Methods for improving robotic surgical systems and devices thereof
Methods, non-transitory computer readable media, and surgical computing devices are illustrated that improve robotic surgical systems. With this technology, one or more machine learning models are trained based on historical state data obtained for a computer-assisted surgical system (CASS) at each of a plurality of time periods during a plurality of historical knee arthroplasty surgical procedures. One or more of the machine learning models are applied to initial state data for a current knee arthroplasty surgical procedure to generate robotic commands required to achieve one or more future states of the CASS. The initial state data comprises a surgical plan. One or more surgical tools of the CASS are then manipulated based on the robotic commands to achieve the one or more future states of the CASS and thereby carry out at least a portion of the surgical plan.
1 . A method for improving robotic surgical systems, the method comprising:
training one or more machine learning models to model state transitions in surgical procedures based on historical state data obtained for a computer-assisted surgical system (CASS) at each of a plurality of time periods during a plurality of historical surgical procedures performed on a plurality of patients, wherein the historical state data comprises states of the CASS for each of the plurality of time periods;
applying one or more of the machine learning models to initial state data for a current surgical procedure to generate robotic commands required to achieve one or more future states of the CASS at least in part using robotic control, wherein the initial state data comprises a surgical plan and one or more surgeon preferences; and
manipulating one or more surgical tools of the CASS based on the robotic commands to achieve the one or more of the future states of the CASS and thereby carry out at least a portion of the surgical plan.
2 . The method of claim 1 , further comprising controlling a robotic arm to automatically manipulate one or more of the surgical tools of the CASS.
3 . The method of claim 1 , wherein the initial state data further comprises one or more of patient anatomical data, and implant data.
4 . The method of claim 1 , further comprising training one or more of the machine learning models further based on patient data associated with one or more of the plurality of historical surgical procedures performed on the plurality of patients.
5 . The method of claim 1 , further comprising outputting to a display device a plurality of visualizations of one or more of the future states of the CASS.
6 . The method of claim 5 , wherein the visualizations collectively depict aspects of an entirety of the current surgical procedure.
7 . The method of claim 5 , further comprising modifying one or more of the plurality of visualizations based on the application of the one or more of the machine learning models to obtained planned future state data for the current surgical procedure, wherein the one or more of the plurality of visualizations are modified to illustrate an impact of the planned future state data on the surgical plan.
8 . The method of claim 5 , wherein one or more of the visualizations comprise a plurality of images corresponding to one or more aspects of the current surgical procedure at one or more of the plurality of time periods corresponding to the one or more of the future states, wherein the visualizations collectively depict one or more changes over the one or more of the time periods to anatomy of a patient on which the current surgical procedure is performed.
9 . A surgical computing device, comprising:
a display device;
memory comprising programmed instructions stored thereon for improving robotic surgical systems; and
one or more processors coupled to the memory and configured to execute the stored programmed instructions to:
train one or more machine learning models to model state transitions in surgical procedures based on historical state data obtained for a computer-assisted surgical system (CASS) at a plurality of time periods during a plurality of historical surgical procedures performed on a plurality of patients, wherein the historical state data comprises states of the CASS for each of the plurality of time periods;
apply one or more of the machine learning models to initial state data for a current surgical procedure to generate one or more robotic commands required to achieve one or more future states of the CASS at least in part using robotic control, wherein the initial state data comprises a surgical plan and one or more surgeon preferences;
control a robotic arm to automatically manipulate one or more surgical tools of the CASS based on the robotic commands to achieve the one or more future states of the CASS; and
output to the display device one or more visualizations of one or more of the future states of the CASS, wherein the visualizations comprise one or more images corresponding to one or more aspects of the current surgical procedure at one or more of the plurality of time periods corresponding to the future states.
10 . The surgical computing device of claim 9 , wherein the initial state data further comprises one or more of patient anatomical data, and implant data.
11 . The surgical computing device of claim 9 , wherein the one or more processors are further configured to execute the stored programmed instructions to train the one or more of the machine learning models further based on patient data associated with one or more of the plurality of historical surgical procedures performed on the plurality of patients.
12 . The surgical computing device of claim 9 , wherein one or more of the visualizations depict one or more of:
an entirety of the current surgical procedure; or
one or more changes over the one or more of the plurality of time periods to anatomy of a patient on which the current surgical procedure is performed.
13 . The surgical computing device of claim 9 , wherein the one or more processors are further configured to execute the stored programmed instructions to modify one or more of the visualizations based on the application of the one or more of the machine learning models to obtained planned future state data for the current surgical procedure.
14 . The surgical computing device of claim 13 , wherein the one or more of the visualizations are modified to illustrate one or more impacts of the planned future state data on the surgical plan.
15 . A non-transitory computer readable medium having stored thereon instructions for improving robotic surgical systems comprising executable code that, when executed by one or more processors, causes the processors to:
train one or more machine learning models to model state transitions in surgical procedures based on historical state data obtained for a computer-assisted surgical system (CASS) at a plurality of time periods during a plurality of historical surgical procedures performed on a plurality of patients, wherein the historical state data comprises states of the CASS for each of the plurality of time periods;
apply one or more of the machine learning models to initial state data for a current surgical procedure to generate robotic commands required to achieve one or more future states of the CASS at least in part using robotic control, wherein the initial state data comprises a surgical plan and one or more surgeon preferences;
output to a display device one or more visualizations of one or more of the future states; and
modify one or more of the visualizations based on the application of the one or more of the machine learning models to obtained planned future state data for the current surgical procedure, wherein the one or more of the visualizations are modified to illustrate an impact of the planned future state data on the surgical plan.
16 . The non-transitory computer readable medium of claim 15 , wherein the executable code, when executed by the one or more processors, further causes the processors to control a robotic arm to automatically manipulate one or more of the surgical tools of the CASS.
17 . The non-transitory computer readable medium of claim 15 , wherein the initial state data further comprises one or more of patient anatomical data, and implant data.
18 . The non-transitory computer readable medium of claim 15 , wherein the executable code, when executed by the one or more processors, further causes the processors to train one or more of the machine learning models further based on patient data associated with one or more of the plurality of historical surgical procedures performed on the plurality of patients.
19 . The non-transitory computer readable medium of claim 15 , wherein the one or more of the visualizations depict one or more of:
an entirety of the current surgical procedure; or
one or more changes over the one or more of the plurality of time periods to anatomy of a patient on which the current surgical procedure is performed.
20 . The non-transitory computer readable medium of claim 15 , wherein the one or more of the visualizations comprise a plurality of images corresponding to one or more aspects of the current surgical procedure at one or more of the plurality of time periods corresponding to the one or more of the future states.