Rectal cancer radiotherapy plan automatic design method based on deep learning

Abstract

The invention provides a rectal cancer radiotherapy plan automatic design method based on deep learning. The method comprises the steps: establishing a U-Net neural network used for deep learning, andestablishing a case database, wherein the case database is clinical intensity modulated radiotherapy plan data of rectal cancer; performing deep learning on the case database to train the U-Net neural network; transmitting a img file of the CT positioning data to the trained U-Net neural network to obtain a prediction target area and prediction dose distribution output by the U-Net neural network; obtaining a dose objective function according to the prediction target area and the prediction dose distribution; and designing a radiotherapy plan by using a Pinnacle planning system according to the prediction target area and the dose objective function. Therefore, the rectal cancer radiotherapy plan automatic design method based on deep learning integrates the target area sketching technology, the dose prediction technology and the automatic planning technology, and the full-automatic design process of the individualized radiotherapy plan is realized in combination with the Pinnacle plansystem.

Description

technical field [0001] The invention relates to the technical field of medical radiation therapy, in particular to an automatic design method for rectal cancer radiotherapy plan based on deep learning. Background technique [0002] Intensity-modulated radiation therapy (IMRT) is a common radiation therapy method. This technology can meet the requirements of high dose distribution and high conformality of the target area, while effectively protecting surrounding normal tissues and organs at risk from unnecessary radiation or less. , thus becoming one of the main treatment modalities for many tumor types today. Due to the specificity of the geometric structure of each patient, the performance of the corresponding radiotherapy plan should be different. Therefore, in order to effectively ensure that the patient receives the best treatment, the design process of the radiotherapy plan should take this specificity into account, so that the patient can be targeted to the patient. S...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an automatic design method for rectal cancer radiotherapy plan based on deep learning to solve the problem that the plan design method in the prior art is limited to part of the process and not complete enough

Images