Robotic Knee Arthroplasty Control With ML-Guided Surgical Commands
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing surgical planning systems for arthroplasty procedures, such as PKA and TKA, often require manual modifications during surgery, lacking precise automation and real-time adjustments based on patient-specific data.
Innovation Solution
A computer-assisted surgical system (CASS) that utilizes machine learning models trained on historical data to generate robotic commands for surgical tools, incorporating patient anatomical and implant data, and surgeon preferences, with real-time visualization and approval mechanisms to ensure accurate bone resection and implant placement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual modifications are used during surgery to adjust the surgical plan, then surgeon flexibility and adaptability are improved, but surgical precision and consistency deteriorate due to human error and variability
Solution Approach 1:
The surgical system segments the workflow into pre-operative planning (where the surgical plan is created with high precision) and intra-operative execution (where the robotic system automatically implements the plan). This segmentation allows the precision-critical tasks to be performed by the robotic system while preserving surgeon flexibility for decision-making.
Solution Approach 2:
The robotic surgical system acts as an intermediary between the pre-operative surgical plan and the actual bone resection/implant placement. It translates the digital surgical plan into precise physical actions, eliminating direct manual manipulation while preserving the surgeon's intent through the pre-planned procedure.
2Manufacturing precision
If automated robotic commands are used to manipulate surgical tools, then surgical precision and consistency are improved, but surgeon control and adaptability deteriorate
Solution Approach 1:
The surgical plan is created in advance with all necessary parameters and instructions, allowing the robotic system to execute precise automated commands without requiring real-time surgeon intervention. The surgeon prepares the detailed plan pre-operatively, enabling automatic execution during surgery.
Solution Approach 2:
The system incorporates feedback mechanisms where the robotic system executes commands based on the surgical plan, and the surgeon can review and approve/modify commands before execution. This feedback loop maintains surgeon control while enabling automated precision execution.
3Productivity
If machine learning models are applied to generate robotic commands in real-time, then surgical efficiency and productivity are improved, but system complexity and computational requirements worsen
Solution Approach 1:
Machine learning models are trained in advance on historical surgical data to learn optimal surgical patterns and decision-making. During surgery, the pre-trained models generate robotic commands rapidly without requiring complex real-time computation, thus improving efficiency while managing system complexity.
Solution Approach 2:
The machine learning models operate autonomously to generate robotic commands based on the surgical plan and real-time surgical data, reducing the need for complex manual control systems and simplifying the overall system architecture while maintaining high productivity.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
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.