{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T20:55:52Z","timestamp":1776459352708,"version":"3.51.2"},"reference-count":39,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T00:00:00Z","timestamp":1608768000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Accurate segmentation of retinal blood vessels is a key step in the diagnosis of fundus diseases, among which cataracts, glaucoma, and diabetic retinopathy (DR) are the main diseases that cause blindness. Most segmentation methods based on deep convolutional neural networks can effectively extract features. However, convolution and pooling operations also filter out some useful information, and the final segmented retinal vessels have problems such as low classification accuracy. In this paper, we propose a multi-scale residual attention network called MRA-UNet. Multi-scale inputs enable the network to learn features at different scales, which increases the robustness of the network. In the encoding phase, we reduce the negative influence of the background and eliminate noise by using the residual attention module. We use the bottom reconstruction module to aggregate the feature information under different receptive fields, so that the model can extract the information of different thicknesses of blood vessels. Finally, the spatial activation module is used to process the up-sampled image to further increase the difference between blood vessels and background, which promotes the recovery of small blood vessels at the edges. Our method was verified on the DRIVE, CHASE, and STARE datasets. Respectively, the segmentation accuracy rates reached 96.98%, 97.58%, and 97.63%; the specificity reached 98.28%, 98.54%, and 98.73%; and the F-measure scores reached 82.93%, 81.27%, and 84.22%. We compared the experimental results with some state-of-art methods, such as U-Net, R2U-Net, and AG-UNet in terms of accuracy, sensitivity, specificity, F-measure, and AUCROC. Particularly, MRA-UNet outperformed U-Net by 1.51%, 3.44%, and 0.49% on DRIVE, CHASE, and STARE datasets, respectively.<\/jats:p>","DOI":"10.3390\/sym13010024","type":"journal-article","created":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T22:56:45Z","timestamp":1608850605000},"page":"24","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["A Multi-Scale Residual Attention Network for Retinal Vessel Segmentation"],"prefix":"10.3390","volume":"13","author":[{"given":"Yun","family":"Jiang","sequence":"first","affiliation":[{"name":"College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3184-9897","authenticated-orcid":false,"given":"Huixia","family":"Yao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China"}]},{"given":"Chao","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China"}]},{"given":"Wenhuan","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China"}]}],"member":"1968","published-online":{"date-parts":[[2020,12,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1016\/j.cmpb.2012.03.009","article-title":"Blood vessel segmentation methodologies in retinal images\u2014A survey","volume":"108","author":"Fraz","year":"2012","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1001\/jamaophthalmol.2013.1743","article-title":"Automated analysis of retinal images for detection of referable diabetic retinopathy","volume":"131","author":"Folk","year":"2013","journal-title":"JAMA Ophthalmol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1016\/j.cmpb.2011.08.009","article-title":"An approach to localize the retinal blood vessels using bit planes and centerline detection","volume":"108","author":"Fraz","year":"2012","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1109\/TPAMI.2012.106","article-title":"Trainable COSFIRE filters for keypoint detection and pattern recognition","volume":"35","author":"Azzopardi","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.bspc.2012.05.005","article-title":"Automatic wavelet-based retinal blood vessels segmentation and vessel diameter estimation","volume":"8","author":"Fathi","year":"2013","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1016\/j.patcog.2012.08.009","article-title":"An effective retinal blood vessel segmentation method using multi-scale line detection","volume":"46","author":"Nguyen","year":"2013","journal-title":"Pattern Recognit."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yin, X.X., Ng, B.W.H., He, J., Zhang, Y., and Abbott, D. (2014, January 22\u201323). Unsupervised segmentation of blood vessels from colour retinal fundus images. Proceedings of the International Conference on Health Information Science, HIS 2014, Shenzhen, China.","DOI":"10.1007\/978-3-319-06269-3_21"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"119","DOI":"10.5626\/JCSE.2014.8.2.119","article-title":"Automatic segmentation of retinal blood vessels based on improved multiscale line detection","volume":"8","author":"Hou","year":"2014","journal-title":"J. Comput. Sci. Eng."},{"key":"ref_9","first-page":"12","article-title":"Segmentation of retinal blood vessels using normalized Gabor filters and automatic thresholding","volume":"55","author":"Tapamo","year":"2014","journal-title":"S. Afr. Comput. J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1016\/j.procs.2015.09.005","article-title":"Retinal blood vessel segmentation approach based on mathematical morphology","volume":"65","author":"Hassan","year":"2015","journal-title":"Procedia Comput. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"204","DOI":"10.4236\/ojmi.2015.54026","article-title":"An improved method for automatic retinal blood vessel vascular segmentation using gabor filter","volume":"5","author":"Karunanayake","year":"2015","journal-title":"Open J. Med. Imaging"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.cmpb.2016.03.001","article-title":"Retinal blood vessels segmentation by using Gumbel probability distribution function based matched filter","volume":"129","author":"Singh","year":"2016","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Orlando, J.I., and Blaschko, M. (2014, January 14\u201318). Learning fully-connected CRFs for blood vessel segmentation in retinal images. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Boston, MA, USA.","DOI":"10.1007\/978-3-319-10404-1_79"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1571","DOI":"10.1166\/jmihi.2015.1565","article-title":"Retinal vessel segmentation using supervised classification based on multi-scale vessel filtering and Gabor wavelet","volume":"5","author":"Tang","year":"2015","journal-title":"J. Med. Imaging Health Inform."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1049\/cje.2016.05.016","article-title":"An ensemble retinal vessel segmentation based on supervised learning in fundus images","volume":"25","author":"Zhu","year":"2016","journal-title":"Chin. J. Electron."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.bspc.2016.05.006","article-title":"A new supervised retinal vessel segmentation method based on robust hybrid features","volume":"30","author":"Aslani","year":"2016","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2181","DOI":"10.1007\/s11548-017-1619-0","article-title":"Multi-level deep supervised networks for retinal vessel segmentation","volume":"12","author":"Mo","year":"2017","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2369","DOI":"10.1109\/TMI.2016.2546227","article-title":"Segmenting retinal blood vessels with deep neural networks","volume":"35","author":"Liskowski","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/s10916-018-1030-6","article-title":"An intelligent model for blood vessel segmentation in diagnosing DR using CNN","volume":"42","author":"Sangeethaa","year":"2018","journal-title":"J. Med. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"075008","DOI":"10.1117\/1.JBO.21.7.075008","article-title":"Segmentation of the foveal microvasculature using deep learning networks","volume":"21","author":"Heisler","year":"2016","journal-title":"J. Biomed. Opt."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.jocs.2017.02.006","article-title":"Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network","volume":"20","author":"Tan","year":"2017","journal-title":"J. Comput. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.compmedimag.2018.04.005","article-title":"Retinal blood vessel segmentation using fully convolutional network with transfer learning","volume":"68","author":"Jiang","year":"2018","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Samuel, P.M., and Veeramalai, T. (2019). Multilevel and Multiscale Deep Neural Network for Retinal Blood Vessel Segmentation. Symmetry, 11.","DOI":"10.3390\/sym11070946"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.eswa.2019.05.029","article-title":"Strided fully convolutional neural network for boosting the sensitivity of retinal blood vessels segmentation","volume":"134","author":"Soomro","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_25","first-page":"012053","article-title":"DA-U-Net: Densely connected convolutional networks and decoder with attention gate for retinal vessel segmentation","volume":"533","author":"Wu","year":"2019","journal-title":"Mater. Sci. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, S., Fu, H., Yan, Y., Zhang, Y., Wu, Q., Yang, M., Tan, M., and Xu, Y. (2019, January 13\u201317). Attention guided network for retinal image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen, China.","DOI":"10.1007\/978-3-030-32239-7_88"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Atli, \u0130., and Gedik, O.S. (2020). Sine-Net: A fully convolutional deep learning architecture for retinal blood vessel segmentation. Eng. Sci. Technol. Int. J.","DOI":"10.1016\/j.jestch.2020.07.008"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"105740","DOI":"10.1016\/j.asoc.2019.105740","article-title":"Application of new deep genetic cascade ensemble of SVM classifiers to predict the Australian credit scoring","volume":"84","author":"Abdar","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1016\/j.ins.2019.12.045","article-title":"DGHNL: A new deep genetic hierarchical network of learners for prediction of credit scoring","volume":"516","author":"Abdar","year":"2020","journal-title":"Inf. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hammad, M., P\u0142awiak, P., Wang, K., and Acharya, U.R. (2020). ResNet-Attention model for human authentication using ECG signals. Expert Syst., e12547.","DOI":"10.1111\/exsy.12547"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2119","DOI":"10.1007\/s11227-020-03205-1","article-title":"Ensemble residual network-based gender and activity recognition method with signals","volume":"76","author":"Tuncer","year":"2020","journal-title":"J. Supercomput."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Qin, X., Wang, Z., Bai, Y., Xie, X., and Jia, H. (2019). FFA-Net: Feature Fusion Attention Network for Single Image Dehazing. arXiv.","DOI":"10.1609\/aaai.v34i07.6865"},{"key":"ref_34","first-page":"2341","article-title":"Single image haze removal using dark channel prior","volume":"33","author":"He","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_35","unstructured":"Zhuang, J. (2018). Laddernet: Multi-path networks based on u-net for medical image segmentation. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Zhang, H., Tan, N., and Chen, L. (2019). Automatic Retinal Blood Vessel Segmentation Based on Fully Convolutional Neural Networks. Symmetry, 11.","DOI":"10.3390\/sym11091112"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"He, K., and Sun, J. (2015, January 7\u201312). Convolutional neural networks at constrained time cost. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., and Asari, V.K. (2018). Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation. arXiv.","DOI":"10.1109\/NAECON.2018.8556686"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"32826","DOI":"10.1109\/ACCESS.2020.2974027","article-title":"Attention Guided U-Net With Atrous Convolution for Accurate Retinal Vessels Segmentation","volume":"8","author":"Lv","year":"2020","journal-title":"IEEE Access"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/13\/1\/24\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:45:57Z","timestamp":1760179557000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/13\/1\/24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,24]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["sym13010024"],"URL":"https:\/\/doi.org\/10.3390\/sym13010024","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,24]]}}}