كاهش بعد داده هاي تصاوير تشديد مغناطيس مغز با استفاده از شكبه عصبي آموزشي يافته توسط الگوريتم ژني

In this paper, a method of dimensionality reduction for MR image sequence data of brain, to a three-dimensional space is presented..Reduction of dimensions is motivated by the need,. to visualize the distribution of data and interactively. segment the MR image sequence. New feature space is extracted using a non-linear _neural network,. A genetic algorithm is used .to; search, for. the neural network. parameters such that. the transformed data in the network output optimize a. specific objective function. Three objective functions are proposed based on Sammonʹs cost function where in two .of them a constraint is added to. the cost function. The data in the three-dimensional (3-D)output feature space is visualized using .the perspective image of the 3-D histogram. MR images are. segmented interactively by determining the bluster centers in the perspective image The results of the proposed methods are compared with those Of Linear Transformation and Back-Propagation Neural Network (BPNN) methods For simulated MR images, two of the proposed criterions produce better results in terms ofʹ cluster separation. Based on 10 real MR image sequence data, the same two criterions result lower segmentation error rates.