Implicit Neural Representations for Generative Modeling of Living Cell Shapes

Logo poskytovatele

Varování

Publikace nespadá pod Pedagogickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Název česky Implicitní neurální reprezentace pro generativní modelování tvaru živých buněk
Autoři

WIESNER David SUK Julian DUMMER Sven SVOBODA David WOLTERINK Jelmer

Rok publikování 2022
Druh Článek ve sborníku
Konference International Conference on Medical Image Computing and Computer Assisted Intervention
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www http://dx.doi.org/10.1007/978-3-031-16440-8_6
Doi http://dx.doi.org/10.1007/978-3-031-16440-8_6
Klíčová slova cell shape modeling; neural networks; implicit neural representations; signed distance function; generative model; interpolation
Popis Methods allowing the synthesis of realistic cell shapes could help generate training data sets to improve cell tracking and segmentation in biomedical images. Deep generative models for cell shape synthesis require a light-weight and flexible representation of the cell shape. However, commonly used voxel-based representations are unsuitable for high-resolution shape synthesis, and polygon meshes have limitations when modeling topology changes such as cell growth or mitosis. In this work, we propose to use level sets of signed distance functions (SDFs) to represent cell shapes. We optimize a neural network as an implicit neural representation of the SDF value at any point in a 3D+time domain. The model is conditioned on a latent code, thus allowing the synthesis of new and unseen shape sequences. We validate our approach quantitatively and qualitatively on C. elegans cells that grow and divide, and lung cancer cells with growing complex filopodial protrusions. Our results show that shape descriptors of synthetic cells resemble those of real cells, and that our model is able to generate topologically plausible sequences of complex cell shapes in 3D+time.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.