Research On Medical Image Processing Method Based On Statistical Inverse Proble Theory

The role of medical image technology in the medical field is becoming more and more obvious.Doctors can use medical image technology to more accurately understand the patient’s condition and make accurate judgments and diagnosis and treatment.But because the medical image itself has noise and other factors,in order to understand the disease accurately,medical image restoration and medical image segmentation technology is particularly important.In medical image restoration,the traditional image restoration effect is relatively poor and the time complexity is higher.This paper deals with image restoration based on statistical inversion theory,and makes full use of the transcendental information of medical images.The Gaussian white noise density function with positive term constraints is added to the prior test function,which has a good robustness to noise.By constructing the MCMC algorithm to estimate the posterior probability density function,the effect of simulated error on the medical image restoration model is analyzed.The current medical image segmentation technology can not satisfy the high precision and high strength of its classification.The traditional image segmentation algorithm needs a good initial boundary value,and the boundary value selected by the current segmentation algorithm can not deal with the problem of medical image boundary blurring.In this paper,the medical image is preprocessed,the feature is extracted,and the four texture features are classified based on Metropolis-SA algorithm.The MSA algorithm is faster in iteration speed,higher accuracy,and less consistent error.