Systems and methods for assisting and augmenting surgical procedures
Systems and methods for providing assistance to a surgeon during an implant surgery are disclosed. A method includes defining areas of interest in diagnostic data of a patient and defining a screw bone type based on the surgeon's input. Post defining the areas of interest, salient points are determined for the areas of interest. Successively, an XZ angle, an XY angle, and a position entry point for a screw are determined based on the salient points of the areas of interest. Successively, a maximum screw diameter and a length of the screw are determined based on the salient points. Thereafter, the screw is identified and suggested to the surgeon for usage during the implant surgery.
1. A computer-implemented method for providing surgical assistance, the method comprising:
receiving one or more pre-operative images of a patient;
generating at least one virtual model of a spine of the patient based on the one or more pre-operative images;
using at least one trained machine learning model to
determine an acceptable outcome for the patient based on at least one of
the one or more pre-operative images, or
the at least one virtual model, and
design a patient-specific implant to achieve the acceptable outcome for the patient when a virtual implant model the patient-specific implant is virtually implanted along the at least one virtual model of the spine of the patient;
after the patient-specific implant is implanted in the patient, receiving one or more post-operative images of the patient,
comparing the received one or more post-operative images with the acceptable outcome for the patient, and
wherein the at least one trained machine learning model is retrained based on the comparison; and
using the retrained at least one trained machine learning model to design at least one patient-specific implant for another patient.
2. The computer-implemented method of claim 1 , wherein retraining the at least one trained machine learning model is based on a similarity score between a modeled result for a planned treatment for achieving the acceptable outcome and an actual post-operative result of the patient.
3. The computer-implemented method of claim 1 , wherein the patient-specific implant is a cage, a rod, a plate, or a spinal fusion device.
4. The computer-implemented method of claim 1 , further comprising:
iteratively simulating surgical outcomes based on the at least one virtual model to generate predicted outcomes; and
determining whether each of the predicted outcomes is acceptable, wherein the acceptable outcome is one of the predicted outcomes determined to be acceptable.
5. The computer-implemented method of claim 1 , further comprising generating, using the at least one virtual model of the patient's spine, the virtual implant model of the patient-specific implant such that the virtual implant model of the patient-specific implant fits the at least one virtual model of the patient's spine.
6. The computer-implemented method of claim 1 , further comprising:
determining one or more values for the patient's spine based on the at least one virtual model of the patient's spine, wherein the one or more values indicate a configuration for the patient's spine; and
determining one or more dimensions for the patient-specific implant based on the determined one or more values.
7. The computer-implemented method of claim 1 , further comprising:
determining a proposed adjustment for the patient's spine; and
displaying one or more dimensions with the one or more pre-operative images for the proposed adjustment.
8. The computer-implemented method of claim 1 , further comprising:
adjusting one or more model parameters of the at least one virtual model of the patient's spine based on training data selected based on a surgery to be performed, wherein the training data includes scored prior patient data.
9. The computer-implemented method of claim 1 , further comprising training the at least one trained machine learning model based on a set of patient data, the set of patient data including, for a plurality of individual patients, at least one of (i) images (ii) patient information, (iii) implant configuration, or (iv) scored surgery outcomes.
10. The computer-implemented method of claim 1 , further comprising:
analyzing one or more simulations for treating the patient's spine; and
revising a design of the patient-specific implant based on the analysis of the one or more simulations.
11. The computer-implemented method of claim 1 , further comprising:
analyzing the one or more ative images using at least one of boundary detection, edge detection, tissue identification, structural analysis, tissue density, or feature matching; and
generating at least a portion of the at least one virtual model of the patient's spine based on the analysis of the one or more perative images.
12. The computer-implemented method of claim 1 , wherein the at least one virtual model is a three-dimensional model, wherein the patient-specific implant is a cage, and wherein designing the patient-specific implant includes:
virtually positioning the virtual implant model of the patient-specific implant along the at least one virtual model of the spine;
digitally measuring one or more distances between vertebrae of the spine associated with a spinal deformity;
adjusting one or more dimensions of the virtual implant model of the patient- specific implant based on the one or more distances, at least one design algorithm, and at least one implant design constraint for the patient's anatomy;
analyzing the at least one virtual model of the spine based on the adjusted virtual implant model of the patient-specific implant that has been virtually implanted along the at least one virtual model of the spine; and
receiving, via a graphical user interface, user input for the surgical assistance, wherein the graphical user interface is configured to allow the user to interact with a system performing the designing of the patient-specific implant.
13. The computer-implemented method of claim 1 , wherein the patient has a spinal deformity, the patient-specific implant is a spinal implant, and the acceptable outcome is for treating the spinal deformity using the spinal implant.
14. A computing system comprising:
one or more processors; and
one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to perform a process comprising:
receiving one or more pre-operative images of a patient;
generating at least one virtual model of a spine of the patient based on the one or more pre-operative images;
using at least one trained machine learning model to determine an acceptable outcome for the patient based on at least one of
the one or more pre-operative images, or
the at least one virtual model, and
design a patient-specific implant to achieve the acceptable outcome for the patient when a virtual implant model of the patient-specific imp lan is virtually implanted along the at least one virtual model of the spine of the patient;
after the patient-specific implant is implanted in the patient, receiving one or more post-operative images of the patient,
comparing the received one or more post-operative images with the acceptable outcome for the patient, and
wherein the at least one trained machine learning model is retrained based on the comparison; and
using the retrained at least one trained machine learning model to design at least one patient-specific implant for another patient.
15. The computing system of claim 14 , wherein retraining the at least one trained machine learning model is based on a similarity score between a modeled result for a planned treatment for achieving the acceptable outcome and an actual post-operative result of the patient.
16. The computing system of claim 14 , wherein the patient-specific implant is a cage, a rod, a plate, or a spinal fusion device.
17. The computing system of claim 14 , wherein the process further comprises:
iteratively simulating surgical outcomes based on the at least one virtual model to generate predicted outcomes; and
determining acceptability of each of the predicted outcomes, wherein the acceptable outcome is one of the predicted outcomes determined to be acceptable.
18. The computing system of claim 14 , wherein the process further comprises generating, using the at least one virtual model of patient's spine, the virtual implant model of the patient-specific implant such that the virtual implant model of the xecific implant fits at least one virtual model of the patient's spine.
19. The computing system of claim 14 , wherein the process further comprises:
determining one or more values for the patient's spine based on the at least one virtual model of the patient's spine, wherein the one or more values indicate a configuration for the patient's spine; and
determining one or more dimensions for the patient-specific implant based on the determined one or more values.
20. The computing system of claim 14 , wherein the process further comprises:
determining a proposed adjustment for the patient's spine; and
displaying one or more dimensions with the one or more pre-operative images for the proposed adjustment.
21. The computing system of claim 14 , wherein the process further comprises:
adjusting one or more model parameters of the a east one virtual model of the patient's spine based on training data selected based on a surgery to be performed, wherein the training data includes scored prior patient data.
22. The computing system of claim 14 , wherein the process further comprises training the at least one trained machine learning model based on a set of patient data, the set of patient data including, for a plurality of individual patients, at least one of (i) images (ii) patient information, (iii) implant configuration, or (iv) scored surgery outcomes.
23. The computing system of claim 14 , wherein the process further comprises:
analyzing one or more simulations for treating the patient's spine; and
revising a design of the patient-specific implant based on the analysis of the one or more simulations.
24. The computing system of claim 14 , wherein the process further comprises:
using boundary detection, edge detection, tissue identification, structural analysis, tissue density, and/or feature matching to analyze the one or more e- operative images; and
generating at least a portion of the at least one virtual model of the patient's spine based on the analysis of the one or more operative images.
25. The computing system of claim 14 , wherein the at least one virtual model is a three-dimensional model with model data, wherein the patient-specific implant is a cage, and wherein the process further comprises:
virtually positioning the virtual implant model of the patient-specific implant along the at least one virtual model of the spine;
digitally measuring one or more distances between vertebrae of the spine associated with a spinal deformity;
adjusting one or more dimensions of the virtual implant model of the patient-specific implant based on the one or more distances, at least one design algorithm, and at least one implant design constraint for the patient's anatomy;
analyzing the at least one virtual model of the spine based on the adjusted virtual implant model of the patient-specific implant that has been virtually implanted along the at least one virtual model of the spine; and
receiving, via a graphical user interface, user input for surgical assistance, wherein the graphical user interface is configured to allow the user to interact with a system performing the designing of the patient-specific implant.
26. The computing system of claim 14 , wherein the patient has a spinal deformity, the patient-specific implant is a spinal implant, and the acceptable outcome is for treating the spinal deformity using the spinal implant.
27. A non-transitory computer-readable storage medium storing instructions that, when executed by a computing system, cause the computing system to perform operations to:
receive one or more pre-operative images of a patient;
generate at least one virtual model of a spine of the patient based on the one or more pre-operative images;
use at least one trained machine learning model to
determine an acceptable outcome for the patient based on at least one of the one or more pre-operative images, or
the at least one virtual model, and
design a patient-specific implant to achieve the acceptable outcome for the patient when a virtual implant model of the ent-specific implant is virtually implanted along the a st virtu spine of the patient;
after the patient-specific implant is implanted in the patient,
receive one or more post-operative images of the patient,
compare the received one or more post-operative images with the acceptable outcome for the patient, and
wherein the at least one trained machine learning model is retrained based on the comparison; and
use the retrained at least one trained machine learning model to design at least one patient-specific implant for another patient.
28. The non-transitory computer-readable storage medium of claim 27 , wherein the operations include retraining the at least one trained machine learning model based on a similarity score between a modeled result for a planned treatment for achieving the acceptable outcome and an actual post-operative result of the patient.
29. The non-transitory computer-readable storage medium of claim 27 , wherein the patient-specific implant is a cage, a rod, a plate, or a spinal fusion device.
30. The non-transitory computer-readable storage medium of claim 27 , wherein the operation further comprise:
iteratively simulating surgical outcomes based on the at least one virtual model to generate predicted outcomes; and
determining acceptability of each of the predicted outcomes, wherein the acceptable outcome is one of the predicted outcomes determined to be acceptable.
31. The non-transitory computer-readable storage medium of claim 27 , wherein the operation further comprise generating using the at least one virtual model atient's spine, the virtual implant model of the patient-specific implant such al virtual implant model of the patient-specific implant fits the at least one virtual model of the patient's spine.
32. The non-transitory computer-readable storage medium of claim 27 , wherein the operation further comprise:
determining one or more values for the patient's spine based on the at least one virtual model of the patient's spine, wherein the one or more values indicate a configuration for the patient's spine; and
determining one or more dimensions for the patient-specific implant based on the determined one or more values.
33. The non-transitory computer-readable storage medium of claim 27 , wherein the operations further comprise:
determining a proposed adjustment for the patient's spine; and
displaying one or more dimensions with the one or more pre-operative images for the proposed adjustment.