Enhanced Retina Blood Vessel Segmentation by Super Resolution Generative Adversarial Networks based U-Net

S Sathiya Priya; J G R Sathiaseelan

doi:10.17485/IJST/v14i43.1502

Article

Enhanced Retina Blood Vessel Segmentation by Super Resolution Generative Adversarial Networks based U-Net

VIEWS 1377
PDF 213

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v14i43.1502

Year: 2021, Volume: 14, Issue: 43, Pages: 3246-3253

Original Article

Enhanced Retina Blood Vessel Segmentation by Super Resolution Generative Adversarial Networks based U-Net

S Sathiya Priya^1*, J G R Sathiaseelan¹

¹Department of Computer Science, Bishop Heber College, Affiliated to Bharathidasan University, Trichy, Tamil Nadu, India

*Corresponding Author
Email: [email protected]

Received Date:12 August 2021, Accepted Date:22 October 2021, Published Date:21 December 2021

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: To improve quality of images from video capture under normal illumination through SMART system and the best performance in the task of retina blood vessel segmentation with minimize segmentation loss and recover high resolution feature and makes it possible to evaluate high resolution image. Methods analysis: Existing research were showed for spontaneous segmentation of retina blood vessel from fundus images through supervised and unsupervised techniques. On the other hand, most of the research absence in segmentation robustness and cannot enhance loss functions so that results of the segmentation have made lots of fake. In our research, supervise the value of segmentation loss functions for a number of iterations and supports measure the accuracy of Super Resolution Generative Adversarial Network (SRGAN) method in training process using DRIVE dataset. Findings: We enhanced the AUC of 0.9943 %, Sensitivity of 0.8352 % and specificity of 0.9849 % using through SRGAN-UNet method. We additionally applied overlap tile technique for validation which made it conceivable to segment high resolution with overall precision 0.9736%. Novelty: Our proposed method to produce new-fangled, imitation occurrences of data that can pass for real data processing method that make high resolution images from experimental lower solution images based U-Net.

Keywords: Super Resolution Generative Adversarial Networks; Retina Blood Vessel Segmentation; UNet; overlaptile Technique; Glaucoma Disease; Sensitive Mirror Analyzer and Retina Tracker (SMART) system

References

Park KB, Choi SH, Lee JY. M-GAN: Retinal Blood Vessel Segmentation by Balancing Losses Through Stacked Deep Fully Convolutional Networks. IEEE Access. 2020;8:146308–146322. Available from: https://dx.doi.org/10.1109/access.2020.3015108
Athira S, Francis F, Raphel R, Sachin NS, Porinchu S, Francis S. Smart mirror: A novel framework for interactive display. 2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT). 2016;p. 1–6. doi: 10.1109/ICCPCT.2016.7530197
Fu H, Xu Y, Lin S, Wong DWK, Liu J. DeepVessel: Retinal Vessel Segmentation via Deep Learning and Conditional Random Field. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016. 2016;p. 132–139. Available from: https://doi.org/10.1007/978-3-319-46723-8_16
Akram MU, Atzaz A, Aneeque SF, Khan SA. Blood Vessel Enhancement and Segmentation Using Wavelet Transform. 2009 International Conference on Digital Image Processing. 2009;p. 34–38. doi: 10.1109/icdip.2009.70
Gu Z, Cheng J, Fu H, Zhou K, Hao H, Zhao Y, et al. CE-Net: Context Encoder Network for 2D Medical Image Segmentation. IEEE Transactions on Medical Imaging. 2019;38(10):2281–2292. Available from: https://dx.doi.org/10.1109/tmi.2019.2903562
Srivastava A, Valkov L, Russell C, Gutmann MU, Sutton C. VeeSRGAN: reducing mode collapse in SRGANs using implicit variational learning. Neural Data Processing Systems. 2017;p. 3308–3318. Available from: https://arxiv.org/abs/1705.07761
Chen X, Xu C, Yang X, Song L, Tao D. Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer. IEEE Transactions on Image Processing. 2019;28(2):546–560. Available from: https://dx.doi.org/10.1109/tip.2018.2869695
Martin M, Arjovsky, Soumith, Chintala L, Léon, Bottou. Wasserstein S Generative Adversarial Networks. Proceedings of the 34th International Conference on Machine Learning. 2017;p. 214–223. Available from: https://proceedings.mlr.press/v70/arjovsky17a.html
Guibas JT, Virdi TS, Li PS. Synthetic Medical Images from Dual Generative Adversarial Networks. Synthetic medical Images from dual generative adversarial networks. 2017. Available from: https://arxiv.org/abs/1709.01872
Fan Z, Lu J, Wei C, Huang H, Cai X, Chen X. A Hierarchical Image Matting Model for Blood Vessel Segmentation in Fundus Images. IEEE Transactions on Image Processing. 2019;28(5):2367–2377. Available from: https://dx.doi.org/10.1109/tip.2018.2885495
Jin Q, Meng Z, Pham TD, Leyi QC, Wei R, Dunet. DUNet: A deformable network for retinal vessel segmentation. Knowledge Based System. 2019;178:149–162. Available from: https://doi.org/10.1016/j.knosys.2019.04.025
Staal J, Abramoff MD, Niemeijer M, Viergever MA, Ginneken Bv. Ridge-Based Vessel Segmentation in Color Images of the Retina. IEEE Transactions on Medical Imaging. 2004;23(4):501–509. Available from: https://dx.doi.org/10.1109/tmi.2004.825627
Owen CG, Rudnicka AR, Mullen R, Barman SA, Monekosso D, Whincup PH, et al. Measuring Retinal Vessel Tortuosity in 10-Year-Old Children: Validation of the Computer-Assisted Image Analysis of the Retina (CAIAR) Program. Investigative Opthalmology & Visual Science. 2009;50(5):2004. Available from: https://dx.doi.org/10.1167/iovs.08-3018
Hoover AD, Kouznetsova V, Goldbaum M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Transactions on Medical Imaging. 2000;19(3):203–210. Available from: https://dx.doi.org/10.1109/42.845178
Li L, Verma M, Nakashima Y, Nagahara H, Kawasaki R. IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks. IEEE Applications of Computer Vision. 2020. doi: 10.1109/wacv45572.2020.9093621
Shin SSY, Lee D, Yun ID, Lee KM. Deep Vessel Segmentation By Learning Graphical Connectivity. Medical Image Analysis. 2018. Available from: https://doi.org/10.1016/j.media.2019.101556
Zhuang J. LadderNet: Multi-path networks based on U-Net for medical image segmentation. Multi-path networks based on U-Net for medical image segmentation”,arXiv. 2018. Available from: https://arxiv.org/abs/1810.07810
Guo C, Szemenyei M, Yi Y, Wang W, Chen B, CF, et al. Spatial Attention U-Net for Retinal Vessel Segmentation. IEEE. 2021;p. 1236–1242. doi: 10.1109/ICPR48806.2021.9413346
Zhang Z, Liu Q, Wang Y. Road Extraction by Deep Residual U-Net. IEEE Geoscience and Remote Sensing Letters. 2018;15(5):749–753. Available from: https://dx.doi.org/10.1109/lgrs.2018.2802944
Azad R, Asadi-Aghbolaghi M, Fathy M, Escalera S. Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions. arXiv. 2019. Available from: https://arxiv.org/abs/1909.00166

Copyright

© 2021 Sathiya Priya & Sathiaseelan. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)