Medical brain MRI images segmentation by improved fuzzy C-Means clustering analysis

For the shortcomings of huge calculation in MRI images segmentation with standard Fuzzy C-Mean algorithm (FCM), a new algorithm combined with histogram statistical information of Improved Fast Fuzzy C-Mean algorithm (HF-KFCM) was proposed. Firstly, the method of multi-scale window traverse is used by this algorithm to find the histogram peaks. Then these peaks are defined as the fuzzy clustering initialization centre. Meanwhile, the fast FCM method based on histogram statistic is used as ergodicity to reduce each iteration calculation. The simulation results show that compared with standard FCM algorithm and other improved algorithms, the proposed algorithm can be improved significantly in fuzzy and clustering effectiveness.