Display options
Cite
Xu Y, Yan K, Kim J, et al. Dual-stage deep learning framework for pigment epithelium detachment segmentation in polypoidal choroidal vasculopathy. Biomed Opt Express. 2017;8(9):4061-4076doi: 10.1364/BOE.8.004061.
Xu, Y., Yan, K., Kim, J., Wang, X., Li, C., Su, L., Yu, S., Xu, X., & Feng, D. D. (2017). Dual-stage deep learning framework for pigment epithelium detachment segmentation in polypoidal choroidal vasculopathy. Biomedical optics express, 8(9), 4061-4076. https://doi.org/10.1364/BOE.8.004061
Xu, Yupeng, et al. "Dual-stage deep learning framework for pigment epithelium detachment segmentation in polypoidal choroidal vasculopathy." Biomedical optics express vol. 8,9 (2017): 4061-4076. doi: https://doi.org/10.1364/BOE.8.004061
Xu Y, Yan K, Kim J, Wang X, Li C, Su L, Yu S, Xu X, Feng DD. Dual-stage deep learning framework for pigment epithelium detachment segmentation in polypoidal choroidal vasculopathy. Biomed Opt Express. 2017 Aug 10;8(9):4061-4076. doi: 10.1364/BOE.8.004061. eCollection 2017 Sep 01. PMID: 28966847; PMCID: PMC5611923.
Copy Download .nbib Format: NLM
Share it on

Biomed Opt Express. 2017 Aug 10;8(9):4061-4076. doi: 10.1364/BOE.8.004061. eCollection 2017 Sep 01.

Dual-stage deep learning framework for pigment epithelium detachment segmentation in polypoidal choroidal vasculopathy.

Biomedical optics express

Yupeng Xu, Ke Yan, Jinman Kim, Xiuying Wang, Changyang Li, Li Su, Suqin Yu, Xun Xu, Dagan David Feng

Affiliations

  1. Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200080, China; Shanghai Key Laboratory of Fundus Disease, Shanghai Engineering Center for Visual Science and Photomedicine, Shanghai, 200080, China.
  2. Biomedical and Multimedia Information Technology (BMIT) Research Group, The University of Sydney, Sydney, NSW, 2006, Australia.

PMID: 28966847 PMCID: PMC5611923 DOI: 10.1364/BOE.8.004061

Abstract

Worldwide, polypoidal choroidal vasculopathy (PCV) is a common vision-threatening exudative maculopathy, and pigment epithelium detachment (PED) is an important clinical characteristic. Thus, precise and efficient PED segmentation is necessary for PCV clinical diagnosis and treatment. We propose a dual-stage learning framework via deep neural networks (DNN) for automated PED segmentation in PCV patients to avoid issues associated with manual PED segmentation (subjectivity, manual segmentation errors, and high time consumption).The optical coherence tomography scans of fifty patients were quantitatively evaluated with different algorithms and clinicians. Dual-stage DNN outperformed existing PED segmentation methods for all segmentation accuracy parameters, including true positive volume fraction (85.74 ± 8.69%), dice similarity coefficient (85.69 ± 8.08%), positive predictive value (86.02 ± 8.99%) and false positive volume fraction (0.38 ± 0.18%). Dual-stage DNN achieves accurate PED quantitative information, works with multiple types of PEDs and agrees well with manual delineation, suggesting that it is a potential automated assistant for PCV management.

Keywords: (100.0100) Image processing; (100.4996) Pattern recognition, neural networks; (110.4500) Optical coherence tomography; (170.3880) Medical and biological imaging

References

  1. Am J Ophthalmol. 2017 May;177:195-205 - PubMed
  2. IEEE Trans Med Imaging. 2017 Feb;36(2):407-421 - PubMed
  3. Biomed Opt Express. 2017 Jul 13;8(8):3627-3642 - PubMed
  4. Retina. 1996;16(6):467-73 - PubMed
  5. Ophthalmology. 2011 Jul;118(7):1373-9 - PubMed
  6. Prog Retin Eye Res. 2016 Jul;53:107-139 - PubMed
  7. Ophthalmology. 2015 Feb;122(2):399-406 - PubMed
  8. Sci Rep. 2016 Feb 22;6:21739 - PubMed
  9. Retina. 2007 Jun;27(5):589-94 - PubMed
  10. Retina. 2012 Sep;32(8):1453-64 - PubMed
  11. Retina. 2012 Jun;32(6):1057-68 - PubMed
  12. Artif Intell Med. 2017 Mar 24;:null - PubMed
  13. Biochem Med (Zagreb). 2015 Jun 05;25(2):141-51 - PubMed
  14. Am J Ophthalmol. 2016 Dec;172:13-27 - PubMed
  15. Ophthalmology. 2015 Apr;122(4):822-32 - PubMed
  16. Med Image Anal. 2013 Dec;17(8):1058-72 - PubMed
  17. Retina. 2005 Apr-May;25(3):304-10 - PubMed
  18. Br J Ophthalmol. 2015 Mar;99(3):289-96 - PubMed
  19. Retina. 2013 Oct;33(9):1735-62 - PubMed
  20. Biomed Opt Express. 2017 Apr 27;8(5):2732-2744 - PubMed
  21. Am J Ophthalmol. 2012 Mar;153(3):515-23 - PubMed
  22. Invest Ophthalmol Vis Sci. 2011 Mar 01;52(3):1599-605 - PubMed
  23. Invest Ophthalmol Vis Sci. 2016 Apr;57(4):1595-603 - PubMed
  24. Retina. 2016 Apr;36(4):778-86 - PubMed
  25. Comput Methods Programs Biomed. 2017 May;143:67-74 - PubMed
  26. IEEE Trans Med Imaging. 2016 Apr;35(4):1077-89 - PubMed
  27. Phys Med Biol. 2016 Dec 21;61(24):8676-8698 - PubMed
  28. IEEE Trans Med Imaging. 2013 Nov;32(11):2034-49 - PubMed
  29. J Clin Med. 2015 Apr 24;4(5):782-821 - PubMed
  30. Am J Ophthalmol. 2014 Dec;158(6):1228-1238.e1 - PubMed
  31. Am J Ophthalmol. 2013 Nov;156(5):974-980.e2 - PubMed
  32. IEEE Trans Pattern Anal Mach Intell. 2017 Apr;39(4):640-651 - PubMed
  33. IEEE Trans Med Imaging. 2017 Sep;36(9):1876-1886 - PubMed
  34. Nature. 2015 May 28;521(7553):436-44 - PubMed
  35. Br J Ophthalmol. 2008 Feb;92(2):197-203 - PubMed
  36. IEEE Trans Med Imaging. 2015 Feb;34(2):441-52 - PubMed
  37. Sci Rep. 2016 Jul 11;6:29619 - PubMed
  38. IEEE Trans Med Imaging. 2009 Sep;28(9):1436-47 - PubMed
  39. Comput Med Imaging Graph. 2007 Jun-Jul;31(4-5):198-211 - PubMed
  40. Opt Lett. 2016 Mar 1;41(5):994-7 - PubMed
  41. Clin Ophthalmol. 2014 Mar 02;8:343-6 - PubMed
  42. Conf Proc IEEE Eng Med Biol Soc. 2016 Aug;2016:635-638 - PubMed

Publication Types