Landmark-free Statistical Shape Modeling via Neural Flow Deformations
This provides a more robust and expressive shape prior for medical imaging tasks such as segmentation and reconstruction, addressing limitations in existing methods.
The paper tackles the problem of statistical shape modeling without requiring dense correspondence between training examples, and presents FlowSSM, which uses neural flow deformations to outperform state-of-the-art methods in expressiveness and robustness for anatomical structures like distal femur and liver.
Statistical shape modeling aims at capturing shape variations of an anatomical structure that occur within a given population. Shape models are employed in many tasks, such as shape reconstruction and image segmentation, but also shape generation and classification. Existing shape priors either require dense correspondence between training examples or lack robustness and topological guarantees. We present FlowSSM, a novel shape modeling approach that learns shape variability without requiring dense correspondence between training instances. It relies on a hierarchy of continuous deformation flows, which are parametrized by a neural network. Our model outperforms state-of-the-art methods in providing an expressive and robust shape prior for distal femur and liver. We show that the emerging latent representation is discriminative by separating healthy from pathological shapes. Ultimately, we demonstrate its effectiveness on two shape reconstruction tasks from partial data. Our source code is publicly available (https://github.com/davecasp/flowssm).