Image segmentation is an important step in most medical image analysis tasks. An effective image segmentation method helps clinicians and patients in image-guided surgery, radiotherapy, early disease detection, volumetric measurement, and three-dimensional visualization. The fuzzy c-means
(FCM) clustering algorithm is one of the most popular methods used for medical image segmentation. However, it does not produce satisfactory results for images with noise and intensity inhomogeneities. Hence, a wavelet-based FCM clustering algorithm is proposed in this work. An advanced wavelet
transform, such as the dual-tree complex wavelet transform (DT-CWT), is proposed to sharpen the edges and to avoid segmentation error caused by noise. An appropriate level of decomposition is selected on the basis of the images. The FCM clustering technique is applied on the wavelet transformed
image by selecting an optimal number of clusters. The combination of DT-CWT and FCM clustering technique produces an effective segmentation result. The conventional discrete wavelet transform (DWT) was also tested, but it was unable to give an efficient segmentation result when combined with
FCM. Experiments were conducted on real T1-weighted magnetic resonance (MR) images to validate the proposed algorithm. Moreover, a comparison was performed with different state-of-the-art algorithms to show the superiority of our proposed method.
Unsupervised colour image segmentation using dual-tree complex wavelet transform