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 images of a patient;
using at least one trained machine learning model for designing a patient-specific implant, the designing of the patient-specific implant includes:
analyzing the one or more images to identify one or more implantation sites along a patient's spine;
generating a virtual model of the patient's spine for review by a user, wherein the virtual model has an implant location for a virtual patient-specific implant representing the patient-specific implant;
receiving, from the user, design criteria associated with the one or more implantation sites and the patient-specific implant;
predicting, using the virtual model, whether the virtual patient-specific implant achieves an acceptable outcome based on the design criteria;
in response to the virtual patient-specific implant achieving an unacceptable outcome,
receiving alternative option input from the user,
updating the design criteria of the virtual patient-specific implant based on the received alternative option input, and
analyzing the updated design criteria using the virtual model to determine whether the updated design criteria causes the virtual patient-specific implant to achieve the acceptable outcome; and
in response to the updated design criteria causing the virtual patient-specific implant to achieve the acceptable outcome, generating a design of the patient-specific implant that fits with one or more vertebral bodies of the virtual model based on the updated design criteria.
2. The method of claim 1 , further comprising simulating the patient-specific implant being implanted along the patient's spine by using the virtual model of the patient's spine.
3. The method of claim 1 , further comprising:
determining one or more values for the patient's spine based on the 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.
4. The method of claim 1 , further comprising:
determining a suggested adjustment for the patient's spine; and
displaying one or more dimensions with at least one image for the suggested adjustment.
5. The method of claim 1 , further comprising:
adjusting one or more model parameters of the 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.
6. The 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.
7. The 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.
8. The method of claim 1 , further comprising:
using boundary detection, edge detection, tissue identification, structural analysis, tissue density, and/or feature matching to analyze the one or more images; and
generating at least a portion of the virtual model of the patient's spine based on the analysis of the one or more images.
9. The method of claim 1 , further comprising identifying an anatomical abnormality of the patient's spine based on the received one or more images.
10. The method of claim 1 , further comprising generating implant data for the patient-specific implant, wherein the implant data includes computer executable instructions that, when executed, direct an automated manufacturing system to manufacture the patient-specific implant.
11. The method of claim 1 , further comprising:
using the at least one trained machine learning model to select at least one anatomical feature of the patient's spine; and
measuring the selected at least one anatomical feature using the virtual model.
12. The method of claim 1 , further comprising:
measuring a distance between a first target vertebra and a second target vertebra using the virtual model of the patient's spine; and
designing the patient-specific implant based on the measured distance.
13. The method of claim 1 , further comprising:
generating manufacturing data based on the design of the patient-specific implant; and
manufacturing the patient-specific implant using 3D-printing based on the generated manufacturing data.
14. The method of claim 1 , wherein the patient is a first patient, the method further comprising:
receiving post-operative images of the first patient for retraining the at least one trained machine learning model; and
after the at least one trained machine learning model is retrained using the received post-operative images, using the retrained at least one trained machine learning model to determine design criteria for a second patient based on one or more images of the second patient.
15. 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 images of a patient;
using at least one trained machine learning model for designing a patient-specific implant, the designing of the patient-specific implant includes:
analyzing the one or more images to identify one or more implantation sites along a patient's spine;
generating a virtual model of the patient's spine for review by a user, wherein the virtual model has an implant location for a virtual patient-specific implant representing the patient-specific implant;
receiving, from the user, design criteria associated with the one or more implantation sites and the patient-specific implant;
predicting, using the virtual model, whether the virtual patient-specific implant achieves an acceptable outcome based on the design criteria;
in response to the virtual patient-specific implant achieving an unacceptable outcome, receiving alternative option input from the user,
updating the design criteria of the virtual patient-specific implant based on the received alternative option input, and
analyzing the updated design criteria using the virtual model to determine whether the updated design criteria causes the virtual patient-specific implant to achieve the acceptable outcome; and
in response to the updated design criteria causing the virtual patient-specific implant to achieve the acceptable outcome, generating a design of the patient-specific implant that fits with one or more vertebral bodies of the virtual model based on the updated design criteria.
16. The system of claim 15 , wherein the process further comprises simulating the patient-specific implant being implanted along the patient's spine by using the virtual model of the patient's spine and the patient-specific implant.
17. The system of claim 15 , wherein the process further comprises:
determining one or more values for the patient's spine based on the virtual model, wherein the one or more values indicate a configuration for the patient's spine; and
determining one or more dimensions of the patient-specific implant based on the determined one or more values.
18. The system of claim 15 , wherein the process further comprises:
determining a suggested adjustment for the patient's spine; and
displaying one or more dimensions with at least one image for the suggested adjustment.
19. 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 images of a patient;
use at least one trained machine learning model for designing a patient-specific implant, the designing of the patient-specific implant includes:
analyzing the one or more images to identify one or more implantation sites along a patient's spine;
generating a virtual model of the patient's spine for review by a user, wherein the virtual model has an implant location for a virtual patient-specific implant representing the patient-specific implant;
receiving, from the user, design criteria associated with the one or more implantation sites and the patient-specific implant;
predicting, using the virtual model, whether the virtual patient-specific implant achieves an acceptable outcome based on the design criteria;
in response to the virtual patient-specific implant achieving an unacceptable outcome,
receiving alternative option input from the user,
updating the design criteria of the virtual patient-specific implant based on the received alternative option input, and
analyzing the updated design criteria using the virtual model to determine whether the updated design criteria causes the virtual patient-specific implant to achieve the acceptable outcome; and
in response to the updated design criteria causing the virtual patient-specific implant to achieve the acceptable outcome, generating a design of the patient-specific implant that fits with one or more vertebral bodies of the virtual model based on the updated design criteria.
20. The non-transitory computer-readable storage medium of claim 19 , wherein the operations further comprise simulating the patient-specific implant being implanted along the patient's spine by using the virtual model of the patient's spine and the patient-specific implant.
21. The non-transitory computer-readable storage medium of claim 19 , wherein the operations further comprise:
determining one or more values for the patient's spine based on the virtual model, wherein the one or more values indicate a configuration for the patient's spine; and
determining one or more dimensions of the patient-specific implant based on the determined one or more values.
22. The non-transitory computer-readable storage medium of claim 19 , wherein the operations further comprise:
determining a suggested adjustment for the patient's spine; and
displaying one or more dimensions with at least one image for the suggested adjustment.
23. A method of manufacturing a patient-specific implant, the method comprising:
receiving manufacturing data for a patient-specific implant, wherein the manufacturing data is generated by a process including:
receiving one or more images of a patient;
using at least one trained machine learning model for designing a patient-specific implant, the designing of the patient-specific implant includes:
analyzing the one or more images to identify one or more implantation sites along a patient's spine,
generating a virtual model of the patient's spine for review by a user, wherein the virtual model has an implant location for a virtual patient-specific implant representing the patient-specific implant,
determining or receiving, from the user, design criteria associated with the one or more implantation sites and the patient-specific implant,
predicting, using the virtual model, whether the virtual patient-specific implant achieves an acceptable outcome based on the design criteria,
in response to the virtual patient-specific implant achieving an unacceptable outcome, receiving alternative option input from the user,
updating the design criteria of the virtual patient-specific implant based on the received alternative option input, and
analyzing the updated design criteria using the virtual model to determine whether the updated design criteria causes the virtual patient-specific implant to achieve the acceptable outcome,
in response to the updated design criteria causing the virtual patient-specific implant to achieve the acceptable outcome generating a design of the patient-specific implant that fits with one or more vertebral bodies of the virtual model based on the updated design criteria; and
manufacturing the patient-specific implant using 3D-printing based on the received manufacturing data.