Title :
Segmentation in MRI of ophthalmology using a robust-type clustering algorithm
Author :
Hung, Wen-Liang ; Yang, Miin-Shen ; Chen, De-Hua
Author_Institution :
Grad. Inst. of Comput. Sci., Nat. Hsinchu Univ. of Educ., Hsinchu, Taiwan
Abstract :
In this paper we propose a robust-type clustering algorithm that has more accuracy than the alternative FCM (AFCM) proposed by Wu and Yang. Moreover, to speed up the proposed algorithm, we use the suppressed idea to modify it. The modified robust-type clustering algorithm presents fast convergence speed and also robustness. Finally, this algorithm is applied in the segmentation of the magnetic resonance image (MRI) of an ophthalmic patient. In our comparisons of the proposed algorithm with the AFCM for these MRI segmentation results, we find that the proposed algorithm provides better detection of abnormal tissue than AFCM.
Keywords :
biomedical MRI; image segmentation; patient diagnosis; pattern clustering; MRI segmentation; abnormal tissue; fuzzy c-means; magnetic resonance image; ophthalmic patient; ophthalmology; robust-type clustering algorithm; Clustering algorithms; Convergence; Euclidean distance; Fuzzy set theory; Image segmentation; Magnetic analysis; Magnetic resonance; Magnetic resonance imaging; Partitioning algorithms; Robustness;
Conference_Titel :
Fuzzy Systems, 2009. FUZZ-IEEE 2009. IEEE International Conference on
Conference_Location :
Jeju Island
Print_ISBN :
978-1-4244-3596-8
Electronic_ISBN :
1098-7584
DOI :
10.1109/FUZZY.2009.5277206