Automatic classification of MRI images for three-dimensional volume reconstruction by using general regression neural networks

Classification of three-dimensional MRI images plays an important role in the volume reconstruction for a variety of medical image analysis, computer-aided diagnosis, three-dimensional reconstruction and visualization applications. By using density, gradient magnitude, and curvature as input parameters, and by defining a set of objective enter ions for the classification evaluation, a novel automatic classification method for volume reconstruction of MRI images by using GRNN is presented in this paper, experiment results demonstrate that the proposed method can not only efficient classify MRI images, but also alleviate people from the time-consuming parameter tune process of previous classification method.