Clustering Based DTI Image Segmentation And 3D Reconstruction

Diffusion Tensor imaging(DTI)is a new type of imaging technique which is based on Diffusion weighted imaging,DTI can provide unique information which can not be provided by other imaging modalities,and has the advantages of non-invasive and no contrast agents.It is the only technique for non-invasive identification of the fine structure of living brain white matter at present.DTI imaging can be used to detect the pathological changes of brain tissue at the molecular level so as to assist in clinical diagnosis.Due to the early onset of certain diseases,such as cerebral ischemia,stroke,dementia,and schizophrenia,some of the water molecules in the brain appear to be abnormally diffused,whereas conventional MRI devices are difficult to detect this change.The extraction and segmentation of tissue regions in DTI data and the method of three-dimensional reconstruction are used to draw them,so as to provide better analytical means for medical auxiliary diagnosis and treatment.Therefore,the following research is mainly done in this paper:1.An improved fuzzy C mean clustering algorithm is proposed,the fuzzy Cmeans clustering algorithm randomly selects the center point of the initial cluster.Because the final clustering result has a certain dependence on the initial clustering center point,the random clustering center point will not affect the final clustering.As a result,the combination of FCM and maximum-minimum distance algorithm is proposed in this paper.The maximum and minimum distances are introduced on the basis of classical FCM,and the improved fuzzy C-means clustering algorithm is validated by the experimental data set.The experimental results show that the improved fuzzy C-means segmentation can obtain more smooth edge information,the wrong segmentation area is reduced,and the segmentation accuracy is improved.2.An adaptive mean drift algorithm is proposed,the basic idea of the mean shift algorithm is to search for the densest area of sample points in the given sample space and drift to the local density maximum along the direction of increasing density.Unlike other clustering algorithms,drifting to find the local maximum is a continuous iterative process,so no prior knowledge is required.However,the bandwidth of the traditional mean shift algorithm is a fixed value and cannot be automatically adjusted according to the distribution of the pixel points.This paper proposes an adaptive mean shift algorithm.By redefining the window function and combining the probability density function of the pixels,the pixel points are different.Probability density applies to different bandwidth values,and the segmentation effect is improved in image segmentation.3.Three-dimensional drawing of corpus callosum was performed,the threedimensional reconstruction is a more intuitive embodiment of medical image segmentation,and the segmentation of medical organizations from a three-dimensional point of view.Surface rendering is an important rendering algorithm.By setting the contour surface of the processed data and rendering it on the peer surface,the final 3D rendering is achieved.Visualization Toolkit VTK,as an open source tool,provides an important platform for 3D reconstruction in surgical simulation,simulation anatomy,medical diagnosis and other fields.In this paper,we have studied the class library and hierarchical structure in VTK by combining the 3D visualization process.Based on the surface rendering algorithm,we have realized the 3D rendering of corpus callosum by combining VTK with Visual Studio 2010 development platform,the experimental results obtained better 3d rendering effect.