ConTrack: Contextual Transformer for Device Tracking in X-ray

TL;DR

ConTrack is a transformer-based model that leverages spatial and temporal context from fluoroscopy and angiography images to improve device detection and tracking during endovascular procedures, addressing occlusion and motion challenges.

Contribution

The paper introduces ConTrack, a novel transformer-based network that integrates spatial templates, segmentation, and flow information for robust device tracking in X-ray imaging.

Findings

Achieves over 45% accuracy in detection and tracking.

Utilizes multiple templates for robustness against occlusion.

Effectively compensates for cardiac and respiratory motions.

Abstract

Device tracking is an important prerequisite for guidance during endovascular procedures. Especially during cardiac interventions, detection and tracking of guiding the catheter tip in 2D fluoroscopic images is important for applications such as mapping vessels from angiography (high dose with contrast) to fluoroscopy (low dose without contrast). Tracking the catheter tip poses different challenges: the tip can be occluded by contrast during angiography or interventional devices; and it is always in continuous movement due to the cardiac and respiratory motions. To overcome these challenges, we propose ConTrack, a transformer-based network that uses both spatial and temporal contextual information for accurate device detection and tracking in both X-ray fluoroscopy and angiography. The spatial information comes from the template frames and the segmentation module: the template frames define the surroundings of the device, whereas the segmentation module detects the entire device to bring more context for the tip prediction. Using multiple templates makes the model more robust to the change in appearance of the device when it is occluded by the contrast agent. The flow information computed on the segmented catheter mask between the current and the previous frame helps in further refining the prediction by compensating for the respiratory and cardiac motions. The experiments show that our method achieves 45% or higher accuracy in detection and tracking when compared to state-of-the-art tracking models.