TY - UNPB
T1 - Rda-inr
T2 - Riemannian Diffeomorphic Autoencoding via Implicit Neural Representations
AU - Dummer, Sven
AU - Strisciuglio, Nicola
AU - Brune, Christoph
N1 - 34 pages, 27 figures (including subfigures)
PY - 2023/5/22
Y1 - 2023/5/22
N2 - Diffeomorphic registration frameworks such as Large Deformation Diffeomorphic Metric Mapping (LDDMM) are used in computer graphics and the medical domain for atlas building, statistical latent modeling, and pairwise and groupwise registration. In recent years, researchers have developed neural network-based approaches regarding diffeomorphic registration to improve the accuracy and computational efficiency of traditional methods. In this work, we focus on a limitation of neural network-based atlas building and statistical latent modeling methods, namely that they either are (i) resolution dependent or (ii) disregard any data/problem-specific geometry needed for proper mean-variance analysis. In particular, we overcome this limitation by designing a novel encoder based on resolution-independent implicit neural representations. The encoder achieves resolution invariance for LDDMM-based statistical latent modeling. Additionally, the encoder adds LDDMM Riemannian geometry to resolution-independent deep learning models for statistical latent modeling. We showcase that the Riemannian geometry aspect improves latent modeling and is required for a proper mean-variance analysis. Furthermore, to showcase the benefit of resolution independence for LDDMM-based data variability modeling, we show that our approach outperforms another neural network-based LDDMM latent code model. Our work paves a way to more research into how Riemannian geometry, shape/image analysis, and deep learning can be combined.
AB - Diffeomorphic registration frameworks such as Large Deformation Diffeomorphic Metric Mapping (LDDMM) are used in computer graphics and the medical domain for atlas building, statistical latent modeling, and pairwise and groupwise registration. In recent years, researchers have developed neural network-based approaches regarding diffeomorphic registration to improve the accuracy and computational efficiency of traditional methods. In this work, we focus on a limitation of neural network-based atlas building and statistical latent modeling methods, namely that they either are (i) resolution dependent or (ii) disregard any data/problem-specific geometry needed for proper mean-variance analysis. In particular, we overcome this limitation by designing a novel encoder based on resolution-independent implicit neural representations. The encoder achieves resolution invariance for LDDMM-based statistical latent modeling. Additionally, the encoder adds LDDMM Riemannian geometry to resolution-independent deep learning models for statistical latent modeling. We showcase that the Riemannian geometry aspect improves latent modeling and is required for a proper mean-variance analysis. Furthermore, to showcase the benefit of resolution independence for LDDMM-based data variability modeling, we show that our approach outperforms another neural network-based LDDMM latent code model. Our work paves a way to more research into how Riemannian geometry, shape/image analysis, and deep learning can be combined.
KW - Computer graphics
KW - Shapes
KW - Neural Networks
KW - 58D05, 53A05, 58B20, 68T07, 62-07, 68U10
KW - Diffeomorphic registration
KW - Riemannian geometry
U2 - 10.48550/arXiv.2305.12854
DO - 10.48550/arXiv.2305.12854
M3 - Preprint
BT - Rda-inr
PB - ArXiv.org
ER -