Intensity-modulated radiotherapy plan optimization method and application based on predicted dose distribution guidance

Abstract

The invention discloses an intensity-modulated radiation therapy plan optimization method based on predictive dose distribution guidance and application thereof. The method includes the steps of: inputting geometric anatomical structural features of a region of interest of a patient into a trained neural network model so as to obtain three-dimensional dose distribution prediction that endangers anorgan; establishing a field intensity distribution model by taking the three-dimensional dose distribution prediction as optimization guide, wherein an optimization objective function of the field intensity distribution model comprises a target item based on the three-dimensional dose distribution prediction and a target item based on equivalent volume dose; and setting relevant parameters basedon the optimization objective function and performing solution to obtain an intensity-modulated radiation therapy optimization plan. According to the invention, the predicted three-dimensional dose distribution is utilized to guide the optimization of the intensity-modulated radiation therapy plan, so that the individual optimization and the voxel-level precise dose optimization can be realized. According to the invention, the equivalent volume target is constructed to compensate the influence of a loose prediction error on a guidance optimization result, a wider solution space is provided atthe same time, and the advancing direction of plan optimization is ensured.

Description

technical field [0001] The present invention relates to the technical field of radiotherapy plan optimization methods, in particular to an intensity-modulated radiotherapy plan optimization method based on three-dimensional dose distribution guidance of organ-at-risk prediction and its application. Background technique [0002] Intensity Modulated Radiation Therapy (IMRT) is currently the most widely used tumor radiation therapy technique, which can make the dose intensity distribution in the target area more uniform and the dose intensity outside the target area drop sharply, thereby reducing the normal tissue complications Probability (Normal Tissue Complication Probability, NTCP), thus effectively increasing the gain ratio of tumor treatment, compared with conventional radiotherapy has a significant advantage. In the planning design of IMRT, since the ideal dose target or constraint is unknown before the plan design, the plan designer often selects the dose target or cons...

AI Technical Summary

Problems solved by technology

However, the prediction has uncertainty, which will have a great impact on the subsequent optimization guidance. How to reasonably and effectively apply the predicted dose distribution information is an important and difficult point

In 2018, Fan et al. In Automatic treatment planning based on three-dimensional dose distribution predicted from deep learning technique, the optimal solution strategy is to reproduce the predicted dose distribution, and guide the plan optimization by introducing it into the objective function. This method Although a feasible plan can be obtained, the quality of the obtained plan is often only close to the forecast or original plan, thus limiting the optimal solution space to a certain extent

Images