Retinal Blood Vessel Segmentation Based on Encoder and Decoder Networks Using Weighted Cross Entropy Loss Function
DOI:
https://doi.org/10.15408/adalah.v9i6.44857Keywords:
Diabetic retinopathy, Retinal blood vessels, Pre-trained transfer learning, Deep learning, Semantic segmentation.Abstract
Retinal disease that has a major impact on human vision is diabetic retinopathy. Diabetic retinopathy is a disease caused by advanced diabetic mellitus. Early detection of the disease is very importance. An automated system that can recognize retinal blood vessel abnormalities is very useful for providing quick information to prevent further damage to the retina. In this study, we propose an automated system for segmenting the blood vessels in retinal fundus images using semantic segmentation based on pre-trained from VGG transfer learning and using median frequency balancing weights for the cross entropy loss function. The median frequency weights are to balance the importance of blood vessel and background pixels to get more accurate training results. The integration of encoder and decoder networks utilizing VGG transfer learning and semantic segmentation can segment retinal blood vessels with a sensitivity value of 85.48% using the DRIVE and STARE database.References
The Expert Committee on the Diagnosis and Classification of Diabetes Mellitus, “Report of the Expert Committee on the Diagnosis and Classification of Diabetes Mellitus,” Diabetes Care, vol. 26, pp. 5–20, 2003.
American Diabetes Association, “Diagnosis and Classification of Diabetes Mellitus,” Diabetes Care, vol. 33, pp. 62–69, 2010.
F. Harney, “Diabetic retinopathy,” Medicine (Baltimore)., vol. 34, pp. 95–98, 2006.
V. Gupta, A. Gupta, M. R. Dogra, and R. Singh, Diabetic Retinopathy Atlas. 2007.
A. A. Alghadyan, “Diabetic retinopathy - An update,” Saudi J. Ophthalmol. Off. J. Saudi Ophthalmol. Soc., vol. 25, pp. 99–111, Apr. 2011.
T. Kauppi et al., “DIARETDB1 diabetic retinopathy database and evaluation protocol,” in Proc. Medical Image Understanding and Analysis, 2007, pp. 1–18.
D. U. N. Qomariah and H. Tjandrasa, “Exudate detection in retinal fundus images using combination of mathematical morphology and Renyi entropy thresholding,” in 2017 11th International Conference on Information & Communication Technology and System, 2017, pp. 31–36.
H. Tjandrasa, A. Wijayanti, and N. Suciati, “Optic Nerve Head Segmentation Using Hough Transform and Active Contours,” TELKOMNIKA, vol. 10, pp. 531–536, 2012.
Y. LeCun, Y. Bengio, and G. Hinton, Deep Learning. 2015.
H. Roth et al., “Deep learning and its application to medical image segmentation,” CoRR, pp. 1–6, 2018.
H. Greenspan, B. van Ginneken, and R. M. Summers, “Guest Editorial Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique,” IEEE Trans. Med. Imaging, vol. 35, pp. 1153–1159, 2016.
B. Kayalıbay, G. Jensen, and P. van der Smagt, CNN-based Segmentation of Medical Imaging Data. 2017.
E. Shelhamer, J. Long, and T. Darrell, “Fully Convolutional Networks for Semantic Segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, pp. 640–651, Apr. 2017.
H. Noh, S. Hong, and B. Han, “Learning Deconvolution Network for Semantic Segmentation,” in Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015, pp. 1520–1528.
M. M. Fraz et al., “Blood vessel segmentation methodologies in retinal images – A survey,” Comput. Methods Programs Biomed., vol. 108, pp. 407–433, 2012.
J. Staal, M. D. Abramoff, M. Niemeijer, M. A. Viergever, and B. van Ginneken, “Ridge-based vessel segmentation in color images of the retina,” IEEE Trans. Med. Imaging, vol. 23, pp. 501–509, 2004.
J. V. B. Soares, J. J. G. Leandro, R. M. Cesar, H. F. Jelinek, and M. J. Cree, “Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification,” IEEE Trans. Med. Imaging, vol. 25, pp. 1214–1222, 2006.
A. Oliveira, S. Pereira, and C. A. Silva, “Retinal vessel segmentation based on Fully Convolutional Neural Networks,” Expert Syst. Appl., vol. 112, pp. 229–242, 2018.
D. Marin, A. Aquino, M. E. Gegundez-Arias, and J. M. Bravo, “A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Gray-Level and Moment Invariants-Based Features,” IEEE Trans. Med. Imaging, vol. 30, pp. 146–158, 2011.
E. Ricci and R. Perfetti, “Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification,” IEEE Trans. Med. Imaging, vol. 26, pp. 1357–1365, 2007.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.
S. Wang, Y. Yin, G. Cao, B. Wei, Y. Zheng, and G. Yang, “Hierarchical retinal blood vessel segmentation based on feature and ensemble learning,” Neurocomputing, vol. 149, pp. 708–717, 2015.
P. Liskowski and K. Krawiec, “Segmenting Retinal Blood Vessels With Deep Neural Networks,” IEEE Trans. Med. Imaging, vol. 35, pp. 2369–2380, 2016.
H. Fu, Y. Xu, D. W. K. Wong, and J. Liu, “Retinal vessel segmentation via deep learning network and fully-connected conditional random fields,” in 2016 IEEE 13th International Symposium on Biomedical Imaging, 2016, pp. 698–701.
T. A. Soomro et al., “Boosting Sensitivity of a Retinal Vessel Segmentation Algorithm with Convolutional Neural Network,” in 2017 International Conference on Digital Image Computing: Techniques and Applications, 2017, pp. 1–8.
Z. Jiang, H. Zhang, Y. Wang, and S.-B. Ko, “Retinal blood vessel segmentation using fully convolutional network with transfer learning,” Comput. Med. Imaging Graph., vol. 68, pp. 1–15, 2018.
Q. Li, B. Feng, L. Xie, P. Liang, H. Zhang, and T. Wang, “A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images,” IEEE Trans. Med. Imaging, vol. 35, pp. 109–118, 2016.
“The Stare Project – Structured Analysis of the Retina,” 1975. [Online]. Available: http://cecas.clemson.edu/~ahoover/stare/.
E. Decencière et al., “Feedback on a publicly distributed image database: The Messidor database,” Image Anal. Stereol., vol. 33, pp. 231–234, 2014.
P. Porwal et al., “Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening Research,” Data, vol. 3, p. 25, 2018.
