by Gino Gulamhussene, Arnab Das, Jonathan Spiegel, Daniel Punzet, Marko Rak, Christian Hansen
Abstract:
CT-guided interventions are standard practice for radiologists to treat lesions in various parts of the human body. In this context, accurate tracking of instruments is of paramount importance for the safety of the procedure and helps radiologists avoid unintended damage to adjacent organs. In this work, a novel method for the estimation of 3D needle tip coordinates in a CT volume using only two 2D projections in an interventional setting is proposed. The method applies a deep learning model for the fuzzy segmentation of the region containing the tip on 2D projections and automatically extracts the position of the tip. A simple UNet achieves a Dice score of 0.9906 for the fuzzy segmentation and an average euclidean distance of 2.96 mm for the needle tip regression task.
Reference:
Needle Tip Tracking During CT-guided Interventions using Fuzzy Segmentation (Gino Gulamhussene, Arnab Das, Jonathan Spiegel, Daniel Punzet, Marko Rak, Christian Hansen), In Bildverarbeitung für die Medizin 2023 (Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff, eds.), Springer Fachmedien Wiesbaden, 2023.
Bibtex Entry:
@inproceedings{gulamhussene_needle_2023,
	address = {Wiesbaden},
	title = {Needle {Tip} {Tracking} {During} {CT}-guided {Interventions} using {Fuzzy} {Segmentation}},
	isbn = {978-3-658-41657-7},
	abstract = {CT-guided interventions are standard practice for radiologists to treat lesions in various parts of the human body. In this context, accurate tracking of instruments is of paramount importance for the safety of the procedure and helps radiologists avoid unintended damage to adjacent organs. In this work, a novel method for the estimation of 3D needle tip coordinates in a CT volume using only two 2D projections in an interventional setting is proposed. The method applies a deep learning model for the fuzzy segmentation of the region containing the tip on 2D projections and automatically extracts the position of the tip. A simple UNet achieves a Dice score of 0.9906 for the fuzzy segmentation and an average euclidean distance of 2.96 mm for the needle tip regression task.},
	booktitle = {Bildverarbeitung für die {Medizin} 2023},
	publisher = {Springer Fachmedien Wiesbaden},
	author = {Gulamhussene, Gino and Das, Arnab and Spiegel, Jonathan and Punzet, Daniel and Rak, Marko and Hansen, Christian},
	editor = {Deserno, Thomas M. and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus and Palm, Christoph and Tolxdorff, Thomas},
	year = {2023},
	pages = {285--291}
}