Keywords: Deep generative model, 3D convolutional neural network, Shape generation, Geometric morphometrics, Shape interpolation
TL;DR: A deep architecture to generate 3D anatomies from an abstract representation
Abstract: This work is an effort in human anatomy synthesis using deep models. Here, we introduce a deterministic deep convolutional architecture to generate human anatomies represented as 3D binarized occupancy maps (voxel-grids). The shape generation process is constrained by the 3D coordinates of a small set of landmarks selected on the surface of the anatomy. The proposed learning framework is empirically tested on the mandible bone where it was able to reconstruct the anatomies from landmark coordinates with the average landmark-to-surface error of 1.42 mm. Moreover, the model was able to linearly interpolate in the Z-space and smoothly morph a given 3D anatomy to another. The proposed approach can potentially be used in semi-automated segmentation with manual landmark selection as well as biomechanical modeling. Our main contribution is to demonstrate that deep convolutional architectures can generate high fidelity complex human anatomies from abstract representations.
Code Of Conduct: I have read and accept the code of conduct.
Remove If Rejected: (optional) Remove submission if paper is rejected.