Back to results
US 11,238,197 B1Granted
Generating a 3D dataset containing a simulated surgical device
OwnerDavid Byron Douglas, Kathleen Mary Douglas +1inventors
InventorsDavid Byron Douglas, Kathleen Mary Douglas, Robert Edwin Douglas
Life of this patent
Estimating the term…
Abstract
This patent includes a method and apparatus for the generation of a simulated, realistic medical device, which can be inserted into a 3D radiological dataset from CT, MRI, PET, SPECT or DTS examinations. This simulated dataset can be segmented, filtered, manipulated, used with artificial intelligence algorithms and viewed in conjunction with head display units and geo-registered tools.
Claims20
A method of generating simulated volumetric datasets comprising:
- generating a 3D coordinate system;
- generating a simulated 3D dataset comprising a set of voxels wherein each voxel within said set of voxels has an assigned data unit within said 3D coordinate system comprising:
- generating a sub-volume, wherein the sub-volume includes a representation of a surgical device;
- inserting said sub-volume into said 3D coordinate system;
- performing a discrimination process on said simulated 3D dataset wherein said discrimination process determines whether said simulated 3D dataset appears real or appears fake;
- and
- modifying voxel(s) within said simulated 3D dataset when said discrimination process determines that said simulated 3D dataset appears fake.
4 more elements
A method comprising:
- using a generative adversarial network to create a first image slice and insert a representation of a surgical device into said first image slice;
- performing a discrimination process to determine if said first image slice appears real;
- if said first image slice appears real, using a generative adversarial network to create at least one additional image slice wherein said at least one additional image slice is contiguous with said first image slice;
- performing the discrimination process to determine if the at least one additional image slice appears real;
- if the at least one additional image slice appears real:
- arranging said first image slice and said at least one additional image slice to generate a volume;
- and
- reconstructing a reformat from said volume wherein said reformat contains at least a portion of said first slice and at least a portion of said at least one additional image slice;
- and
- performing a discrimination process on said reformat.
7 more elements
A method comprising:
- using an artificial intelligence (AI) process to create a first image slice wherein said first image slice comprises a representation of a surgical device;
- performing a discrimination process to determine if said first image slice appears real;
- if said first image slice appears real, using an AI process to create at least one additional image slice wherein said at least one additional image slice is contiguous with said first image slice;
- performing the discrimination process to determine if the at least one additional image slice appears real;
- if the at least one additional image slice appears real:
- arranging said first image slice and said at least one additional image slice to generate a volume;
- and
- reconstructing a reformat from a said volume wherein said reformat contains at least a portion of said first slice and at least a portion of said at least one additional image slice;
- and
- performing a discrimination process on said reformat.
7 more elements
Dependencies are inferred from the claim text.