Estimation Of Joint Replacement Poses From Magnetic Field Readings

Abstract

Disclosed herein are methods for determining kinematic information of a joint. A method according to one embodiment may comprise the steps of receiving data obtained from a sensor of an implanted joint implant, analyzing the data with a trained estimation model to simultaneously determine kinematic information of the joint in six degrees of freedom, and outputting the kinematic information. In another embodiment, a method may comprise the steps of applying data obtained from a Hall sensor of an implanted joint implant to a trained estimation model to simultaneously determine kinematic information of the joint in six degrees of freedom; and outputting the kinematic information.

1 . A method of determining kinematic information of a joint comprising the steps of:
 receiving data obtained from a sensor of an implanted joint implant;   analyzing the data with a trained estimation model to simultaneously determine kinematic information of the joint in six degrees of freedom using input from a machine learning module; and   outputting the kinematic information.   
     
     
         2 . The method of  claim 1 , wherein the sensor is a Hall sensor and the joint implant further includes at least one magnet. 
     
     
         3 . The method of  claim 1 , wherein machine learning module includes any of a neural network and a regression network. 
     
     
         4 . The method of  claim 1 , wherein the joint is a knee joint and the implanted joint implant includes femoral and tibial components. 
     
     
         5 . The method of  claim 4 , wherein the femoral component includes a plurality of magnets and the tibial component includes a Hall sensor. 
     
     
         6 . The method of  claim 1 , further comprising the step of training the estimation model. 
     
     
         7 . The method of  claim 6 , wherein the step of training the estimation model includes obtaining data from a prototype. 
     
     
         8 . The method of  claim 7 , wherein the data pertains to different poses of the prototype. 
     
     
         9 . The method of  claim 8 , wherein the data is obtained through the use of a robot. 
     
     
         10 . The method of  claim 8 , wherein the data is obtained through the use of video motion capture. 
     
     
         11 . The method of  claim 6 , wherein the step of training the estimation model includes creating a finite element analysis. 
     
     
         12 . The method of  claim 11 , wherein the step of training the estimation model further includes obtaining data from a prototype. 
     
     
         13 . The method of  claim 12 , further comprising determining a model error. 
     
     
         14 . The method of  claim 1 , wherein the implanted joint implant is any of a knee implant, shoulder implant, hip implant, and spine implant. 
     
     
         15 . A method of determining kinematic information of a joint comprising the steps of:
 applying data obtained from a Hall sensor of an implanted joint implant to a trained estimation model to simultaneously determine kinematic information of the joint in six degrees of freedom; and   outputting the kinematic information.   
     
     
         16 . The method of  claim 15 , wherein the joint is a knee joint and the implanted joint implant includes femoral and tibial components. 
     
     
         17 . The method of  claim 16 , wherein the femoral component includes one or more magnets and the tibial component includes the Hall sensor. 
     
     
         18 . The method of  claim 15 , wherein the outputting step includes providing a visual model of the kinematic information. 
     
     
         19 . The method of  claim 18 , wherein the visual model is a graphical representation of the motion of bones of the joint. 
     
     
         20 . A method of determining kinematic information of a knee joint comprising the steps of:
 applying data obtained from the cooperation of a magnet of a femoral component and a Hall sensor of a tibial component to a trained estimation model to simultaneously determine kinematic information of the knee joint in six degrees of freedom; and   outputting the kinematic information as a visual representation depicting the movement of the femur and the tibia.