PixelTopoIS: a pixel-topology-coupled guidewire tip segmentation framework for robot-assisted intervention

Existing works showed great performance in pixel-level guidewire segmentation. However, topology-level segmentation has not been fully exploited in these works. Guidewire (tip) endpoint localization and (guidewire) loop detection are typical topology-level guidewire segmentation tasks. A superb guidewire segmentation algorithm should achieve both low endpoint localization error and high loop detection accuracy.

This paper focuses on pixel-topology-coupled guidewire (tip) segmentation. The contributions are (1) two algorithmic improvements including an iterative segmentation framework and a pixel-topology-coupled loss function (2) a new metric that comprehensively evaluates the segmentation results at both pixel and topology level (3) the first publicly available guidewire dataset (The dataset can be downloaded from www.njzdyyrobocgsu.com ) containing 4500+ X-ray images with radiologist-annotated results.

The algorithm rivals the state-of-the-art methods in pixel-level metric (0.06-4.21% for the F1-score) in most sequences, achieving performance comparable to the best method on two sequences. Our method also shows competitive performance (20% for the loop existence accuracy) on the newly introduced metric. Experiments are also performed to quantitatively validate the functionality of different components in our framework.

The framework is effective in segmenting the guidewire by considering pixel and topology equally, providing an accurate position of the tip's endpoint (pixel-level) to the surgeon/robot and preserving the clinically meaningful guidewire structure (topology-level) simultaneously.