Intraoperative Liver Surface Completion with Graph Convolutional VAE

TL;DR

This paper introduces a geometric deep learning approach using a variational autoencoder to predict complete liver surfaces from partial intraoperative data, improving surgical visualization.

Contribution

It presents a novel VAE-based method with a frequency domain data augmentation technique for intraoperative liver surface completion.

Findings

Outperforms rigid registration in visible areas

Effective on real intraoperative data

Robust shape completion with non-rigid deformation

Abstract

In this work we propose a method based on geometric deep learning to predict the complete surface of the liver, given a partial point cloud of the organ obtained during the surgical laparoscopic procedure. We introduce a new data augmentation technique that randomly perturbs shapes in their frequency domain to compensate the limited size of our dataset. The core of our method is a variational autoencoder (VAE) that is trained to learn a latent space for complete shapes of the liver. At inference time, the generative part of the model is embedded in an optimisation procedure where the latent representation is iteratively updated to generate a model that matches the intraoperative partial point cloud. The effect of this optimisation is a progressive non-rigid deformation of the initially generated shape. Our method is qualitatively evaluated on real data and quantitatively evaluated on synthetic data. We compared with a state-of-the-art rigid registration algorithm, that our method outperformed in visible areas.