Automated catheter localization in volumetric ultrasound using 3D patch-wise U-net with focal loss

Hongxu Yang, Caifeng Shan, Alexander F. Kolen, Peter de With

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

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.
Original languageEnglish
Title of host publication2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages1346-1350
Number of pages5
ISBN (Electronic)978-1-5386-6249-6
DOIs
Publication statusPublished - Sep 2019
Event26th IEEE International Conference on Image Processing (ICIP 2019) - Taipei, Taiwan
Duration: 22 Sep 201925 Sep 2019

Conference

Conference26th IEEE International Conference on Image Processing (ICIP 2019)
Abbreviated titleICIP 2019
CountryTaiwan
CityTaipei
Period22/09/1925/09/19

Keywords

  • 3D U-Net
  • 3D ultrasound
  • Catheter localization
  • Dense sampling
  • Focal loss

Fingerprint Dive into the research topics of 'Automated catheter localization in volumetric ultrasound using 3D patch-wise U-net with focal loss'. Together they form a unique fingerprint.

Cite this