Research On Medical Image Segmentation And 3D Reconstruction Algorithm

The main work of this paper is image segmentation technology study in medical image 3D visualization and the realization of medical image 3D reconstruction. Medical image 3D visualization is to use the 2D images information to reconstruct 3D image, then stereoscopic display, and conduct various kinds of medical image data processing.Medical image segmentation is to divide the medical image into several regions, and then extract the interested regions of tissues or organs. Segmentation is an essential step in the medical image processing, the accuracy of segmentation is very important for the follow-up medical image processing and the doctor to assess the real situation of the diseases. Medical image segmentation is a classic problem in image segmentation field, because of the complexity of medical images, so far there is not any all-purpose segmentation method. In this paper, the original segmentation methods, especially the methods that are common used in recent years are in-depth studied, then a fuzzy C-means clustering algorithm for image segmentation based on ant colony algorithm and a sequence medical image segmentation algorithm based on the improved active contour model are proposed. First, this paper uses ant algorithm's overall robustness advantages to get the cluster center and the clusters number of the image, and then make the results as the initial cluster centers and the number of clusters of fuzzy C-means clustering algorithm. This algorithm overcomes the shortcomings of the traditional FCM clustering algorithm. On this basis, aiming at the disability that original active contour model is more sensitive to initial contour, the paper establishes an initial contour forecast model that uses segmented image contours forecast undivided images' initial contours. Then this algorithm defines a new energy function of the active contour model curve, because in the process of energy minimization, the curve is likely to converge to a local optimum, this algorithm combines the regional information and edge information of image as image energy, so that the model can target the convergence of the real edge better. Experimental results demonstrate the effectiveness of these two improved algorithms.3D image reconstruction technique is to get realistic 3D structure information from the 2D sequence images of objects, called the prototype of the objects. By this way, users can more easily to observe and analyze the symptom in a multi-levels and multi-angle way, and this increases the accuracy and scientific of medical diagnosis a lot, so 3D image reconstruction technique will play a very important role in clinical diagnosis assisted in the clinical diagnosis. This paper analyzes 3D medical image reconstruction technique deeply, and compares the advantages and disadvantages of the various methods. Then, it realizes the 3D medical image reconstruction separately use surface rendering and volume rendering method in the MATLAB environment.At last, a summary of the research work is concretely proposed and future improvements on the basis of this paper are suggested.