Method and system for synthesizing real-time image by using optical surface motion signals
A system for synthesizing a real-time image by using optical surface motion signals includes: an acquisition unit configured to acquire an image of a patient before treatment and real-time optical surface data of the patient during treatment; and a synthesis unit configured to synthesize the acquired image of the patient before treatment and the real-time optical surface data of the patient during treatment into a real-time image that is synchronized with a change of the optical surface motion signals according to a certain mapping relationship. The synthesized real-time image achieves precise, real-time, non-invasive, visual dynamic tracking of the moving target volumes without concomitant dose during radiotherapy on the existing traditional accelerator platform.
1. A system for synthesizing a real-time image by using optical surface motion signals, comprising: an acquisition unit and a synthesis unit; wherein
the acquisition unit is configured to acquire an image of a patient before a treatment and real-time optical surface data of the patient during the treatment; and
the synthesis unit is configured to implement a synthesizing of 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, wherein the real-time optical surface data and the optical surface motion signals are measurements of a movement of a surface of the patient's body obtained from optical light.
2. The system according to claim 1 , wherein,
the image of the patient before the treatment is a 4D image acquired directly before the treatment, or a LID image reconstructed from a 3D image of the patient before the treatment.
3. The system according to claim 2 , further comprising a deep learning network model unit with the mapping relationship; wherein
the deep learning network model unit is configured to obtain the image of the patient at a first phase before the treatment and the real-time optical surface data of the patient at a second phase during the treatment, input a deep learning network model, output an image at the second phase, and combine images at continuous phases to obtain a real-time dynamic 4D image synchronized with the change of the optical surface motion signals.
4. The system according to claim 1 , wherein,
the real-time optical surface data is standardized prior to 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 the change of the optical surface motion signals according to the mapping relationship.
5. The system according to claim 4 , further comprising a deep learning network model unit with the mapping relationship; wherein
the deep learning network model unit is configured to obtain the image of the patient at a first phase before the treatment and the real-time optical surface data of the patient at a second phase during the treatment, input a deep learning network model, output an image at the second phase, and combine images at continuous phases to obtain a real-time dynamic 4D image synchronized with the change of the optical surface motion signals.
6. The system according to claim 1 , further comprising a deep learning network model unit with the mapping relationship; wherein
the deep learning network model unit is configured to obtain the image of the patient at a first phase before the treatment and the real-time optical surface data of the patient at a second phase during the treatment, input a deep learning network model, output an image at the second phase, and combine images at continuous phases to obtain a real-time dynamic 4D image synchronized with the change of the optical surface motion signals.
7. The system of claim 1 , wherein said synthesizing into the real-time image is performed by employing body surface outer contour data, extracted from said image of the patient before the treatment and the real-time optical surface data, and wherein the body surface outer contour data and the real-time optical surface data are respectively defined as: a) a corresponding 2D height distribution of points of the surface of the patient's body relative to a coronal plane, or b) a corresponding 3D binary mask of a contour of the surface of the patient's body.
8. The system of claim 1 , wherein said synthesizing into the real-time image is performed by employing body surface outer contour data extracted from said image of the patient before the treatment and the real-time optical surface data, and wherein the body surface outer contour data and the real-time optical surface data are respectively defined as a corresponding 2D height distribution of points of the surface of the patient's body relative to a coronal plane.
9. The system of claim 1 , wherein said synthesizing into the real-time image is performed by employing body surface outer contour data extracted from said image of the patient before the treatment and the real-time optical surface data, and wherein the body surface outer contour data and the real-time optical surface data are respectively defined as a corresponding 3D binary mask of a contour of the surface of the patient's body.
10. 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, wherein the real-time optical surface data and the optical surface motion signals are measurements of a movement of a surface of the patient's body obtained from optical light.
11. The method according to claim 10 , wherein,
the image of the patient before the treatment is a 4D image acquired directly before the treatment or a 4 D image reconstructed from a 3D image of the patient before the treatment.
12. The method according to claim 11 , wherein,
the mapping relationship is obtained by a deep learning network model; and
the method further comprises:
obtaining the image of the patient at a first phase before the treatment and the real-time optical surface data of the patient at a second phase during the treatment,
inputting the deep learning network model,
outputting an image at the second phase, and
combining images at continuous phases to obtain a real-time dynamic 4D image synchronized with the change of the optical surface motion signals.
13. The method according to claim 10 , further comprising
standardizing the real-time optical surface data prior to 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 the change of the optical surface motion signals according to the mapping relationship.
14. The method according to claim 13 , wherein,
the mapping relationship is obtained by a deep learning network model; and
the method further comprises:
obtaining the image of the patient at a first phase before the treatment and the real-time optical surface data of the patient at a second phase during the treatment,
inputting the deep learning network model,
outputting an image at the second phase, and
combining images at continuous phases to obtain a real-time dynamic 4D image synchronized with the change of the optical surface motion signals.
15. The method according to claim 10 , wherein,
the mapping relationship is obtained by a deep learning network model; and
the method further comprises:
obtaining the image of the patient at a first phase before the treatment and the real-time optical surface data of the patient at a second phase during the treatment,
inputting the deep learning network model,
outputting an image at the second phase, and
combining images at continuous phases to obtain a real-time dynamic 4D image synchronized with the change of the optical surface motion signals.
16. The method of claim 10 , wherein said synthesizing into the real-time image is performed by employing body surface outer contour data extracted from said image of the patient before the treatment and the real-time optical surface data, and wherein the body surface outer contour data and the real-time optical surface data are respectively defined as: a) a corresponding 2D height distribution of points of the surface of the patient's body relative to a coronal plane, or b) a corresponding 3D binary mask of a contour of the surface of the patient's body.
17. The method of claim 10 , wherein said synthesizing into the real-time image is performed by employing body surface outer contour data extracted from said image of the patient before the treatment and the real-time optical surface data, and wherein the body surface outer contour data and the real-time optical surface data are respectively defined as a corresponding 2D height distribution of points of the surface of the patient's body relative to a coronal plane.
18. The method of claim 10 , wherein said synthesizing into the real-time image is performed by employing body surface outer contour data extracted from said image of the patient before the treatment and the real-time optical surface data, and wherein the body surface outer contour data and the real-time optical surface data are respectively defined as a corresponding 3D binary mask of a contour of the surface of the patient's body.