A system and method are disclosed to ingest sonography data at a high frame rate, to generate a high quality 3D model. The system could comprise standard sonography equipment, coupled to a computer with graphics display and machine learning software. The method works by a user generating 2D ultrasonic images of an object, which are sent to the computer. The machine-learning system then uses the sonography data to create 3D models from collections of 2D video, and creates a platonic 3D model of the subject. While the user is scanning the object, the system then presents gaps in the 3D model which the user fills by scanning the corresponding locations in greater detail, to complete generation of the high quality 3D model. This model can then be used with a computer, cell phone, or tablet to allow a doctor or curious bystander to rotate, view from varying angles.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Blaylock, Joseph, "Virtual Sonography", Technical Disclosure Commons, (December 05, 2016)