| CPC G06T 7/11 (2017.01) [A61N 5/1039 (2013.01); G06T 2200/24 (2013.01); G06T 2207/10081 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20092 (2013.01); G06T 2207/30004 (2013.01)] | 18 Claims |

|
1. A method, comprising:
executing, by one or more processors coupled to a non-transitory memory, a first segmentation model that receives a medical image of a patient as an input and generates an initial segmentation of the medical image for a radiotherapy treatment of the patient;
identifying, by the one or more processors, a refinement to the initial segmentation generated in response to an input at a user interface presenting the initial segmentation;
executing, by the one or more processors, a second segmentation model that receives the medical image, the initial segmentation of the medical image, and the refinement as input and generates a refined segmentation of the medical image;
identifying, by the one or more processors, a correction to the refined segmentation of the medical image;
fine-tuning, by the one or more processors, the first segmentation model for the patient based on the medical image and the correction to the refined segmentation to generate a first fine-tuned segmentation model; and
fine-tuning, by the one or more processors, the second segmentation model for the patient based on the medical image, the initial segmentation, and the correction to the refined segmentation to generate a second fine-tuned segmentation model.
|