Display options
Cite
Nalepa J, Marcinkiewicz M, Kawulok M. Data Augmentation for Brain-Tumor Segmentation: A Review. Front Comput Neurosci. 2019;13:83doi: 10.3389/fncom.2019.00083.
Nalepa, J., Marcinkiewicz, M., & Kawulok, M. (2019). Data Augmentation for Brain-Tumor Segmentation: A Review. Frontiers in computational neuroscience, 1383. https://doi.org/10.3389/fncom.2019.00083
Nalepa, Jakub, et al. "Data Augmentation for Brain-Tumor Segmentation: A Review." Frontiers in computational neuroscience vol. 13 (2019): 83. doi: https://doi.org/10.3389/fncom.2019.00083
Nalepa J, Marcinkiewicz M, Kawulok M. Data Augmentation for Brain-Tumor Segmentation: A Review. Front Comput Neurosci. 2019 Dec 11;13:83. doi: 10.3389/fncom.2019.00083. eCollection 2019. PMID: 31920608; PMCID: PMC6917660.
Copy Download .nbib Format: NLM
Share it on

Front Comput Neurosci. 2019 Dec 11;13:83. doi: 10.3389/fncom.2019.00083. eCollection 2019.

Data Augmentation for Brain-Tumor Segmentation: A Review.

Frontiers in computational neuroscience

Jakub Nalepa, Michal Marcinkiewicz, Michal Kawulok

Affiliations

  1. Future Processing, Gliwice, Poland.
  2. Silesian University of Technology, Gliwice, Poland.
  3. Netguru, Poznan, Poland.

PMID: 31920608 PMCID: PMC6917660 DOI: 10.3389/fncom.2019.00083

Abstract

Data augmentation is a popular technique which helps improve generalization capabilities of deep neural networks, and can be perceived as implicit regularization. It plays a pivotal role in scenarios in which the amount of high-quality ground-truth data is limited, and acquiring new examples is costly and time-consuming. This is a very common problem in medical image analysis, especially tumor delineation. In this paper, we review the current advances in data-augmentation techniques applied to magnetic resonance images of brain tumors. To better understand the practical aspects of such algorithms, we investigate the papers submitted to the Multimodal Brain Tumor Segmentation Challenge (BraTS 2018 edition), as the BraTS dataset became a standard benchmark for validating existent and emerging brain-tumor detection and segmentation techniques. We verify which data augmentation approaches were exploited and what was their impact on the abilities of underlying supervised learners. Finally, we highlight the most promising research directions to follow in order to synthesize high-quality artificial brain-tumor examples which can boost the generalization abilities of deep models.

Copyright © 2019 Nalepa, Marcinkiewicz and Kawulok.

Keywords: MRI; data augmentation; deep learning; deep neural network; image segmentation

References

  1. BMC Med Imaging. 2017 May 4;17(1):29 - PubMed
  2. AMIA Annu Symp Proc. 2018 Apr 16;2017:979-984 - PubMed
  3. Comput Methods Programs Biomed. 2018 May;158:113-122 - PubMed
  4. Acad Radiol. 2006 Jul;13(7):803-10 - PubMed
  5. Sci Data. 2017 Sep 05;4:170117 - PubMed
  6. IEEE Trans Pattern Anal Mach Intell. 2018 Sep;40(9):2051-2065 - PubMed
  7. IEEE Trans Image Process. 2009 Mar;18(3):624-35 - PubMed
  8. IEEE Trans Image Process. 1996;5(10):1473-80 - PubMed
  9. Comput Med Imaging Graph. 2014 Jun;38(4):306-14 - PubMed
  10. Neuroimage Clin. 2019;22:101727 - PubMed
  11. IEEE Trans Pattern Anal Mach Intell. 2013 Aug;35(8):1798-828 - PubMed
  12. PLoS One. 2016 Oct 25;11(10):e0164891 - PubMed
  13. Neurocomputing. 2019 Sep 3;335:34-45 - PubMed
  14. Nature. 2015 May 28;521(7553):436-44 - PubMed
  15. Comput Methods Programs Biomed. 2019 Jul;176:135-148 - PubMed
  16. Front Neurosci. 2019 Mar 14;13:144 - PubMed
  17. Front Neurosci. 2019 Oct 24;13:1128 - PubMed
  18. IEEE Trans Med Imaging. 2015 Oct;34(10):1993-2024 - PubMed
  19. IEEE Trans Med Imaging. 2016 May;35(5):1240-1251 - PubMed
  20. Front Neuroinform. 2013 Dec 23;7:39 - PubMed
  21. Med Image Anal. 2017 Dec;42:60-88 - PubMed
  22. PLoS One. 2017 Oct 6;12(10):e0185844 - PubMed
  23. Med Image Anal. 2019 Jul;55:136-147 - PubMed

Publication Types