A Medical Image Segmentation Methods Based on SOM and Wavelet Transforms

摘要

Image segmentation plays a crucial role in many medical imaging applications and is an importantbut inherently difficult problem. The paper discuses the method that classify unsupervised image using aKohonen self-organizing map neural network. This method exits two problems: training time of the network istoo long and the classified result and quantity were bigger influenced by the noise of image. Two-dimensionalDiscrete Wavelet Transforms (DWT) decompose MRI image into the small size and denoise approximationimages. Kohonen self-organizing map neural network is trained with approximation image, then trained neuralnetwork classify pixels of original image. Training time of the network was notability decrease and the classifiedquality influenced by the noise of image was notability reduce. The technique presented here has shown a veryencouraging level of performance for the problem of segmentation in MRI image of the head.