Segmentation of 3D MR liver images using synchronised oscillators network

Recent development of three-dimensional imaging techniques with application in medical science demands a development of appropriate 3D image analysis techniques. This paper presents a segmentation method based on three-dimensional network of synchronized oscillators applied for 3D MR liver images. Principles of oscillator network operation were described. The network was tested on sample 3D artificial images, one corrupted by noise and distorted by non-uniform illumination and second containing textures. Segmentation results of liver images were compared and discussed with those obtained with the use of multilayer feedforward perceptron (MLP). It was demonstrated that the advantage of the discussed approach is its resistance to changes of visual image information caused for example by noise, very often present in biomedical images.