System and method for learning models of radiotherapy treatment plans to predict radiotherapy dose distributions

Abstract

The present invention relates to systems and methods for developing radiotherapy treatment plans though the use of machine learning approaches and neural network components. A neural network is trained using one or more three-dimensional medical images, one or more three-dimensional anatomy maps, and one or more dose distributions to predict a fluence map or a dose map. During training the neuralnetwork receives a predicted dose distribution determined by the neural network that is compared to an expected dose distribution. Iteratively the comparison is performed until a predetermined threshold is achieved. The trained neural network is then utilized to provide a three-dimensional dose distribution.

Description

[0001] Cross References to Related Applications

[0002] This application claims the full benefit and priority of U.S. Provisional Patent Application No. 62 / 384,192, filed September 7, 2016, entitled "Learning Models of RadiotherapyTreatment Plans to Predict Therapy Dose Distributions," the disclosure of which is for all purposes Incorporated herein by reference in its entirety. technical field

[0003] The present invention generally relates to radiation therapy systems. More specifically, embodiments of the disclosed invention present systems and methods for developing and implementing radiation therapy planning within a radiation therapy system utilizing machine learning algorithms and neural networks. Background technique

[0004] Radiation therapy has been used to treat tumors in human (and animal) tissue. Intensity Modulated Radiation Therapy (IMRT) and Volume Modulated Arc Therapy (VMAT) have become the standard of care in modern cancer radiation therapy, offering g...

Images