Real-time and accurate soft tissue deformation prediction

Abstract

For soft tissue deformation prediction, a biomechanical or other tissue-related physics model is used to find an instantaneous state of the soft tissue. A machine-learned artificial neural network isapplied to predict the position of volumetric elements (e.g., mesh node) from the instantaneous state. Since the machine-learned artificial neural network may predict quickly (e.g., in a second or less), the soft tissue position at different times or a further time given the instantaneous state is provided in real-time without the minutes of physics model computation. For example, a real-time, biomechanical solver is provided, allowing interaction with the soft tissue model, while still getting accurate results. The accuracy allows for generating images of a soft tissue with greater accuracy and/or the benefit of user interaction in real-time.

Description

technical field [0001] This embodiment relates to computing soft tissue deformations, such as for medical imaging, computer animation or games. Determining organ deformation may be important for medical image reconstruction, medical image registration, digital twin modeling for data integration and outcome prediction, three-dimensional (3D) mesh editing, augmented or virtual reality, or other applications. Background technique [0002] Biomechanical models of soft tissue (e.g., as a priori or constraints) can provide more information for determining the deformation of said soft tissue under various conditions (e.g., subject to external forces such as pressure or gravity, internal forces such as stiffness or active stress, etc.). realistic capabilities. Existing techniques explicitly use finite element methods or other integration methods to solve biomechanical equations given boundary conditions, external forces, constitutive laws, and model parameters. While accurate, the...

AI Technical Summary

Problems solved by technology

While these methods perform model reduction on the object's deformation space, newer methods perform reduction on the object's material model

The scope of use of these methods has not addressed biomechanical models that are more physiologically accurate and thus realistic

Images