Systems and methods for electrode orientation determination in deep brain stimulation (dbs)

Abstract

The present disclosure provides systems and methods for estimating an orientation of an implanted deep brain stimulation (DBS) lead. Such methods include generating an initial image dataset, down-sampling a respective image or adding noise to images of the subset of the initial image dataset, and re-slicing at least a subset of the modified image dataset along an alternative primary imaging axis, to generate an integrated image dataset. The method also include partitioning the integrated image dataset into a preliminary training image dataset and a testing image dataset, and re-sizing at least a subset of the preliminary training image dataset with a localized field of view around a depicted DBS lead, to generate a training image dataset. The method further includes training a machine-learning model using the training image dataset, and executing the trained machine-learning model to estimate, during a DBS implantation procedure, an orientation of a subject implanted DBS lead.

What is claimed is: 
     
         1 . A computing device for estimating an orientation of an implanted deep brain stimulation (DBS) lead, the computing device comprising:
 a processor; and   a memory device communicatively coupled to the processor, the memory device including instructions that, when executed, cause the processor to:
 generate an initial image dataset, each image in the initial image dataset including a depiction of an implanted DBS lead and a label of an orientation of the implanted DBS lead; 
 modify the initial image dataset by duplicating and modifying at least a subset of the initial image dataset to generate a modified image dataset; 
 modify the modified image dataset by duplicating and re-slicing at least a subset of the modified image dataset to generate an integrated image dataset; 
 partition the integrated image dataset into a preliminary training image dataset and a testing image dataset; 
 modify the preliminary training image dataset by duplicating and re-sizing at least a subset of the preliminary training image dataset to generate a training image dataset; 
 train a machine-learning model using the training image dataset; and 
 execute the trained machine-learning model to estimate, during a DBS implantation procedure, an orientation of a subject implanted DBS lead. 
   
     
     
         2 . The computing device of  claim 1 , wherein the machine-learning model is an artificial neural network, and wherein training the machine-learning model includes implementing transfer learning techniques. 
     
     
         3 . The computing device of  claim 1 , wherein at least some of the images in the initial image dataset include at least one of intra-operative or post-operative computed tomography (CT) images. 
     
     
         4 . The computing device of  claim 1 , wherein at least some of the images in the initial image dataset include at least one of intra-operative fluoroscopy images or post-operative fluoroscopy images. 
     
     
         5 . The computing device of  claim 1 , wherein the initial image dataset includes pre-operative magnetic resonance imaging (MRI) images identifying anatomical features of a brain in which the DBS lead is to be implanted. 
     
     
         6 . The computing device of  claim 1 , wherein the instructions further cause the processor to:
 test the trained machine-learning model using at least a subset of the testing image dataset.   
     
     
         7 . The computing device of  claim 6 , wherein the instructions further cause the processor to:
 refine the trained machine-learning model based on an outcome of the testing of the trained machine-learning model.   
     
     
         8 . The computing device of  claim 7 , wherein the instructions further cause the processor to:
 validate the refined trained machine-learning model using at least another subset of the testing image dataset.   
     
     
         9 . The computing device of  claim 1 , wherein the instructions further cause the processor to:
 receive, during the DBS implantation procedure, a subject image including a depiction of the subject implanted DBS lead with an unknown orientation;   input the subject image to the trained machine-learning model;   receive, as output in response to the executing of the trained machine-learning model, the estimated orientation of the subject implanted DBS lead; and   output, to a user of the computing device, the estimated orientation of the subject implanted DBS lead.   
     
     
         10 . A computer-implemented method for estimating deep brain stimulation (DBS) lead orientation, the method comprising:
 generating an initial image dataset, each image in the initial image dataset including a depiction of an implanted DBS lead and a label of an orientation of the implanted DBS lead;   modifying the initial image dataset by duplicating and modifying at least a subset of the initial image dataset to generate a modified image dataset;   modifying the modified image dataset by duplicating and re-slicing at least a subset of the modified image dataset to generate an integrated image dataset;   partitioning the integrated image dataset into a preliminary training image dataset and a testing image dataset;   modifying the preliminary training image dataset by duplicating and re-sizing at least a subset of the preliminary training image dataset to generate a training image dataset;   training a machine-learning model using the training image dataset; and   executing the trained machine-learning model to estimate, during a DBS implantation procedure, an orientation of a subject implanted DBS lead.   
     
     
         11 . The method of  claim 10 , wherein training the machine-learning model comprises training an artificial neural network by implementing transfer learning techniques. 
     
     
         12 . The method of  claim 10 , wherein generating the initial image data set includes receiving at least one of intra-operative or post-operative computed tomography (CT) images. 
     
     
         13 . The method of  claim 11 , wherein generating the initial image data set includes receiving at least one of intra-operative fluoroscopy images or post-operative fluoroscopy images. 
     
     
         14 . The method of  claim 11 , wherein generating the initial image data set includes receiving pre-operative magnetic resonance imaging (MRI) images identifying anatomical features of a brain in which the DBS lead is to be implanted. 
     
     
         15 . The method of  claim 10 , further comprising:
 testing the trained machine-learning model using at least a subset of the testing image dataset.   
     
     
         16 . The method of  claim 15 , further comprising:
 refining the trained machine-learning model based on an outcome of the testing of the trained machine-learning model.   
     
     
         17 . The method of  claim 16 , further comprising:
 validating the refined trained machine-learning model using at least another subset of the testing image dataset.   
     
     
         18 . The method of  claim 10 , further comprising:
 receiving, during the DBS implantation procedure, a subject image including a depiction of the subject implanted DBS lead with an unknown orientation;   inputting the subject image to the trained machine-learning model;   receiving, as output in response to the executing of the trained machine-learning model, the estimated orientation of the subject implanted DBS lead; and   outputting, to a user, the estimated orientation of the subject implanted DBS lead.   
     
     
         19 . Non-transitory computer-readable media having computer-executable instructions thereon, wherein when executed by a processor of a computing device communicatively coupled to a memory device, cause the processor of the computing device to:
 generate an initial image dataset, each image in the initial image dataset including a depiction of an implanted DBS lead and a label of an orientation of the implanted DBS lead;   modify the initial image dataset by duplicating and modifying at least a subset of the initial image dataset to generate a modified image dataset;   modify the modified image dataset by duplicating and re-slicing at least a subset of the modified image dataset to generate an integrated image dataset;   partition the integrated image dataset into a preliminary training image dataset and a testing image dataset;   modify the preliminary training image dataset by duplicating and re-sizing at least a subset of the preliminary training image dataset to generate a training image dataset;   train a machine-learning model using the training image dataset; and   execute the trained machine-learning model to estimate, during a DBS implantation procedure, an orientation of a subject implanted DBS lead.   
     
     
         20 . The non-transitory computer-readable media of  claim 19 , wherein the computer-executable instructions further cause the processor to:
 test the trained machine-learning model using at least a subset of the testing image dataset.