Segmentation of Tubular Structures Using Iterative Training with Tailored Samples

TL;DR

This paper introduces an iterative training scheme for minimal path methods that improves segmentation and centerline extraction of tubular structures, requiring minimal annotated data and outperforming previous approaches.

Contribution

The novel iterative training approach tailors training samples for minimal path methods without altering existing annotations, enhancing segmentation and centerline extraction.

Findings

Achieves state-of-the-art results on multiple datasets

Requires only a few annotated images

Outperforms seven previous methods

Abstract

We propose a minimal path method to simultaneously compute segmentation masks and extract centerlines of tubular structures with line-topology. Minimal path methods are commonly used for the segmentation of tubular structures in a wide variety of applications. Recent methods use features extracted by CNNs, and often outperform methods using hand-tuned features. However, for CNN-based methods, the samples used for training may be generated inappropriately, so that they can be very different from samples encountered during inference. We approach this discrepancy by introducing a novel iterative training scheme, which enables generating better training samples specifically tailored for the minimal path methods without changing existing annotations. In our method, segmentation masks and centerlines are not determined after one another by post-processing, but obtained using the same steps. Our method requires only very few annotated training images. Comparison with seven previous approaches on three public datasets, including satellite images and medical images, shows that our method achieves state-of-the-art results both for segmentation masks and centerlines.