Research on segmentation model of optic disc and optic cup in fundus.
Deep learning
Fundus image segmentation
Glaucoma screening
REFUGE dataset
YOLO model
Journal
BMC ophthalmology
ISSN: 1471-2415
Titre abrégé: BMC Ophthalmol
Pays: England
ID NLM: 100967802
Informations de publication
Date de publication:
28 Jun 2024
28 Jun 2024
Historique:
received:
04
01
2024
accepted:
20
06
2024
medline:
29
6
2024
pubmed:
29
6
2024
entrez:
29
6
2024
Statut:
epublish
Résumé
Glaucoma is a worldwide eye disease that can cause irreversible vision loss. Early detection of glaucoma is important to reduce vision loss, and retinal fundus image examination is one of the most commonly used solutions for glaucoma diagnosis due to its low cost. Clinically, the cup-disc ratio of fundus images is an important indicator for glaucoma diagnosis. In recent years, there have been an increasing number of algorithms for segmentation and recognition of the optic disc (OD) and optic cup (OC), but these algorithms generally have poor universality, segmentation performance, and segmentation accuracy. By improving the YOLOv8 algorithm for segmentation of OD and OC. Firstly, a set of algorithms was designed to adapt the REFUGE dataset's result images to the input format of the YOLOv8 algorithm. Secondly, in order to improve segmentation performance, the network structure of YOLOv8 was improved, including adding a ROI (Region of Interest) module, modifying the bounding box regression loss function from CIOU to Focal-EIoU. Finally, by training and testing the REFUGE dataset, the improved YOLOv8 algorithm was evaluated. The experimental results show that the improved YOLOv8 algorithm achieves good segmentation performance on the REFUGE dataset. In the OD and OC segmentation tests, the F1 score is 0.999. We improved the YOLOv8 algorithm and applied the improved model to the segmentation task of OD and OC in fundus images. The results show that our improved model is far superior to the mainstream U-Net model in terms of training speed, segmentation performance, and segmentation accuracy.
Sections du résumé
BACKGROUND
BACKGROUND
Glaucoma is a worldwide eye disease that can cause irreversible vision loss. Early detection of glaucoma is important to reduce vision loss, and retinal fundus image examination is one of the most commonly used solutions for glaucoma diagnosis due to its low cost. Clinically, the cup-disc ratio of fundus images is an important indicator for glaucoma diagnosis. In recent years, there have been an increasing number of algorithms for segmentation and recognition of the optic disc (OD) and optic cup (OC), but these algorithms generally have poor universality, segmentation performance, and segmentation accuracy.
METHODS
METHODS
By improving the YOLOv8 algorithm for segmentation of OD and OC. Firstly, a set of algorithms was designed to adapt the REFUGE dataset's result images to the input format of the YOLOv8 algorithm. Secondly, in order to improve segmentation performance, the network structure of YOLOv8 was improved, including adding a ROI (Region of Interest) module, modifying the bounding box regression loss function from CIOU to Focal-EIoU. Finally, by training and testing the REFUGE dataset, the improved YOLOv8 algorithm was evaluated.
RESULTS
RESULTS
The experimental results show that the improved YOLOv8 algorithm achieves good segmentation performance on the REFUGE dataset. In the OD and OC segmentation tests, the F1 score is 0.999.
CONCLUSIONS
CONCLUSIONS
We improved the YOLOv8 algorithm and applied the improved model to the segmentation task of OD and OC in fundus images. The results show that our improved model is far superior to the mainstream U-Net model in terms of training speed, segmentation performance, and segmentation accuracy.
Identifiants
pubmed: 38943095
doi: 10.1186/s12886-024-03532-4
pii: 10.1186/s12886-024-03532-4
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
273Subventions
Organisme : Wenzhou Municipal Science and Technology Bureau
ID : Y20220760
Informations de copyright
© 2024. The Author(s).
Références
Wang L, et al. Computerized assessment of glaucoma severity based on color fundus images. Medical imaging 2019: Biomedical Applications in Molecular, Structural, and functional imaging. SPIE; 2019.
Quigley HA, Broman AT. The number of people with glaucoma worldwide in 2010 and 2020. Br J Ophthalmol. 2006;90(3):262–7.
pubmed: 16488940
pmcid: 1856963
doi: 10.1136/bjo.2005.081224
Tham Y-C, et al. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology. 2014;121(11):2081–90.
pubmed: 24974815
doi: 10.1016/j.ophtha.2014.05.013
Baum J, et al. Assessment of intraocular pressure by palpation. Am J Ophthalmol. 1995;119(5):650–1.
pubmed: 7733191
doi: 10.1016/S0002-9394(14)70227-2
Drance S, et al. Risk factors for progression of visual field abnormalities in normal-tension glaucoma. Am J Ophthalmol. 2001;131(6):699–708.
pubmed: 11384564
doi: 10.1016/S0002-9394(01)00964-3
Garway-Heath D, Hitchings R. Quantitative evaluation of the optic nerve head in early glaucoma. Br J Ophthalmol. 1998;82(4):352–61.
pubmed: 9640180
pmcid: 1722573
doi: 10.1136/bjo.82.4.352
Jonas JB, et al. Ranking of optic disc variables for detection of glaucomatous optic nerve damage. Investig Ophthalmol Vis Sci. 2000;41(7):1764–73.
Thakur N, Juneja M. Survey on segmentation and classification approaches of optic cup and optic disc for diagnosis of glaucoma. Biomed Signal Process Control. 2018;42:162–89.
doi: 10.1016/j.bspc.2018.01.014
Sivaswamy J, et al. A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis. JSM Biomedical Imaging Data Papers. 2015;2(1):1004.
Lim G et al. Integrated optic disc and cup segmentation with deep learning. in. 2015 IEEE 27th International Conference on Tools with Artificial Intelligence (ICTAI). 2015. IEEE.
Lodhia V, et al. Acceptability, usability, and views on deployment of peek, a mobile phone mhealth intervention for eye care in Kenya: qualitative study. JMIR mHealth uHealth. 2016;4(2):e4746.
doi: 10.2196/mhealth.4746
Roychowdhury S, et al. Optic disc boundary and vessel origin segmentation of fundus images. IEEE J Biomedical Health Inf. 2015;20(6):1562–74.
doi: 10.1109/JBHI.2015.2473159
Lalonde M, Beaulieu M, Gagnon L. Fast and robust optic disc detection using pyramidal decomposition and Hausdorff-based template matching. IEEE Trans Med Imaging. 2001;20(11):1193–200.
pubmed: 11700746
doi: 10.1109/42.963823
Zheng Y et al. Optic disc and cup segmentation from color fundus photograph using graph cut with priors. in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22–26, 2013, Proceedings, Part II 16. 2013. Springer.
Aquino A, Gegúndez-Arias ME, Marín D. Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques. IEEE Trans Med Imaging. 2010;29(11):1860–9.
pubmed: 20562037
doi: 10.1109/TMI.2010.2053042
Giachetti A, Ballerini L, Trucco E. Accurate and reliable segmentation of the optic disc in digital fundus images. J Med Imaging. 2014;1(2):024001–024001.
doi: 10.1117/1.JMI.1.2.024001
Dai B, Wu X, Bu W. Optic disc segmentation based on variational model with multiple energies. Pattern Recogn. 2017;64:226–35.
doi: 10.1016/j.patcog.2016.11.017
Haleem MS, et al. A novel adaptive deformable model for automated optic disc and cup segmentation to aid glaucoma diagnosis. J Med Syst. 2018;42:1–18.
doi: 10.1007/s10916-017-0859-4
Joshi GD, Sivaswamy J, Krishnadas S. Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment. IEEE Trans Med Imaging. 2011;30(6):1192–205.
pubmed: 21536531
doi: 10.1109/TMI.2011.2106509
Xu J, et al. Optic disk feature extraction via modified deformable model technique for glaucoma analysis. Pattern Recogn. 2007;40(7):2063–76.
doi: 10.1016/j.patcog.2006.10.015
Li T, et al. Applications of deep learning in fundus images: a review. Med Image Anal. 2021;69:101971.
pubmed: 33524824
doi: 10.1016/j.media.2021.101971
Edupuganti VG, Chawla A, Kale A. Automatic optic disk and cup segmentation of fundus images using deep learning. in 2018 25th IEEE international conference on image processing (ICIP). 2018. IEEE.
Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5–9, 2015, Proceedings, Part III 18. 2015. Springer.
Goodfellow I et al. Generative adversarial nets. Adv Neural Inf Process Syst, 2014. 27.
Mohan D, Kumar JH, Seelamantula CS. High-performance optic disc segmentation using convolutional neural networks. in 2018 25th IEEE international conference on image processing (ICIP). 2018. IEEE.
Mohan D, Kumar JH, Seelamantula CS. Optic disc segmentation using cascaded multiresolution convolutional neural networks. in 2019 IEEE International Conference on Image Processing (ICIP). 2019. IEEE.
Liu Q, et al. A spatial-aware joint optic disc and cup segmentation method. Neurocomputing. 2019;359:285–97.
doi: 10.1016/j.neucom.2019.05.039
Fu H, et al. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation. IEEE Trans Med Imaging. 2018;37(7):1597–605.
pubmed: 29969410
doi: 10.1109/TMI.2018.2791488
Gu Z, et al. Ce-net: Context encoder network for 2d medical image segmentation. IEEE Trans Med Imaging. 2019;38(10):2281–92.
pubmed: 30843824
doi: 10.1109/TMI.2019.2903562
Yu S, et al. Robust optic disc and cup segmentation with deep learning for glaucoma detection. Comput Med Imaging Graph. 2019;74:61–71.
pubmed: 31022592
doi: 10.1016/j.compmedimag.2019.02.005
Zhang Y, et al. TAU: transferable attention U-Net for optic disc and cup segmentation. Knowl Based Syst. 2021;213:106668.
doi: 10.1016/j.knosys.2020.106668
Wang S, et al. Patch-based output space adversarial learning for joint optic disc and cup segmentation. IEEE Trans Med Imaging. 2019;38(11):2485–95.
pubmed: 30794170
doi: 10.1109/TMI.2019.2899910
Wang S et al. Boundary and entropy-driven adversarial learning for fundus image segmentation. in Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part I 22. 2019. Springer.
Chen N. (2024). REFUGE. figshare. Figure. https://doi.org/10.6084/m9.figshare.26049574.v2 .
Kim J, et al. Identifying those at risk of glaucoma: a deep learning approach for optic disc and cup segmentation and their boundary analysis. Diagnostics. 2022;12(5):1063.
pubmed: 35626219
pmcid: 9139683
doi: 10.3390/diagnostics12051063
Bochkovskiy A, Wang C-Y, Liao H-YM. Yolov4: Optimal speed and accuracy of object detection arXiv preprint arXiv:2004.10934, 2020.
Zhang H et al. mixup: Beyond empirical risk minimization arXiv preprint arXiv:1710.09412, 2017.
Redmon J et al. You only look once: Unified, real-time object detection. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
Ren S et al. Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst, 2015. 28.
Liu W et al. Ssd: Single shot multibox detector. in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. 2016. Springer.
Zheng Z, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans Cybernetics. 2021;52(8):8574–86.
doi: 10.1109/TCYB.2021.3095305
Zhang Y-F, et al. Focal and efficient IOU loss for accurate bounding box regression. Neurocomputing. 2022;506:146–57.
doi: 10.1016/j.neucom.2022.07.042
Minaee S, et al. Image segmentation using deep learning: a survey. IEEE Trans Pattern Anal Mach Intell. 2021;44(7):3523–42.
Bian X, et al. Optic disc and optic cup segmentation based on anatomy guided cascade network. Comput Methods Programs Biomed. 2020;197:105717.
pubmed: 32957060
doi: 10.1016/j.cmpb.2020.105717
Jiang Y, et al. RSAP-Net: joint optic disc and cup segmentation with a residual spatial attention path module and MSRCR-PT pre-processing algorithm. BMC Bioinformatics. 2022;23(1):523.
pubmed: 36474136
pmcid: 9727976
doi: 10.1186/s12859-022-05058-2