Skip to main content
SpringerLink
Log in

3D Retinal Vessel Segmentation in OCTA Volumes: Annotated Dataset MORE3D and Hybrid U-Net with Flattening Transformation

  • Conference paper
  • First Online:
Pattern Recognition (DAGM GCPR 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14264))

Included in the following conference series:

  • 111 Accesses

Abstract

Optical Coherence Tomography Angiography (OCTA) extends the 3D structural representation of the retina from conventional OCT with an additional representation of “flow” and is used as non-invasive angiography technique in ophthalmology today. While there are several works for the segmentation of vascular network in OCTA images, most of them are tested on 2D enface images (top view projection) only. Such 2D enface images have the drawback that they depend on a good 3D segmentation of retinal layers, the so-called slabs. Especially in case of retinal diseases (e.g. exudations of the retina) this segmentation is not always clear, even for medical experts. In contrast, we consider the problem of full 3D segmentation of retinal vessels in OCTA images. We present the dataset MORE3D (Münster Octa REtina 3D dataset) that is the first one with 3D annotation. We introduce a general flattening transformation that simplifies and accelerates the 3D data labeling and processing, and also enables a specialized data augmentation. Moreover, we realize a hybrid U-net to achieve a first reference segmentation performance on our dataset. In addition to the common performance metrics we also apply skeleton-based metrics for a more comprehensive structural performance evaluation. With this work we contribute to the advancement of 3D retinal vessel segmentation in OCTA volumes.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Ashraf, M., et al.: Vascular density of deep, intermediate and superficial vascular plexuses are differentially affected by diabetic retinopathy severity. Investig. Ophthalmol. Vis. Sci. 61(10), 53 (2020)

    Article  Google Scholar 

  2. Azzopardi, G., et al.: Trainable COSFIRE filters for vessel delineation with application to retinal images. Med. Image Anal. 19(1), 46–57 (2015)

    Article  Google Scholar 

  3. Breger, A., et al.: Blood vessel segmentation in en-face OCTA images: a frequency based method. CoRR abs/2109.06116 (2021)

    Google Scholar 

  4. Chaudhuri, S., et al.: Detection of blood vessels in retinal images using two-dimensional matched filters. IEEE Trans. Med. Imaging 8(3), 263–269 (1989)

    Article  Google Scholar 

  5. Davis, J., Goadrich, M.: The relationship between precision-recall and roc curves. In: 23rd International Conference on Machine Learning (ICML), pp. 233–240 (2006)

    Google Scholar 

  6. Eladawi, N., et al.: Automatic blood vessels segmentation based on different retinal maps from OCTA scans. Comput. Biol. Med. 89, 150–161 (2017)

    Article  Google Scholar 

  7. Eladawi, N., et al.: Early signs detection of diabetic retinopathy using optical coherence tomography angiography scans based on 3D multi-path convolutional neural network. In: IEEE International Conference on Image Processing (ICIP), pp. 1390–1394 (2019)

    Google Scholar 

  8. Engberg, A.M.E., et al.: Automated quantification of retinal microvasculature from OCT angiography using dictionary-based vessel segmentation. In: 23rd Conference on Medical Image Understanding and Analysis (MIUA), pp. 257–269 (2019)

    Google Scholar 

  9. Erdt, M., Raspe, M., Suehling, M.: Automatic hepatic vessel segmentation using graphics hardware. In: Dohi, T., Sakuma, I., Liao, H. (eds.) Medical Imaging and Augmented Reality. MIAR 2008. LNCS, vol. 5128, pp. 403–412 . Springer, Berlin, Heidelberg (2008). https://doi.org/10.1007/978-3-540-79982-5_44

  10. Faatz, H., et al.: Optical coherence tomography angiography of types 1 and 2 choroidal neovascularization in age-related macular degeneration during anti-vegf therapy: evaluation of a new quantitative method. Eye 33(9), 1466–1471 (2019)

    Article  Google Scholar 

  11. Frangi, A.F., et al.: Multiscale vessel enhancement filtering. In: Wells, W.M., Colchester, A., Delp, S. (eds.) Medical Image Computing and Computer-Assisted Intervention – MICCAI’98. MICCAI 1998. LNCS, vol. 1496, pp. 130–137. Springer, Berlin, Heidelberg (1998). https://doi.org/10.1007/BFb0056195

  12. Fu, W., et al.: Frangi-net. In: Maier, A., Deserno, T., Handels, H., Maier-Hein, K., Palm, C., Tolxdorff, T. (eds.) Bildverarbeitung fur die Medizin 2018. Informatik aktuell, pp. 341–346. Springer Vieweg, Berlin, Heidelberg (2018). https://doi.org/10.1007/978-3-662-56537-7_87

  13. Hao, J., et al.: Retinal structure detection in OCTA image via voting-based multitask learning. IEEE Trans. Med. Imaging 41(12), 3969–3980 (2022)

    Article  Google Scholar 

  14. Hu, K., et al.: Joint-seg: treat foveal avascular zone and retinal vessel segmentation in OCTA images as a joint task. IEEE Trans. Instrum. Meas. 71, 1–13 (2022)

    Google Scholar 

  15. Jerman, T., et al.: Enhancement of vascular structures in 3D and 2D angiographic images. IEEE Trans. Med. Imaging 35(9), 2107–2118 (2016)

    Article  MathSciNet  Google Scholar 

  16. Jia, Y., et al.: Split-spectrum amplitude-decorrelation angiography with optical coherence tomography. Opt. Express 20(4), 4710–4725 (2012)

    Article  Google Scholar 

  17. Kuhlmann, J., et al.: Axial stretching of vessels in the retinal vascular plexus with 3D OCT-angiography. Transl. Vis. Sci. Technol. 11, 21 (2022)

    Article  Google Scholar 

  18. Kumar, K.S., Singh, N.P.: Analysis of retinal blood vessel segmentation techniques: a systematic survey. Multimed. Tools Appl. 82(5), 7679–7733 (2023)

    Article  Google Scholar 

  19. Lamy, J. et al.: Vesselness filters: a survey with benchmarks applied to liver imaging. In: 25th International Conference on Pattern Recognition (ICPR), pp. 3528–3535 (2020)

    Google Scholar 

  20. Lavia, C., Bonnin, S., Maule, M., Erginay, A., Tadayoni, R., Gaudric, A.: Vessel density of superficial intermediate and deep capillary plexus using optical coherence tomography angiography. Retina 39(2), 247–258 (2019)

    Article  Google Scholar 

  21. Li, M., et al.: OCTA-500: a retinal dataset for optical coherence tomography angiography study. CoRR abs/2012.07261 (2020)

    Google Scholar 

  22. Li, M., Zhang, W., Chen, Q.: Image magnification network for vessel segmentation in OCTA images. In: Yu, S., et al. (eds.) Pattern Recognition and Computer Vision. PRCV 2022. LNCS, vol. 13537, pp. 426–435. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-18916-6_35

  23. Li, Q., Sone, S., Doi, K.: Selective enhancement filters for nodules, vessels, and airway walls in two- and three-dimensional CT scans. Med. Phys. 30(8), 2040–2051 (2003)

    Article  Google Scholar 

  24. Li, M., et al.: Image projection network: 3D to 2D image segmentation in OCTA images. IEEE Trans. Med. Imaging 39(11), 3343–3354 (2020)

    Article  Google Scholar 

  25. Lin, T., et al.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 318–327 (2020)

    Google Scholar 

  26. Liu, X., et al.: OCTA retinal vessel segmentation based on vessel thickness inconsistency loss. In: IEEE International Conference on Image Processing (ICIP), pp. 2676–2680 (2022)

    Google Scholar 

  27. Liu, Y., et al.: Projection artifact suppression for inner retina in OCT angiography. In: IEEE 16th International Symposium on Biomedical Imaging (ISBI), pp. 592–596 (2019)

    Google Scholar 

  28. Liu, Y., et al.: Disentangled representation learning for OCTA vessel segmentation with limited training data. IEEE Trans. Med. Imaging 41(12), 3686–3698 (2022)

    Article  Google Scholar 

  29. Läthén, G., Jonasson, J., Borga, M.: Blood vessel segmentation using multi-scale quadrature filtering. Pattern Recognit. Lett. 31, 762–767 (2010)

    Article  Google Scholar 

  30. Ma, Y., et al.: ROSE: a retinal OCT-Angiography vessel segmentation dataset and new model. IEEE Trans. Med. Imaging 40(3), 928–939 (2021)

    Article  Google Scholar 

  31. Ma, Z., et al.: Retinal OCTA image segmentation based on global contrastive learning. Sensors 22(24), 9847 (2022)

    Article  Google Scholar 

  32. Meiburger, K.M., et al.: Automatic segmentation and classification methods using Optical Coherence Tomography Angiography (OCTA): a review and handbook. Appl. Sci. 11, 9734 (2021)

    Article  Google Scholar 

  33. Pissas, T., et al.: Deep iterative vessel segmentation in OCT Angiography. Biomed. Opt. Express 11(5), 2490 (2020)

    Article  Google Scholar 

  34. Ricci, E., Perfetti, R.: Retinal blood vessel segmentation using line operators and support vector classification. IEEE Trans. Med. Imaging 26(10), 1357–1365 (2007)

    Article  Google Scholar 

  35. Sarabi, M.S., et al.: 3D retinal vessel density mapping with OCT-Angiography. IEEE J. Biomed. Health Inform. 24(12), 3466–3479 (2020)

    Article  Google Scholar 

  36. Sato, Y., et al.: Tissue classification based on 3D local intensity structures for volume rendering. IEEE Trans. Med. Imaging 6(2), 160–180 (2000)

    Google Scholar 

  37. Sazak, C., Nelson, C.J., Obara, B.: The multiscale bowler-hat transform for blood vessel enhancement in retinal images. Pattern Recognit. 88, 739–750 (2019)

    Article  Google Scholar 

  38. Spaide, R.F., Klancnik, J.M., Cooney, M.J.: Retinal vascular layers in macular telangiectasia type 2 imaged by optical coherence tomographic angiography. JAMA Ophthalmol. 133(1), 66–73 (2015)

    Article  Google Scholar 

  39. Spaide, R.F., et al.: Optical coherence tomography angiography. Prog. Retin. Eye Res. 64, 1–55 (2018)

    Article  Google Scholar 

  40. Staal, J., Abràmoff, M.D., Niemeijer, M., Viergever, M.A., van Ginneken, B.: Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23(4), 501–509 (2004)

    Article  Google Scholar 

  41. Sule, O.O.: A survey of deep learning for retinal blood vessel segmentation methods: taxonomy, trends, challenges and future directions. IEEE Access 10, 38202–38236 (2022)

    Article  Google Scholar 

  42. Taibouni, K., et al.: Automated quantification of choroidal neovascularization on optical coherence tomography angiography images. Comput. Biol. Med. 114, 103450 (2019)

    Article  Google Scholar 

  43. Xiao, P., et al.: OMSN and FAROS: OCTA microstructure segmentation network and fully annotated retinal OCTA segmentation dataset. CoRR abs/2212.13059 (2022)

    Google Scholar 

  44. Yan, Z., Yang, X., Cheng, K.: A skeletal similarity metric for quality evaluation of retinal vessel segmentation. IEEE Trans. Med. Imaging 37(4), 1045–1057 (2018)

    Article  Google Scholar 

  45. Zana, F., Klein, J.: Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation. IEEE Trans. Image Process. 10(7), 1010–1019 (2001)

    Article  Google Scholar 

  46. Zhang, J., et al.: 3D shape modeling and analysis of retinal microvasculature in OCT-Angiography images. IEEE Trans. Med. Imaging 39(5), 1335–1346 (2020)

    Article  Google Scholar 

  47. Zhou, C., et al.: Automatic multiscale enhancement and segmentation of pulmonary vessels in CT pulmonary angiography images for cad applications. Med. Phys. 34(12), 4567–4577 (2007)

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported by the Dr. Werner Jackstädt-Stiftung.

Author information

Authors and Affiliations

  1. Faculty of Mathematics and Computer Science, University of Münster, Münster, Germany

    Julian Kuhlmann & Xiaoyi Jiang

  2. Department of Ophthalmology, St. Franziskus-Hospital, Münster, Germany

    Kai Rothaus, Henrik Faatz, Daniel Pauleikhoff & Matthias Gutfleisch

Authors
  1. Julian Kuhlmann
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kai Rothaus
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaoyi Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Henrik Faatz
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Daniel Pauleikhoff
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Matthias Gutfleisch
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaoyi Jiang .

Editor information

Editors and Affiliations

  1. IWR, Heidelberg University, Heidelberg, Germany

    Ullrich Köthe

  2. IWR, Heidelberg University, Heidelberg, Germany

    Carsten Rother

Appendix

Appendix

If we overestimate the diameter r of the vessel by p percent (see Fig. 3), then the True Positive Rate will become:

$$\begin{aligned} T\!P\!R_\text {2D}(p) &= \frac{2r}{2r+2pr} = \frac{1}{1+p} \\ T\!P\!R_\text {3D}(p) &= \frac{\pi r^2}{\pi r^2+(\pi (r+pr)^2-\pi r^2)}=\frac{1}{(1+p)^2} \end{aligned}$$

Similarly if we underestimate the vessel diameter by p percent we have Positive Predictive Value:

$$\begin{aligned} P\!PV_\text {2D}(p) &= \frac{2(r-pr)}{2(r-pr)+2pr} = 1-p \\ P\!PV_\text {3D}(p) &= \frac{\pi (r-pr)^2}{\pi (r-pr)^2+(\pi r^2-\pi (r-pr)^2)}=(1-p)^2 \end{aligned}$$

These results can be used to compare the inherent complexity of vessel detection in 2D vs. 3D (see Sect. 2).

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Kuhlmann, J., Rothaus, K., Jiang, X., Faatz, H., Pauleikhoff, D., Gutfleisch, M. (2024). 3D Retinal Vessel Segmentation in OCTA Volumes: Annotated Dataset MORE3D and Hybrid U-Net with Flattening Transformation. In: Köthe, U., Rother, C. (eds) Pattern Recognition. DAGM GCPR 2023. Lecture Notes in Computer Science, vol 14264. Springer, Cham. https://doi.org/10.1007/978-3-031-54605-1_19

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-54605-1_19

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-54604-4

  • Online ISBN: 978-3-031-54605-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation