Deformation estimation of an elastic object by partial observation using a neural network
This addresses a critical need for accurate deformation estimation in computer-assisted surgery, enabling better navigation by predicting full object deformations from limited data, though it is incremental as it applies neural networks to a known bottleneck in the field.
The study tackled the problem of estimating the deformation of entire 3D elastic objects, such as internal organs, using displacement data from very few observation points, achieving an average error of 0.041 mm for a human liver model deformed up to 66.4 mm with only around 3% observations.
Deformation estimation of elastic object assuming an internal organ is important for the computer navigation of surgery. The aim of this study is to estimate the deformation of an entire three-dimensional elastic object using displacement information of very few observation points. A learning approach with a neural network was introduced to estimate the entire deformation of an object. We applied our method to two elastic objects; a rectangular parallelepiped model, and a human liver model reconstructed from computed tomography data. The average estimation error for the human liver model was 0.041 mm when the object was deformed up to 66.4 mm, from only around 3 % observations. These results indicate that the deformation of an entire elastic object can be estimated with an acceptable level of error from limited observations by applying a trained neural network to a new deformation.