Research On Medical Image Segmentation Algorithm With Anti-Noise And Bias Field Correction

In recent years,the medical equipment system has been continuously improved,and medical imaging technology has become more and more mature,especially in clinical medicine,which can effectively improve the diagnosis rate of doctors.As the focus of current medical image segmentation,magnetic resonance imaging(MRI)plays an important role in brain tissue segmentation.The brain tissue is mainly composed of three major parts:gray matter(GM),white matter(WM)and cerebro-spinal fluid(CSF).Accurate segmentation of brain tissue can effectively conduct quantitative analysis of brain regions,so as to accurately evaluate brain diseases.Although existing segmentation algorithms can be applied to different types of images to complete segmentation,these algorithms have the same or similar problems when dealing with brain MR images:Firstly,the segmentation of brain MR images with bias field is greatly affected by bias field and the segmentation result is not ideal because of the inadequate removal of bias field.Secondly,in the segmentation of brain MR images with noise,the algorithm is sensitive to noise and weak in robustness due to the insufficient use of the relationship between the neighboring pixels.To solve these problems,this paper proposes an MR image segmentation method(MPCFCM)with anti-noise and bias field correction,which implements segmentation by point-to-plane algebraic distance constraint.Different from traditional point-based clustering methods,a hyper-center of clustering(i.e.,plane)model is defined,and data clustering is completed by optimizing different planes.In addition,to realize the point clustering with plane,a key problem that how to measure the distance from point to plane needs to be solved.This paper adopts the algebraic distance as a measure function,which can avoid the nonlinear problem caused by a direct calculation of the minimum distance between a point and a plane,thus simplifying the computational complexity.In the proposed algorithm,spatial distance,local variance and gray-difference of neighbors are combined to connstuct a new antinoise smoothing factor for constraining the energy function so that the algorithm has better anti-noise and retains more image details.Finally,the singular value decomposition is performed on the loss energy,some information removed is re-added to the segmented image to repair it.The experimental results show that MPCFCM algorithm can better correct bias field and eliminate noise and obtain accurate image segmentation results with more details.The medical image segmentation method with anti-noise and bias field correction proposed in this paper can effectively estimate the bias field and suppress the influence of noise,at the same time,it can segment the brain tissue accurately and provide a reliable basis for disease diagnosis and medical data visualization.It provides a new idea for segmenting medical images with bias fields and noise in the future.