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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
Azzopardi, G., et al.: Trainable COSFIRE filters for vessel delineation with application to retinal images. Med. Image Anal. 19(1), 46–57 (2015)
Breger, A., et al.: Blood vessel segmentation in en-face OCTA images: a frequency based method. CoRR abs/2109.06116 (2021)
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)
Davis, J., Goadrich, M.: The relationship between precision-recall and roc curves. In: 23rd International Conference on Machine Learning (ICML), pp. 233–240 (2006)
Eladawi, N., et al.: Automatic blood vessels segmentation based on different retinal maps from OCTA scans. Comput. Biol. Med. 89, 150–161 (2017)
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)
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)
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
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)
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
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
Hao, J., et al.: Retinal structure detection in OCTA image via voting-based multitask learning. IEEE Trans. Med. Imaging 41(12), 3969–3980 (2022)
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)
Jerman, T., et al.: Enhancement of vascular structures in 3D and 2D angiographic images. IEEE Trans. Med. Imaging 35(9), 2107–2118 (2016)
Jia, Y., et al.: Split-spectrum amplitude-decorrelation angiography with optical coherence tomography. Opt. Express 20(4), 4710–4725 (2012)
Kuhlmann, J., et al.: Axial stretching of vessels in the retinal vascular plexus with 3D OCT-angiography. Transl. Vis. Sci. Technol. 11, 21 (2022)
Kumar, K.S., Singh, N.P.: Analysis of retinal blood vessel segmentation techniques: a systematic survey. Multimed. Tools Appl. 82(5), 7679–7733 (2023)
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)
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)
Li, M., et al.: OCTA-500: a retinal dataset for optical coherence tomography angiography study. CoRR abs/2012.07261 (2020)
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
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)
Li, M., et al.: Image projection network: 3D to 2D image segmentation in OCTA images. IEEE Trans. Med. Imaging 39(11), 3343–3354 (2020)
Lin, T., et al.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 318–327 (2020)
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)
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)
Liu, Y., et al.: Disentangled representation learning for OCTA vessel segmentation with limited training data. IEEE Trans. Med. Imaging 41(12), 3686–3698 (2022)
Läthén, G., Jonasson, J., Borga, M.: Blood vessel segmentation using multi-scale quadrature filtering. Pattern Recognit. Lett. 31, 762–767 (2010)
Ma, Y., et al.: ROSE: a retinal OCT-Angiography vessel segmentation dataset and new model. IEEE Trans. Med. Imaging 40(3), 928–939 (2021)
Ma, Z., et al.: Retinal OCTA image segmentation based on global contrastive learning. Sensors 22(24), 9847 (2022)
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)
Pissas, T., et al.: Deep iterative vessel segmentation in OCT Angiography. Biomed. Opt. Express 11(5), 2490 (2020)
Ricci, E., Perfetti, R.: Retinal blood vessel segmentation using line operators and support vector classification. IEEE Trans. Med. Imaging 26(10), 1357–1365 (2007)
Sarabi, M.S., et al.: 3D retinal vessel density mapping with OCT-Angiography. IEEE J. Biomed. Health Inform. 24(12), 3466–3479 (2020)
Sato, Y., et al.: Tissue classification based on 3D local intensity structures for volume rendering. IEEE Trans. Med. Imaging 6(2), 160–180 (2000)
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)
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)
Spaide, R.F., et al.: Optical coherence tomography angiography. Prog. Retin. Eye Res. 64, 1–55 (2018)
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)
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)
Taibouni, K., et al.: Automated quantification of choroidal neovascularization on optical coherence tomography angiography images. Comput. Biol. Med. 114, 103450 (2019)
Xiao, P., et al.: OMSN and FAROS: OCTA microstructure segmentation network and fully annotated retinal OCTA segmentation dataset. CoRR abs/2212.13059 (2022)
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)
Zana, F., Klein, J.: Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation. IEEE Trans. Image Process. 10(7), 1010–1019 (2001)
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)
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)
Acknowledgments
This work was supported by the Dr. Werner Jackstädt-Stiftung.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
If we overestimate the diameter r of the vessel by p percent (see Fig. 3), then the True Positive Rate will become:
Similarly if we underestimate the vessel diameter by p percent we have Positive Predictive Value:
These results can be used to compare the inherent complexity of vessel detection in 2D vs. 3D (see Sect. 2).
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
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)