Publikation
Robust Statistical Shape Modelling with Implicit Neural Representations
Christoph Großbröhmer; Fenja Falta; Ron Keuth; Timo Kepp; Mattias P. Heinrich
In: Christoph Palm; Katharina Breininger; Thomas Martin Deserno; Heinz Handels; Andreas Maier; Klaus Maier-Hein; Thomas Tolxdorff (Hrsg.). Bildverarbeitung für die Medizin 2025. Workshop Bildverarbeitung für die Medizin (BVM-2025), Regensburg, Pages 32-37, ISBN 978-3-658-47422-5, Springer Fachmedien Wiesbaden, 2025.
Zusammenfassung
We present a frameworkfor multi-label statistical shape modelling using implicit neural representations (INRs). By training a generalised INR alongside instance-specific latent codes to model individual shapes as continuous signed distance maps, the approach captures complex anatomical variations without relying on fixed landmarks. We further propose to employ the shape model for regularisation to obtain robust reconstructions of corrupted or incomplete data. Experiments on 2D chest X-ray segmentations demonstrate that this regularisation facilitates reconstructions under flawed data conditions, achieving highfidelity segmentations. Conceptual examples highlight topological advantages of INR-based shape models over conventional point distribution models.