Hybrid multiresolution Slantlet transform and fuzzy c-means clustering approach for normal-pathological brain MR image segregation

Abstract 

The paper presents a new approach for automated segregation of brain MR images, using an improved orthogonal discrete wavelet transform (DWT), known as the Slantlet transform (ST), and a fuzzy c-means (FCM) clustering approach. ST has excellent time-frequency resolution characteristics and these can be achieved with shorter supports for the filter, compared to DWT employed for identical situations. FCM clustering, on the other hand, can provide efficient classification results, if it is implemented for well-processed input feature vectors. Thus, by combining both the ST and the FCM clustering approaches, a hybrid scheme has been developed that can segregate brain MR images. This automated tool when developed can infer whether the input image is that of a normal brain or a pathological brain. The proposed technique has been applied to several benchmark brain MR images and the results reveal excellent accuracy in characterizing human brain MR imaging.

Keywords: Slantlet transform (ST), Fuzzy c-means (FCM) clustering, Magnetic resonance imaging (MRI), Time-frequency localization, Image histogram