Automated Catheter Localization in Volumetric Ultrasound Using 3D Patch-Wise U-Net with Focal Loss
Lists
Only you see this
Abstract
3D ultrasound (US) imaging has become an attractive option for image-guided interventions. Fast and accurate catheter localization in 3D cardiac US can improve the outcome and efficiency of the cardiac interventions. In this paper, we propose a catheter localization method for 3D cardiac US using the patch-wise semantic segmentation with model fitting. Our 3D U-Net is trained with the focal loss of cross-entropy, which makes the network to focus more on samples that are difficult to classify. Moreover, we adopt a dense sampling strategy to overcome the extremely imbalanced catheter occupation in the 3D US data. Extensive experiments on our challenging ex-vivo dataset show that the proposed method achieves an F-1 score of 65.1% for catheter segmentation, outperforming the state-of-the-art methods. With this, our method can localize RF-ablation catheters with an average error of 1.28 mm.
BibTeX
@inproceedings{yang2019automated,
author = {Hongxu Yang and Caifeng Shan and Alexander F. Kolen and Peter H. N. de With},
title = {{Automated Catheter Localization in Volumetric Ultrasound Using 3D Patch-Wise U-Net with Focal Loss}},
booktitle = {ICIP},
year = {2019},
doi = {10.1109/icip.2019.8803045},
}Loading related content...