Pulmonary Vessel Segmentation based on Orthogonal Fused U-Net++ of Chest CT Images

TL;DR

This paper introduces a novel 2.5D orthogonal fused U-Net++ framework for pulmonary vessel segmentation in chest CT images, achieving high accuracy with lower complexity compared to 3D networks.

Contribution

The work proposes a 2.5D multi-planar fusion approach with a refinement process, outperforming existing models in pulmonary vessel segmentation accuracy.

Findings

Achieved a DICE score of 0.9272 on LIDC dataset

Outperformed state-of-the-art 2D and 3D segmentation models

Demonstrated lower network complexity and memory usage

Abstract

Pulmonary vessel segmentation is important for clinical diagnosis of pulmonary diseases, while is also challenging due to the complicated structure. In this work, we present an effective framework and refinement process of pulmonary vessel segmentation from chest computed tomographic (CT) images. The key to our approach is a 2.5D segmentation network applied from three orthogonal axes, which presents a robust and fully automated pulmonary vessel segmentation result with lower network complexity and memory usage compared to 3D networks. The slice radius is introduced to convolve the adjacent information of the center slice and the multi-planar fusion optimizes the presentation of intra- and inter- slice features. Besides, the tree-like structure of the pulmonary vessel is extracted in the post-processing process, which is used for segmentation refining and pruning. In the evaluation experiments, three fusion methods are tested and the most promising one is compared with the state-of-the-art 2D and 3D structures on 300 cases of lung images randomly selected from LIDC dataset. Our method outperforms other network structures by a large margin and achieves by far the highest average DICE score of 0.9272 and precision of 0.9310, as per our knowledge from the pulmonary vessel segmentation models available in the literature.