Method and system for non-contact patient registration in image-guided surgery
Systems and methods used to perform touchless registration of images for surgical navigation are disclosed. In some embodiments, the systems include a 3-D scanning device to capture spatial data of a region of interest of a patient and a reference frame. A digital mesh model is generated from the spatial data. A reference frame model is registered with the digital mesh model. Anatomical features of the digital mesh model and a patient registration model are utilized to register the digital mesh model with the patient registration model. A position of a surgical instrument is tracked relative to the reference frame and the patient registration model.
1. A method of touchless registration for a surgical procedure, comprising:
scanning a region of interest (ROI) of a patient and a reference frame using a 3-D scanning device to capture a collection of spatial data points;
constructing an ROI digital mesh model from the collection of spatial data points;
detecting the reference frame in the collection of spatial data points;
constructing a reference frame digital mesh from the spatial data points;
registering a reference frame registration model with the reference frame mesh model;
detecting an anatomical feature of the ROI digital mesh model and a corresponding anatomical feature of a patient registration model utilizing a facial detection algorithm;
weighting the anatomical feature of the ROI digital mesh model and the corresponding anatomical feature of the patient registration model; and
registering the ROI digital mesh model with the patient registration model utilizing the weighted anatomical features of the ROI digital mesh model and the patient registration model to generate a navigation space;
wherein the weighting of the anatomical feature is based on a level of repeatability of positions of the anatomical features relative to the ROI.
2. The method of claim 1 , wherein the anatomical feature comprises any one of a region of a nose, a region of an eye, a region of an ear, a region of a mouth, region of a cheek, a region of an eyebrow, a region of a jaw, and any combination thereof.
3. The method of claim 1 , further comprising creating the patient registration model from any one of computed tomography (CT), magnetic resonance image (MRI), computer tomography angiography (CTA), magnetic resonance angiography (MRA), intraoperative CT images.
4. The method of claim 1 , further comprising:
detecting a location and position of the reference frame digital mesh model within a digital mesh model.
5. The method of claim 1 , further comprising displaying the registered reference frame registration model with the ROI digital mesh model.
6. The method of claim 4 , wherein the digital mesh model comprises: the ROI digital mesh model; and
the reference frame digital mesh model.
7. The method of claim 1 , wherein the reference frame comprises a structure disposed adjacent the ROI.
8. The method of claim 1 , wherein the reference frame comprises an electromagnetic (EM) reference frame or an optical reference frame coupled to the patient within the ROI.
9. A method of touchless registration for a surgical procedure, comprising:
scanning a region of interest (ROI) of a patient and a reference frame using a 3-D scanning device to capture a collection of spatial data points;
constructing an ROI digital mesh model from the collection of spatial data points;
detecting the reference frame in the collection of spatial data points;
detecting an anatomical feature of the ROI digital mesh model and a corresponding anatomical feature of a patient registration model utilizing a facial detection algorithm;
weighting the anatomical feature of the ROI digital mesh model and the corresponding anatomical feature of the patient registration model; and
registering the ROI digital mesh model with the patient registration model utilizing the weighted anatomical features of the ROI digital mesh model and the patient registration model to generate a navigation space;
wherein the weighting of the anatomical feature is based on a level of repeatability of positions of the anatomical features relative to the ROI.
10. The method of claim 9 , wherein the weighting is high when the position of the anatomical feature is repeatable relative to the ROI.
11. The method of claim 10 , wherein in the high weighted anatomical feature comprises any one of the bony contours around an eye, an eyebrow, a nose, a forehead region and any combination thereof.
12. The method of claim 9 , wherein the weighting is low when the position of the anatomical feature is variable relative to the ROI.
13. The method of claim 12 , wherein the low weighted anatomical feature is removed from the facial detection algorithm.
14. The method of claim 12 , wherein the low weighted anatomical feature comprises any one a cheek region, a jaw region, a back of the head region, a region of an ear and any combination thereof.
15. A method of non-contact registration for an image guided surgical procedure, comprising:
3-D scanning a region of interest (ROI) of a patient and a reference frame structure using a 3-D scanning device to capture a collection of spatial data points;
constructing a digital mesh model from the collection of spatial data points, wherein the digital mesh model comprises:
an ROI mesh model; and
a reference frame mesh model;
determining a location and a position of the reference frame mesh model within the digital mesh model;
registering the reference frame mesh model with a registration reference frame model;
detecting an anatomical feature of the ROI mesh model and a corresponding anatomical feature of a patient registration model utilizing a facial detection algorithm;
weighting the anatomical feature of the ROI digital mesh model and the corresponding anatomical feature of the patient registration model utilizing the facial detection algorithm; and
registering the ROI mesh model with the patient registration model utilizing the weighted anatomical feature of the ROI digital mesh model and the patient registration model;
wherein the weighting of the anatomical feature is based on a level of repeatability of a position of the anatomical feature relative to the ROI.
16. The method of claim 15 , wherein the weighting of the anatomical feature is high when the position of the anatomical feature is highly repeatable relative to the ROI.
17. The method of claim 16 , wherein the high weighted anatomical feature comprises any one of the bony contours around an eye, an eyebrow, a nose, a forehead region, and any combination thereof.
18. The method of claim 15 , wherein the weighting of the anatomical feature is low when the position of the anatomical features is variable relative to the ROI.
19. The method of claim 18 , wherein the low weighted anatomical feature is removed from the facial detection algorithm.
20. The method of claim 18 , wherein in the low weighted anatomical feature comprises any one a cheek region, a jaw region, a back of the head region, a region of an ear and any combination thereof.
21. The method of claim 15 , wherein the anatomical feature comprises any one of a nose, an eye, an ear, a mouth, a cheek, an eyebrow, a jaw, and any combination thereof.
22. The method of claim 15 , further comprising creating the patient registration model from any one of computed tomography (CT), magnetic resonance image (MRI), computer tomography angiography (CTA), magnetic resonance angiography (MRA), and intraoperative CT images.