Abstract
Purpose
Chest X-ray is one of the most widespread examinations of the human body. In interventional radiology, its use is frequently associated with the need to visualize various tube-like objects, such as puncture needles, guiding sheaths, wires, and catheters. Detection and precise localization of these tube-like objects in the X-ray images are, therefore, of utmost value, catalyzing the development of accurate target-specific segmentation algorithms. Similar to the other medical imaging tasks, the manual pixel-wise annotation of the tubes is a resource-consuming process.
Methods
In this work, we aim to alleviate the lack of annotated images by using artificial data. Specifically, we present an approach for synthetic generation of the tube-shaped objects, with a generative adversarial network being regularized with a prior-shape constraint. Namely, our model uses Frangi-based regularization to draw synthetic tubes in the predefined fake mask regions and, then, uses the adversarial component to preserve the global realistic appearance of the synthesized image.
Results
Our method eliminates the need for the paired image–mask data and requires only a weakly labeled dataset, with fine-tuning on a small paired sample (10–20 images) proving sufficient to reach the accuracy of the fully supervised models.
Conclusion
We report the applicability of the approach for the task of segmenting tubes and catheters in the X-ray images, whereas the results should also hold for the other acquisition modalities and image computing applications that contain tubular objects.
Similar content being viewed by others
Notes
Our implementation: https://github.com/ilyas-sid/SoftFrangiFilter2D.
References
Kholiavchenko M, Sirazitdinov I, Kubrak K, Badrutdinova R, Kuleev R, Yuan Y, Vrtovec T, Ibragimov B (2020) Contour-aware multi-label chest x-ray organ segmentation. Int J Comput Assist Radiol Surg 15(3):425–436
Yi X, Adams SJ, Henderson RD, Babyn P (2020) Computer-aided assessment of catheters and tubes on radiographs: How good is artificial intelligence for assessment? Radiology. Artif Intell 2(1):190082
Frid-Adar M, Amer R, Greenspan H (2019) Endotracheal tube detection and segmentation in chest radiographs using synthetic data. Springer, Berlin
Subramanian V, Wang H, Wu JT, Wong KC, Sharma A, Syeda-Mahmood T (2019) Automated detection and type classification of central venous catheters in chest x-rays. Springer, Berlin
Yi X, Adams S, Babyn P, Elnajmi A (2020) Automatic catheter and tube detection in pediatric x-ray images using a scale-recurrent network and synthetic data. J Digit Imaging 33(1):181–190
Nikolenko SI (2019) Synthetic data for deep learning. Springer, Berlin
Gong X, Chen S, Zhang B, Doermann D (2021) Style consistent image generation for nuclei instance segmentation. pp 3994–4003
Prokopenko D, Stadelmann JV, Schulz H, Renisch S, Dylov DV (2019) Unpaired synthetic image generation in radiology using gans. Workshop on Artificial Intelligence in Radiation Therapy. Springer, pp 94–101
Costa P, Galdran A, Meyer MI, Niemeijer M, Abràmoff M, Mendonça AM, Campilho A (2017) End-to-end adversarial retinal image synthesis. IEEE Trans Med Imaging 37(3):781–791
Zhao H, Li H, Maurer-Stroh S, Cheng L (2018) Synthesizing retinal and neuronal images with generative adversarial nets. Med Image Anal 49:14–26
Li Q, Yu Z, Wang Y, Zheng H (2020) Tumorgan: a multi-modal data augmentation framework for brain tumor segmentation. Sensors 20(15):4203
Lee H, Mansouri M, Tajmir S, Lev MH, Do S (2018) A deep-learning system for fully-automated peripherally inserted central catheter (picc) tip detection. J Digit Imaging 31(4):393–402
Gherardini M, Mazomenos E, Menciassi A, Stoyanov D (2020) Catheter segmentation in x-ray fluoroscopy using synthetic data and transfer learning with light u-nets. Comput Methods Programs Biomed 192:105420
Heimann T, Meinzer H-P (2009) Statistical shape models for 3d medical image segmentation: a review. Med Image Anal 13(4):543–563
Frangi AF, Niessen WJ, Vincken KL, Viergever MA (1998) Multiscale vessel enhancement filtering. Springer, Berlin
Sato, Y., Nakajima, S., Atsumi, H., Koller, T., Gerig, G., Yoshida, S., Kikinis, R.: 3d multi-scale line filter for segmentation and visualization of curvilinear structures in medical images. In: CVRMed-MRCAS’97, pp. 213– 222 ( 1997). Springer
Ullah I, Chikontwe P, Choi H, Yoon C-H, Park SH (2021) Synthesize and segment: towards improved catheter segmentation via adversarial augmentation. Appl Sci 11(4):1638
Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. pp 2223–2232
Mao X, Li Q, Xie H, Lau RY, Wang Z, Paul Smolley S (2017) Least squares generative adversarial networks. pp 2794–2802
Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM (2017) Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. pp 2097–2106
OpenCV, F.: opencv/cvat. https://github.com/opencv/cvat
Ronneberger O, Fischer P, Brox, T.: U-net, (2015). Convolutional networks for biomedical image segmentation. Springer, pp 234–241
Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)
Shit S, Paetzold JC, Sekuboyina A, Ezhov I, Unger A, Zhylka A, Pluim JP, Bauer U, Menze BH (2021) cldice-a novel topology-preserving loss function for tubular structure segmentation. pp 16560–16569
Park T, Liu M-Y, Wang T-C, Zhu J-Y (2019) Semantic image synthesis with spatially-adaptive normalization. pp 2337–2346
Zhu P, Abdal R, Qin Y, Wonka, P.: Sean, (2020) Image synthesis with semantic region-adaptive normalization. pp 5104–5113
Zacharov I, Arslanov R, Gunin M, Stefonishin D, Bykov A, Pavlov S, Panarin O, Maliutin A, Rykovanov S, Fedorov M (2019) “zhores” –petaflops supercomputer for data-driven modeling, machine learning and artificial intelligence installed in skolkovo institute of science and technology. Open Engineering 9(1):512–520
Acknowledgements
We acknowledge support from the Zhores computational cluster team [27].
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
At time of conducting this study, all authors were associated with Philips Research. The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants performed by any of the authors. This research study was conducted retrospectively using human subject data made available in open access by [20]. Ethical approval was not required as confirmed by the license attached with the open access data.
Informed consent
This article does not contain patient data.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sirazitdinov, I., Schulz, H., Saalbach, A. et al. Tubular shape aware data generation for segmentation in medical imaging. Int J CARS 17, 1091–1099 (2022). https://doi.org/10.1007/s11548-022-02621-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-022-02621-3