Automatic generation method of target region of benign prostatic hyperplasia based on deep neural network

Abstract

The invention discloses a method for automatically generating a target region of prostate hyperplasia based on a deep neural network, which comprises the following steps: 1) obtaining an MRI image of a patient with benign prostatic hyperplasia before operation, and performing slices and data preprocessing; 2) obtaining slices 3) Complete the 3D segmentation of the prostate physiological contour and generate a 3D point cloud model of the prostate physiological structure at the same time; 4) Establish a virtual artificial potential field based on the slices of the central zone of the prostate, and Strengthen the protection of key directions to obtain the distribution of the safety factor on the slice, and then obtain a reasonable target area; 5) perform three-dimensional reconstruction on the prostate slice containing the outline of the target area, and finally obtain a three-dimensional benign prostatic hyperplasia surgery target model. The method of the invention can realize the three-dimensional reconstruction of the prostate and the BPH target area, and has a driving effect on improving the safety and efficiency of the BPH operation.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method for automatically generating a target area for benign prostatic hyperplasia based on a deep neural network. Background technique [0002] Benign prostatic prostate (BPH) is one of the most common symptomatic diseases in middle-aged and elderly men. As you age, the glands in the median zone of the prostate will slowly proliferate, which will restrict the flow of urine and block the urethra. BPH can cause lower urinary tract symptoms (LUTS), including poor urination, frequent urination, sequelae of dribbling, and incomplete urination and nocturia, which seriously affects the normal life of the elderly. With the aging of human society, the incidence and prevalence of BPH and LUTS increase rapidly. BPH affects 8% of men in their 30s and 50% of men in their 50s, and this number will increase to greater than 80% as men reach their 80s. The most effective tr...

AI Technical Summary

Problems solved by technology

Meanwhile, the surgical field needs to be easily modified by the surgeon since the accuracy and robustness of the deep learning method is worse than that of the doctor's experience

As of now, there is no method to automatically reconstruct the target region of BPH under MRI images

Images