Three-dimensional dose distribution prediction method for intensity-modulated radiotherapy planning based on deep network learning

Abstract

The invention provides a method for predicting the three-dimensional dose distribution of an intensity-modulated radiotherapy plan based on deep learning. The method includes: collecting effective intensity-modulated radiotherapy planning data to form a case database; extracting the three-dimensional anatomical structure contour features of each patient's region of interest from the case database; dividing the three-dimensional anatomical structure contour of the patient's region of interest into several binary Two-dimensional contour slice map; extract the dose characteristics of each patient from the case database, and divide it into several two-dimensional dose slice distribution maps; build a deep convolutional network, input the patient's two-dimensional contour slice map and the corresponding two-dimensional dose slice distribution Figure, the association model between anatomical structure contour features and dose features is obtained through model training; the three-dimensional dose distribution of new patients is predicted using the trained association model. By using the method of the present invention, the correlation between anatomical structure features and dose features can be effectively obtained, and the accuracy of dose prediction can be improved.

Description

Technical field [0001] The present invention relates to the field of intelligent radiation therapy, and more particularly to prediction methods of three-dimensional dose distribution based on deep network learning. Background technique [0002] Tumor radiotherapy, with its unique advantages, one of the main means of the World Health Organization proposed in tumor treatment. Its main goal is to reduce the dose deposition of the surrounding normal tissue while ensuring a particular dose while ensuring a particular dose. Improve the local control rate of tumors. Military radiotherapy is a kind of self-shaped radiation treatment, which is one of three-dimensional suitable radiotherapy, requiring radiation inner dose intensity to regulate. It makes the distribution of the radiotherapy dose consistent with the shape of the target area, and the high dose of a uniform distribution is received, ensuring the killing of tumor cells, and improves therapeutic effect of radiotherapy. [0003] ...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the defects of the above-mentioned prior art, and provide a three-dimensional dose distribution prediction method suitable for intensity-modulated radiotherapy planning, so as to solve the problem of incomplete description of anatomical information in the prior art and the inability to simultaneously predict multiple regions of interest, etc. question

Images