Next Article in Journal
Wind-Induced Phenomena in Long-Span Cable-Supported Bridges: A Comparative Review of Wind Tunnel Tests and Computational Fluid Dynamics Modelling
Next Article in Special Issue
Fully Leveraging Deep Learning Methods for Constructing Retinal Fundus Photomontages
Previous Article in Journal
Trends and Challenges in Network Covert Channels Countermeasures
Previous Article in Special Issue
Quantitative Assessment of Shape Deformation of Regional Cranial Bone for Evaluation of Surgical Effect in Patients with Craniosynostosis
Open AccessArticle

Synthesize and Segment: Towards Improved Catheter Segmentation via Adversarial Augmentation

1
Department of Robotics Engineering, DGIST, Daegu 42988, Korea
2
DGIST-ETH Microrobotics Research Center, DGIST, Daegu 42988, Korea
3
Division of Cardiology, Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam-si 13620, Korea
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editor: Francesco Bianconi
Appl. Sci. 2021, 11(4), 1638; https://doi.org/10.3390/app11041638
Received: 31 December 2020 / Revised: 3 February 2021 / Accepted: 7 February 2021 / Published: 11 February 2021
Automatic catheter and guidewire segmentation plays an important role in robot-assisted interventions that are guided by fluoroscopy. Existing learning based methods addressing the task of segmentation or tracking are often limited by the scarcity of annotated samples and difficulty in data collection. In the case of deep learning based methods, the demand for large amounts of labeled data further impedes successful application. We propose a synthesize and segment approach with plug in possibilities for segmentation to address this. We show that an adversarially learned image-to-image translation network can synthesize catheters in X-ray fluoroscopy enabling data augmentation in order to alleviate a low data regime. To make realistic synthesized images, we train the translation network via a perceptual loss coupled with similarity constraints. Then existing segmentation networks are used to learn accurate localization of catheters in a semi-supervised setting with the generated images. The empirical results on collected medical datasets show the value of our approach with significant improvements over existing translation baseline methods. View Full-Text
Keywords: adversarial learning; catheter robot; convolutional neural networks; image translation adversarial learning; catheter robot; convolutional neural networks; image translation
Show Figures

Figure 1

MDPI and ACS Style

Ullah, I.; Chikontwe, P.; Choi, H.; Yoon, C.H.; Park, S.H. Synthesize and Segment: Towards Improved Catheter Segmentation via Adversarial Augmentation. Appl. Sci. 2021, 11, 1638. https://doi.org/10.3390/app11041638

AMA Style

Ullah I, Chikontwe P, Choi H, Yoon CH, Park SH. Synthesize and Segment: Towards Improved Catheter Segmentation via Adversarial Augmentation. Applied Sciences. 2021; 11(4):1638. https://doi.org/10.3390/app11041638

Chicago/Turabian Style

Ullah, Ihsan; Chikontwe, Philip; Choi, Hongsoo; Yoon, Chang H.; Park, Sang H. 2021. "Synthesize and Segment: Towards Improved Catheter Segmentation via Adversarial Augmentation" Appl. Sci. 11, no. 4: 1638. https://doi.org/10.3390/app11041638

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop