Abstract
Retina vessel segmentation plays an important role in the field of clinical imaging for the detection of ophthalmologic and cardiovascular diseases like hypertension, glaucoma, diabetic retinopathy, and choroidal neovascularization. Automatic segmentation of the retina blood vessel results in earlier detection of these diseases which helps in early treatment. Various deep learning models have been proposed for the semantic segmentation of the images. In this paper, five efficient and popular deep learning models have been trained and tested for the purpose of semantic segmentation. These five models are U-Net, ENet, SegNet, U-Net with ResNet34, and U-Net with ResNet18. The models have been compared on three vital parameters of segmentation, namely IoU score, accuracy, and loss functions. During training ENet performs better but suffers from the problem of overfitting during testing and validation phase. U-Net with ResNet 34 has outperformed during testing, achieving 96.4% accuracy, and 89.75% IoU score.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kanski, J.J. , Bowling, B.: Clinical Ophthalmology: A Systematic Approach. Elsevier Health Sciences (2011)
Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: Enet: A deep neural network architecture for real-time semantic segmentation (2016). arXiv preprint arXiv:1606.02147
Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). arXiv preprint arXiv:1502.03167
Badrinarayanan, V., Mishra, B., Cipolla, R.: Understanding symmetries in deep networks (2015). arXiv preprint arXiv:1511.01029
Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234–241. Springer (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Introduction-drive-grand challenge. https://drive.grand-challenge.org/. Accessed on 28 Dec 2020
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tiwari, T., Saraswat, M. (2022). Comparative Analysis of Semantic Segmentation by Using Deep Learning Models on Retinal Vessel. In: Saraswat, M., Roy, S., Chowdhury, C., Gandomi, A.H. (eds) Proceedings of International Conference on Data Science and Applications. Lecture Notes in Networks and Systems, vol 287. Springer, Singapore. https://doi.org/10.1007/978-981-16-5348-3_25
Download citation
DOI: https://doi.org/10.1007/978-981-16-5348-3_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-5347-6
Online ISBN: 978-981-16-5348-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)