Rda-Inr: Riemannian Diffeomorphic Autoencoding Via Implicit Neural Representations

Research output: Contribution to conferencePosterAcademic

8 Downloads (Pure)

Abstract

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. This poster focuses 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 and 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.
Original languageEnglish
Publication statusPublished - 28 May 2024
EventSIAM Conference on Imaging Science, IS 2024 - Westin Peachtree Plaza Hotel, Atlanta, United States
Duration: 28 May 202431 May 2024
https://siam.org/conferences/cm/conference/is24

Conference

ConferenceSIAM Conference on Imaging Science, IS 2024
Abbreviated titleSIAM IS 2024
Country/TerritoryUnited States
CityAtlanta
Period28/05/2431/05/24
Internet address

Keywords

  • Shape space
  • Riemannian geometry
  • Principal geodesic analysis
  • LDDMM
  • Diffeomorphic registration
  • Latent space
  • Implicit neural representations

Fingerprint

Dive into the research topics of 'Rda-Inr: Riemannian Diffeomorphic Autoencoding Via Implicit Neural Representations'. Together they form a unique fingerprint.

Cite this