image segmentation. It is able to directly evolve from the initial segmentation by spatial fuzzy clustering. The controlling parameters of level set evolution are also estimated from the results of fuzzy clustering. Moreover the fuzzy level set algorithm is enhanced with locally regularized evolution. Such improvements facilitate level set manipulation and lead to more robust segmentation. Performance evaluation of the proposed algorithm was carried on medical images from different modalities. The results confirm its effectiveness for medical image segmentation.

If you think it is helpful, please cite:
----------------------------------------
B.N. Li, C.K. Chui, S. Chang, S.H. Ong (2011) Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation. Computers in Biology and Medicine 41(1) 1-10.
----------------------------------------

• Required Products: Image Processing Toolbox; Fuzzy Logic Toolbox
• MATLAB release: MATLAB 7.8 (R2009a)

[zey]

 

[Pham Truong]

 

[Tripp]

Can't find the function initfcm() invoked in SFCM2D at line 39

[ABing]

To Tripp,

initfcm() is a subroutine by Matlab :D Of course, it is not difficult to implement such function by ourselves.

[Tripp]

So then this code requires the Fuzzy Logic Toolbox? It would be helpful to list that under "required products."

[Jamuna]

 

[Jamuna]

very nice code...it perfectly worked for the fundus images I used...

[paramveer sran]

can anyone tell me how to calculate imgfcm and beta/ thank you

[ABing]

Hi, Sran,

Here is a subroutine SFCM2D for calculating imgfcm. You may observe the clustering results by changing the index.

Once you design the index of a desired subregion, the subroutine fuzzyLSM will figure out beta automatically.

Rgds,