Method and device for predicting dose volume histogram of organ-at-risk of radiotherapy plan

Abstract

The invention provides a method and a device for predicting a dose volume histogram of an organ-at-risk of a radiotherapy plan. The method comprises the following steps: determining an anatomical structure diagram of a region-of-interest and a dose area histogram of an organ-at-risk for model training; determining a prediction model; and inputting the labeled anatomical structure diagram of the region-of-interest of a new patient into the prediction model, and predicting to obtain the organ-at-risk dose volume histogram of the new patient. According to the invention, the method and the deviceare short in prediction time consumption, high in accuracy and suitable for target regions with various prescription doses and patients with various different organ-at-risk anatomical structures, arenot limited to tumor types, can predict different tumor types, are wide in clinical application range, and can achieve automatic setting and plan quality inspection of the individualized reverse planinitial objective function, improve the radiotherapy plan design quality, shorten the design time and solve the problems of time consumption and large plan quality difference of accurate radiotherapyplan design.

Description

technical field [0001] The invention relates to the technical field of medical radiation therapy, in particular to a method and device for predicting a dose volume histogram of an organ at risk in a radiotherapy plan. Background technique [0002] Radiation therapy (radiotherapy, RT) is an important means of tumor treatment, more than 50% of tumor patients need to receive palliative or radical radiotherapy, including intensity-modulated radiation therapy (IMRT), fixed-field intensity-modulated radiation therapy (FB-IMRT), Volume modulated radiotherapy (VMAT) and tomospheric tomotherapy (TOMO) are currently the mainstream techniques for tumor radiotherapy. The purpose of the IMRT plan is to ensure that the tumor target area receives sufficient irradiation dose, and at the same time reduce the exposure dose to normal tissues and organs at risk around the target area as much as possible. However, the design of IMRT plans is complex and time-consuming, relying on the designer’s...

AI Technical Summary

Problems solved by technology

However, in clinical practice, the above methods require manual feature extraction, and these features cannot cover all the anatomical characteristics of patients, especially for complex tumor types (head and neck tumors), which reduces the accuracy and scope of clinical application

Images