Research Of Medical Image Segmentation Algorithm Based On The Cloud Model

At present,medical imaging technology plays an important role in medical diagnosis.Due to the influence of the imaging device,the local body effect,the patient's postural movement and the uniform linear motion of the examination bed,there are noise,artifacts,edge blur and unevenness of the signal intensity etc.in medical images.Cloud model is a model to use the language to describe the uncertainty conversion between qualitative of the concept and it value.It combines the fuzziness and the randomness,and forms an intermapping between the qualitative and quantitative information.It is an approximate normal distribution rather than a strict normal distribution.And its characteristic can well solve the poor edge segmentation faults.Therefore,this paper uses two methods based on cloud model to explore the division of medical images,and through the theoretical and experimental aspects to verify its effectiveness.The specific research content includes the following two aspects:1.This paper proposes a new graph cut medical image partitioning method that calculates image data using cloud model for constructing the objective functions(CM-GC).In the objective function,it contains a boundary preserving smooth term and a data item which evaluates the deviation of each pixel that belongs to different regions.The core method models the foreground object and background of the images as cloud models by the back cloud generator.The data item is calculated with the X-condition cloud generator.We use the membership degree between each pixel to calculate the similarity of the neighbor pixel established as the smooth term.The energy minimization is completed with the minimum cut theory and the graph cut iterations.In contrast to segmentation results with discontinuous edges using conventional graph cut method,this method has better generality and accuracy.2.This paper proposes a new medical image segmentation method based on cloud model and level set.The region-based level set segmentation method is generally based on the gray-scale uniform distribution of images,so these algorithms are usually poor uneven gray-scale image segmentation results.In order to solve this problem,the CM-LS algorithm uses the cloud model and the level set algorithm to use the image.First,the cloud transform algorithm is used to divide the image into several cloud superimpositions,and then through the "soft or cloud" on the sub-cloud model to get the foreground and background of the cloud model.According to the formula,the level set function is initialized,and the iterative solution level set function is used to get the final segmentation result.The cloud model method can effectively degrade the boundaries of uneven grayscale images,which can not only save the convergence instability caused by the intervention of human intervention,but also can accelerate the convergence of the level set function.In addition,the use of cloud model algorithm to initialize the level set function can reduce the level set function on the noise sensitive and weak boundary image segmentation effect of the problem.