Method for segmenting radiotherapy image by combining deep neural network and probability graph model

Abstract

The invention discloses a method for segmenting a radiotherapy image by combining a deep neural network and a probability graph model. The method comprises the following steps: before image segmentation, forming a learning set by using a group of two-dimensional medical images, pre-segmented images and benchmark annotation data corresponding to the medical images so as to train a deep neural network model; during image segmentation, using a deep neural network model for processing an input image and a pre-segmented image to obtain a group of multi-channel score maps, each pixel channel uniquely corresponding to a certain region of interest, and a score value in the pixel channel representing the probability that a pixel belongs to the region of interest corresponding to the channel; usinga probability graph model method for each multi-channel score graph to generate a multi-channel annotation graph, wherein each channel image represents the position annotation of the region of interest corresponding to the channel; and for each original two-dimensional medical image, fusing the multi-channel annotation images into a final annotation image as an image segmentation result.

Description

technical field [0001] The invention relates to a method for segmenting medical images, in particular to a method for segmenting radiotherapy images by combining a deep neural network and a probability map model. Background technique [0002] Radiation therapy refers to treatments that use high-energy radiation to kill tumor cells in order to cure or shrink tumors. The types of radiation beams used in this method include: X-rays, gamma rays, and / or charged particle beams, among others. When the absorbed dose in the target area exceeds a certain level, high-energy radiation will directly damage the DNA molecules of abnormal cells in the area, or generate charged particles and cause indirect damage; some severely damaged cells will stop dividing or directly die. However, the process also affects healthy cells located in surrounding vital organs or other human anatomy. On the one hand, the radiotherapy dose designed for the target area is usually sufficient to cause a greater...

AI Technical Summary

Problems solved by technology

[0007] To sum up, the current radiotherapy process faces a dilemma: in order to treat more patients within a unit time, the course of treatment needs to be shortened; but in order to ensure the accuracy and efficacy of treatment, the time for treatment planning needs to be appropriately increased

Images