Fully Automatic Catheter Localization in C-Arm Images Using ℓ1-Sparse Coding

Abstract

Abstract. We propose a method to perform automatic detection and tracking of electrophysiology (EP) catheters in C-arm fluoroscopy sequences. Our approach does not require any initialization, is completely automatic, and can concurrently track an arbitrary number of overlapping catheters. After a pre-processing step, we employ sparse coding to first detect candidate catheter tips, and subsequently detect and track the catheters. The proposed technique is validated on 2835 C-arm images, which include 39,690 manually selected ground-truth catheter electrodes. Results demonstrated sub-millimeter detection accuracy and real-time tracking performances.

Computer‐aided detection of retained surgical needles from postoperative radiographs

“…Although there have been previous studies [4][5][6][7] to detect line-like objects, those techniques could not be directly applied for the automatic detection of needles. For example, for the detection of lasso catheters 5 , a similar idea of ellipse fitting was used, but the ellipse fitting was done by first detecting the electrodes as 'blobs' and then checking whether these 'blobs' could fit an ellipse.…”

Online tracking of interventional devices for endovascular aortic repair

“…Throughout the past years, there has been a lot of efforts towards detecting and tracking catheter tips in fluoroscopic sequences for various applications and purposes [12,14,15]. However, these techniques can not be applied for the stent graft delivery device due to its inhomogeneous appearance and rather large size.…”

Scale-space for empty catheter segmentation in PCI fluoroscopic images

“…al [2] has also proposed efficient catheter tracking for electrophysiology procedures. Various works on segmentation of pigtail catheters [10] and EP catheters [12,13] portray the importance of segmentation of interventional tools and endovascular devices.…”