The Application And Research Of Lung Region Segmentation In Chest X-ray Images Based On Active Shape Model

Medical image segmentation plays a very important part in biomedical images, and clinical diagnosis, pathological analysis; it is also the foundation of medical image processing, analysis and understanding. As the complexity of human anatomy, the irregular of tissues and the differences between individuals, the traditional image segmentation algorithms are not so satisfied. So, it is imperative for us to find an effective method for medical image segmentationThe deformable Model segmentation method shows its unique advantages and comprehensive applicability in dealing with diverse, complex medical images. Therefore, this article proposed a segmentation technology based on the deformable model—Active Shape Model. Firstly, we selected some shape examples to be training set. In order to model a shape,we represented it by a set of points by placing points around the boundary. This must be done for each shape in the training set. Then we aligned the training set and captured the statistics of a set of aligned shapes. In order to make use of the statistics of the grey level in regions around each of the labeled model points,we should model the gray level appearance. In image search,we calculate a suggested movement for each model point and compute changes in the pose and shape parameters,then update the pose and shape parameters. The procedure is iterative,it repeats until no significant change results. The final shape is the shape we wanted.In this paper, the Active Shape Model algorithm are researched and improved based on medical image, and the mainly work is as follows:(1)This article analyzed the currently domestic and foreign image segmentation algorithm, and focused on the Active Shape Model (ASM) algorithm to achieve, including the Point Distribution Model, Gray-level Model, the model searching process and several other aspects.(2)Based on the traditional Active Shape Model algorithm, some improvements are made, including multi-resolution search strategy, semi-automatic marker extraction, the adjustment of initial location. And combined with Gabor wavelet, Gabor Jet was used instead of gray-level models in the multi-resolution search strategy, in order to get better segmentation results.(3)Gabor ASM method and traditional ASM algorithm are used in medical iamge segmentation experiments, including: lung segmentation in chest DR images, lung area extraction in CT images, and brain corpus callosum segmentation in MR image. The statistical error comparison between the two algorithms is made. The experimental results showed that compared with the traditional ASM algorithm, there is a greater improvements in the accuracy and precision of the proposed algorithm in medical image segmentation,.