Mean Field Network based Graph Refinement with application to Airway Tree Extraction

TL;DR

This paper introduces a novel graph refinement approach using mean field networks for extracting airway trees from 3D chest CT images, demonstrating significant accuracy improvements over existing methods.

Contribution

The work formulates airway tree extraction as a Bayesian graph refinement problem using mean field networks, enabling learned inference with neural network techniques.

Findings

Significant improvement in airway extraction accuracy compared to baseline methods.

Effective modeling of airway branches using Bayesian smoothing and Gaussian density estimates.

Demonstrated applicability of mean field networks for 3D medical image analysis.

Abstract

We present tree extraction in 3D images as a graph refinement task, of obtaining a subgraph from an over-complete input graph. To this end, we formulate an approximate Bayesian inference framework on undirected graphs using mean field approximation (MFA). Mean field networks are used for inference based on the interpretation that iterations of MFA can be seen as feed-forward operations in a neural network. This allows us to learn the model parameters from training data using back-propagation algorithm. We demonstrate usefulness of the model to extract airway trees from 3D chest CT data. We first obtain probability images using a voxel classifier that distinguishes airways from background and use Bayesian smoothing to model individual airway branches. This yields us joint Gaussian density estimates of position, orientation and scale as node features of the input graph. Performance of the method is compared with two methods: the first uses probability images from a trained voxel classifier with region growing, which is similar to one of the best performing methods at EXACT'09 airway challenge, and the second method is based on Bayesian smoothing on these probability images. Using centerline distance as error measure the presented method shows significant improvement compared to these two methods.