Download fulltext HTML
1.
Hejazi M, Razaghi G, Aghsaei Fard M. Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture. JOVR [Internet]. 2023Feb.13 [cited 2024May3];18(1):41–50. Available from: https://knepublishing.com/index.php/JOVR/article/view/12724

https://doi.org/10.18502/jovr.v18i1.12724

statistics

  • 410 Abstract Views
  • 258 PDF Views
  • 0 HTML Views

authors

  • Marjaneh Hejazi

    Marjaneh Hejazi

    Medical Physics and Biomedical Engineering Department, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
  • Ghazale Razaghi

    Ghazale Razaghi

    Medical Physics and Biomedical Engineering Department, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
  • Masoud Aghsaei Fard

    Masoud Aghsaei Fard

    Department of Ophthalmology, Farabi Eye Hospital, Tehran University of Medical Sciences, Tehran, Iran

Published Date

  • Feb 13, 2023
This journal is publishing all the articles under Creative Commons Attribution License CC BY 4.0.

Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture

Journal of Ophthalmic and Vision Research (JOVR) / Jan–Mar 2023, Volume 18, Issue 1 / Pages 41–50

Abstract

Purpose: In this study, an algorithm based on deep learning was presented to reduce the retinal nerve fiber layer (RNFL) segmentation errors in spectral domain optical coherence tomography (SD-OCT) scans using ophthalmologists’ manual segmentation as a reference standard.
Methods: In this study, we developed an image segmentation network based on deep learning to automatically identify the RNFL thickness from B-scans obtained with SD-OCT. The scans were collected from Farabi Eye Hospital (500 B-scans were used for training, while 50 were used for testing). To remove the speckle noise from the images, preprocessing was applied before training, and postprocessing was performed to fill any discontinuities that might exist. Afterward, output masks were analyzed for their average thickness. Finally, the calculation of mean absolute error between predicted and ground truth RNFL thickness was performed.
Results: Based on the testing database, SD-OCT segmentation had an average dice similarity coefficient of 0.91, and thickness estimation had a mean absolute error of 2.23 ± 2.1 μm. As compared to conventional OCT software algorithms, deep learning predictions were better correlated with the best available estimate during the test period (r2 = 0.99 vs r2 = 0.88, respectively; P < 0.001).
Conclusion: Our experimental results demonstrate effective and precise segmentation of the RNFL layer with the coefficient of 0.91 and reliable thickness prediction with MAE 2.23 ± 2.1 μm in SD-OCT B-scans. Performance is comparable with human annotation of the RNFL layer and other algorithms according to the correlation coefficient of 0.99 and 0.88, respectively, while artifacts and errors are evident.

Keywords:

Deep Learning, Optical Coherence Tomography, Retinal Nerve Fiber Layer

References
1. Pierro L, Gagliardi M, Iuliano L, Ambrosi A, Bandello F. Retinal nerve fiber layer thickness reproducibility using seven different OCT Instruments. Invest Ophthalmol Vis Sci 2012;53:5912–5920.

2. Asrani S, Essaid L, Alder BD, Santiago-Turla C. Artifacts in spectral-domain optical coherence tomography measurements in glaucoma. JAMA Ophthalmol 2014;132:396–402.

3. Liu Y, Simavli H, Que CJ, Rizzo JL, Tsikata E, Maurer R, et al. Patient characteristics associated with artifacts in spectralis optical coherence tomography imaging of the retinal nerve fiber layer in glaucoma. Am J Ophthalmol 2015;159:565–576.

4. Jammal AA, Thompson AC, Ogata NG, Mariottoni EB, Urata CN, Costa VP, et al. Detecting retinal nerve fibre layer segmentation errors on spectral domain-optical coherence tomography with a deep learning algorithm. Sci Rep 2019;9:1–9.

5. Mansberger SL, Menda SA, Fortune BA, Gardiner SK, Demirel S. Automated segmentation errors when using optical coherence tomography to measure retinal nerve fiber layer thickness in glaucoma. Am J Ophthalmol 2017;174:1–8.

6. Shen D, Wu G, Suk HI. Deep learning in medical image analysis. Annu Rev Biomed Eng 2017;19:221–248.

7. Christopher M, Bowd C, Belghith A, Goldbaum MH, Weinreb RN, Fazio MA, et al. Deep learning approaches predict glaucomatous visual field damage from Oct optic nerve head en face images and retinal nerve fiber layer thickness maps. Ophthalmology 2020;127:346–356.

8. Devalla SK, Renukanand PK, Sreedhar BK, Subramanian G, Zhang L, Perera S, et al. DRUNET: A dilated-residual UNet Deep Learning Network to segment optic nerve head tissues in optical coherence tomography images. Biomed Opt Express 2018;9:3244–3265.

9. Thompson AC, Jammal AA, Berchuck SI, Mariottoni EB, Medeiros FA. Assessment of a segmentation-free deep learning algorithm for diagnosing glaucoma from optical coherence tomography scans. JAMA Ophthalmol 2020;138:333–339.

10. Ma R, Liu Y, Tao Y, Alawa KA, Shyu M-L, Lee RK. Deep learning–based retinal nerve fiber layer thickness measurement of murine eyes. Transl Vis Sci Technol 2021;10:21.

11. Mariottoni EB, Jammal AA, Urata CN, Berchuck SI, Thompson AC, Estrela T, et al. Quantification of retinal nerve fibre layer thickness on optical coherence tomography with a deep learning segmentation-free approach. Sci Rep 2020;10:1–9.

12. Medeiros FA, Jammal AA, Thompson AC. From machine to machine: An OCT-trained deep learning algorithm for objective quantification of glaucomatous damage in fundus photographs. Ophthalmology 2019;126:513–521.

13. An G, Omodaka K, Hashimoto K, Tsuda S, Shiga Y, Takada N, et al. Glaucoma diagnosis with machine learning based on optical coherence tomography and color fundus images. J Healthc Eng 2019;2019:1–9.

14. Fang L, Cunefare D, Wang C, Guymer RH, Li S, Farsiu S. Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search. Biomed Opt Express 2017;8:2732–2744.

15. Pekala M, Joshi N, Liu TYA, Bressler NM, DeBuc DC, Burlina P. Deep Learning based retinal OCT segmentation. Comput Biol Med 2019;114:103445.

16. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. Med Image Comput Assist Interv 2015;234–241.

17. Kipli K, Enamul Hoque M, Thai Lim L, Afendi Zulcaffle TM, Kudnie Sahari S, Hamdi Mahmood M. Retinal image blood vessel extraction and quantification with Euclidean distance transform approach. IET Image Process 2020;14:3718–3724.

18. Tang X, Zheng R, Wang Y. Distance and edge transform for skeleton extraction. IEEE/CVF ICCVW 2021;2136–2141.

19. Ben-Cohen A, Mark D, Kovler I, Zur D, Barak A, Iglicki M, et al. Retinal layers segmentation using fully convolutional network in OCT images. RSIP Vision 2017;1–8.

20. Lu D, Heisler M, Ma D, Dabiri S, Lee S, Ding GW, et al. Cascaded deep neural networks for retinal layer segmentation of optical coherence tomography with fluid presence. arXiv preprint arXiv:1912.03418.

21. Zhou Z, Siddiquee MMR, Tajbakhsh N, Liang J. UNet++: A nested U-net architecture for medical image segmentation. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support 2018;11045:3–11.

22. Matovinovic IZ, Loncaric S, Lo J, Heisler M, Sarunic M. Transfer learning with U-net type model for automatic segmentation of three retinal layers in optical coherence tomography images. 11th International Symposium on Image and Signal Processing and Analysis (ISPA) 2019;49–53.