Dual-channel asymmetric convolutional neural network for an efficient retinal blood vessel segmentation in eye fundus images

• Autorzy: Xu Yanan , Fan Yingle

Identyfikatory

DOI

10.1016/j.bbe.2022.05.003

• Języki publikacji: EN

Abstrakty

EN

The morphological properties of retinal vessels are closely related to the diagnosis of ophthalmic diseases. However, many problems in retinal images, such as complicated directions of vessels and difficult recognition of capillaries, bring challenges to the accurate segmentation of retinal blood vessels. Thus, we propose a new retinal blood vessel segmentation method based on a dual-channel asymmetric convolutional neural network (CNN). First, we construct the thick and thin vessel extraction module based on the morphological differences in retinal vessels. A two-dimensional (2D) Gabor filter is used to perceive the scale characteristics of blood vessels after selecting the direction of blood vessels; thereby, adaptively extracting the thick vessel features characterizing the overall characteristics and the thin vessel features preserving the capillaries from fundus images. Then, considering that the single-channel network is unsuitable for the unified characterization of thick and thin vessels, we develop a dual-channel asymmetric CNN based on the U-Net model. The MainSegment-Net uses the step-by-step connection mode to achieve rapid positioning and segmentation of thick vessels; the FineSegment-Net combines dilated convolution and the skip connection to achieve the fine extraction of thin vessels. Finally, the output of the dual-channel asymmetric CNN is fused and coded to combine the segmentation results of thick and thin vessels. The performance of our method is evaluated and tested by DRIVE and CHASE_DB1. The results show that the accuracy (Acc), sensitivity (SE), and specificity (SP) of our method on the DRIVE database are 0.9630, 0.8745, and 0.9823, respectively. The evaluation indexes Acc, SE, and SP of the CHASE_DB1 database are 0.9694, 0.8916, and 0.9794, respectively. Additionally, our method combines the biological vision mechanism with deep learning to achieve rapid and automatic segmentation of retinal vessels, providing a new idea for diagnosing and analyzing subsequent medical images.

Słowa kluczowe

EN

retinal image; blood vessel segmentation; 2D Gabor filter; convolutional neural network; dilated convolution; feature fusion

PL

obraz siatkówki oka; segmentacja naczyń krwionośnych; sieć neuronowa konwolucyjna; fuzja funkcji

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 2
• Strony: 695--706
• Opis fizyczny: Bibliogr. 35 poz., rys., tab., wykr.

Twórcy

autor

Xu Yanan

• Laboratory of Pattern Recognition and Image Processing, Hangzhou Dianzi University, Hangzhou, China

autor

Fan Yingle

• Laboratory of Pattern Recognition and Image Processing, Hangzhou Dianzi University, Hangzhou 310018, China

Bibliografia

• [1] Prasad Reddy PVGD. Blood vessel extraction in fundus images using hessian eigenvalues and adaptive thresholding. Evol Intel 2021;14(2):577–82.
• [2] Ramos-Soto O, Rodríguez-Esparza E, Balderas-Mata SE, Oliva D, Hassanien AE, Meleppat RK, et al. An efficient retinal blood vessel segmentation in eye fundus images by using optimized top-hat and homomorphic filtering. Comput Methods Prog Biomed 2021;201. 105949.
• [3] Tian C, Fang T, Fan Y, Wu W. Multi-path convolutional neural network in fundus segmentation of blood vessels. Biocybern Biomed Eng 2020;40(2):583–95.
• [4] Farokhian F, Yang C, Demirel H, Wu S, Beheshti I. Automatic parameters selection of Gabor filters with the imperialism competitive algorithm with application to retinal vessel segmentation. Biocybern Biomed Eng 2017;37(1):246–54.
• [5] Tchinda BS, Tchiotsop D, Noubom M, Louis-Dorr V, Wolf D. Retinal blood vessels segmentation using classical edge detection filters and the neural network. Inform Med Unlock 2021;23(3). 100521.
• [6] Samuel PM, Veeramalai T. VSSC Net: Vessel Specific Skip chain Convolutional Network for blood vessel segmentation. Comput Methods Prog Biomed 2021;198. 105769.
• [7] Oliveira A, Pereira S, Silva CA. Retinal vessel segmentation based on Fully Convolutional Neural Networks. Expert Syst Appl 2018;112:229–42.
• [8] Li Z, Jia M, Yang X, Xu M. Blood vessel segmentation of retinal image based on Dense-U-Net Network. Micromachines 2021;12(12):1478.
• [9] Liu C, Gu P, Xiao Z, Tang J. Multiscale U-Net with spatial positional attention for retinal vessel segmentation. J Healthc Eng 2022;2022:1–10.
• [10] Chaudhuri S, Chatterjee S, Katz N, Nelson M, Goldbaum M. Detection of blood vessels in retinal images using two-dimensional matched filters. IEEE Trans Med Imaging 1989;8(3):263–9.
• [11] Hugo AR, Gabriel ACJ, Ivan CA, José RP, Sergio L. Blood vessel segmentation in retinal fundus images using Gabor filters, fractional derivatives, and Expectation Maximization. Appl Math Comput 2018;339:568–87.
• [12] Luo ZL, Jia Y. The comparison of retinal vessel segmentation methods in fundus images. J Phys Conf Ser 2020;1574. 012160.
• [13] Delibasis KK, Kechriniotis AI, Tsonos C, Assimakis N. Automatic model-based tracing algorithm for vessel segmentation and diameter estimation. Comput Methods Prog Biomed 2010;99(2):108–22.
• [14] Zhao J, Yang J, Ai D, Song H, Jiang Y, Huang Y, et al. Automatic retinal vessel segmentation using multi-scale superpixel chain tracking. Digit Signal Process 2018;81:26–42.
• [15] Tian F, Li Y, Wang J, Chen W, Hemanth J. Blood vessel segmentation of fundus retinal images based on improved frangi and mathematical morphology. Comput Math Methods Med 2021;2021:1–11.
• [16] Geetharamani R, Balasubramanian L. Retinal blood vessel segmentation employing image processing and data mining techniques for computerized retinal image analysis. Biocybern Biomed Eng 2016;36(1):102–18.
• [17] Ding JQ, Zhang ZH, Tang JJ, Guo F. A multichannel deep neural network for retina vessel segmentation via a fusion mechanism. Front Bioeng Biotech 2021;9. 697915.
• [18] Orlando JI, Prokofyeva E, Blaschko MB. A discriminatively trained fully connected conditional random field model for blood vessel segmentation in fundus images. IEEE Trans Biomed Eng 2017;64(1):16–27.
• [19] Fu H, Xu Y, Wong DWK, Liu J. Retinal vessel segmentation via deep learning network and fully-connected conditional random fields. In: IEEE 13th International Symposium on Biomedical Imaging (ISBI). p. 698–701.
• [20] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 2017;39(4):640–51.
• [21] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. Medical Image Comput Comput-Assisted Intervention 2015;9351:234–41.
• [22] 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 Trans Med Imaging 2019;38(10):2281–92.
• [23] Pan X, Zhang Q, Zhang H, Li S. A fundus retinal vessels segmentation scheme based on the improved deep learning U-Net model. IEEE Access 2019;7:122634–43.
• [24] Cloutman LL. Interaction between dorsal and ventral processing streams: Where, when and how? Brain Lang 2013;127(2):251–63.
• [25] Pathan S, Kumar P, Pai R, Bhandary SV. Automated detection of optic disc contours in fundus images using decision tree classifier. Biocybern Biomed Eng 2019;40(1):52–64.
• [26] Spratling MW. Image segmentation using a sparse coding model of cortical area V1. IEEE Trans Image Process 2013;22(4):1631–43.
• [27] Fang A, Zhao X, Zhang Y. Cross-modal image fusion guided by subjective visual attention. Neurocomputing 2020;414:333–45.
• [28] David SA, Mahesh C, Kumar VD, Polat K, Alhudhaif A, Nour M, et al. Retinal blood vessels and optic disc segmentation using U-Net. Math Probl Eng 2022;2022:1–11.
• [29] Staal J, Abràmoff MD, Niemeijer M, Viergever MA, Ginneken BV. Ridge-based vessel segmentation in color images of the retina. IEEE Trans Med Imaging 2004;23(4):501–9.
• [30] Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B, Rudnicka AR, Owen CG, et al. An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Trans Biomed Eng 2012;59(9):2538–48.
• [31] Khan TM, Khan MAU, Rehman NU, Naveed K, Afridi IU, Naqvi SS, et al. Width-wise vessel bifurcation for improved retinal vessel segmentation. Biomed Signal Process Control 2022;71.
• [32] Khawaja A, Khan TM, Khan MAU, Nawaz SJ. A multi-scale directional line detector for retinal vessel segmentation. Sensors 2019;19(22):4949.
• [33] Peng S, Zheng C, Xu F, Xiao H, Nam HD, Wu Y. Blood vessels segmentation by using CDNet. In: IEEE 3rd International Conference on Image, Vision and Computing (ICIVC). p. 305–15.
• [34] Yan Z, Yang X, Cheng KTT. Joint segment-level and pixel-wise losses for deep learning based retinal vessel segmentation. IEEE Trans Biomed Eng 2018;65(9):1912–23.
• [35] Li Q, Feng B, Xie LP, Liang P, Zhang H, Wang T. A Crossmodality Learning Approach for Vessel Segmentation in Retinal Images. IEEE Trans Med Imaging 2016;35(1):109–18.