Statistical modeling of pulmonary vasculatures with topological priors in CT volumes

Yuki Saeki (1) , Atsushi Saito (1) , Jean Cousty (2) , Yukiko Kenmochi (2) , Akinobu Shimizu (1)

1 TUAT - Tokyo University of Agriculture and Technology
2 LIGM - Laboratoire d'Informatique Gaspard-Monge

A statistical appearance model of blood vessels based on variational autoencoder (VAE) is well adapted to image intensity variations. However, images reconstructed with such a statistical model may have topological defects, such as loss of bifurcation and creation of undesired hole. In order to build a 3D anatomical model of blood vessels, we incorporate topological prior into the statistical modeling. Qualitative and quantitative results on 2567 real CT volume patches and on 10000 artificial ones show the efficiency of the proposed framework.

Mots clés: Statistical model; Topological data analysis; Variational autoencoder; Vasculature

Domaines: Informatique [cs]

Yuki Saeki, Atsushi Saito, Jean Cousty, Yukiko Kenmochi, Akinobu Shimizu. Statistical modeling of pulmonary vasculatures with topological priors in CT volumes. MICCAI 2021 workshop on Topological Data Analysis and Its Applications for Medical Data, Sep 2021, Strasbourg (virtual), France. pp.108-118, ⟨10.1007/978-3-030-87444-5_11⟩. ⟨hal-03334462⟩