Method and system for synthesizing real-time image by using optical surface motion signals

A method for synthesizing a real-time image by using optical surface motion signals, comprising:

• acquiring an image of a patient before a treatment and real-time optical surface data of the patient during the treatment;
• and
• synthesizing the image of the patient before the treatment and the real-time optical surface data of the patient during the treatment into the real-time image synchronized with a change of the optical surface motion signals according to a mapping relationship.

A deep learning network model training system for synthesizing a real-time image by using optical surface motion signals, comprising a deep learning network model unit;

• wherein the deep learning network model unit is configured to train a deep learning network model to obtain a mapping relationship between body surface data and internal structure data of a patient;
• the deep learning network model is trained on a 4D image data set, an input of the deep learning network model comprises a 4D image at a first phase and optical surface data or body surface outer contour data at a second phase, and an output of the deep learning network model is an image at the second phase.

A deep learning network model training method for synthesizing a real-time image by using optical surface motion signals, comprising:

• training a deep learning network model to obtain a mapping relationship between body surface data and internal structure data of a patient, wherein
• the deep learning network model is trained on a 4D image data set, an input of the deep learning network model comprises a 4D image at a first phase and optical surface data or body surface outer contour data at a second phase, and an output of the deep learning network model is an image at the second phase.