Pathological Pulmonary Lobe Segmentation from CT Images using Progressive Holistically Nested Neural Networks and Random Walker

TL;DR

This paper introduces a novel deep learning-based method combining progressive holistically nested neural networks and random walker algorithms for automatic pathological pulmonary lobe segmentation from CT images, improving robustness and accuracy.

Contribution

It is the first to apply deep learning to PPLS, coupling P-HNN with RW for improved segmentation without relying on prior airway or vessel segmentation.

Findings

Achieved a mean Jaccard score of 0.888 on diseased lungs

Significantly outperformed previous state-of-the-art methods (p < 0.001)

Demonstrated robustness in diseased lung conditions

Abstract

Automatic pathological pulmonary lobe segmentation(PPLS) enables regional analyses of lung disease, a clinically important capability. Due to often incomplete lobe boundaries, PPLS is difficult even for experts, and most prior art requires inference from contextual information. To address this, we propose a novel PPLS method that couples deep learning with the random walker (RW) algorithm. We first employ the recent progressive holistically-nested network (P-HNN) model to identify potential lobar boundaries, then generate final segmentations using a RW that is seeded and weighted by the P-HNN output. We are the first to apply deep learning to PPLS. The advantages are independence from prior airway/vessel segmentations, increased robustness in diseased lungs, and methodological simplicity that does not sacrifice accuracy. Our method posts a high mean Jaccard score of 0.888$\pm$0.164 on a held-out set of 154 CT scans from lung-disease patients, while also significantly (p < 0.001) outperforming a state-of-the-art method.