{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T23:31:58Z","timestamp":1780097518040,"version":"3.54.0"},"reference-count":54,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2020,7,24]],"date-time":"2020-07-24T00:00:00Z","timestamp":1595548800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51607029"],"award-info":[{"award-number":["51607029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836011"],"award-info":[{"award-number":["61836011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2020GFZD008"],"award-info":[{"award-number":["2020GFZD008"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Computer-aided automatic segmentation of retinal blood vessels plays an important role in the diagnosis of diseases such as diabetes, glaucoma, and macular degeneration. In this paper, we propose a multi-scale feature fusion retinal vessel segmentation model based on U-Net, named MSFFU-Net. The model introduces the inception structure into the multi-scale feature extraction encoder part, and the max-pooling index is applied during the upsampling process in the feature fusion decoder of an improved network. The skip layer connection is used to transfer each set of feature maps generated on the encoder path to the corresponding feature maps on the decoder path. Moreover, a cost-sensitive loss function based on the Dice coefficient and cross-entropy is designed. Four transformations\u2014rotating, mirroring, shifting and cropping\u2014are used as data augmentation strategies, and the CLAHE algorithm is applied to image preprocessing. The proposed framework is tested and trained on DRIVE and STARE, and sensitivity (Sen), specificity (Spe), accuracy (Acc), and area under curve (AUC) are adopted as the evaluation metrics. Detailed comparisons with U-Net model, at last, it verifies the effectiveness and robustness of the proposed model. The Sen of 0.7762 and 0.7721, Spe of 0.9835 and 0.9885, Acc of 0.9694 and 0.9537 and AUC value of 0.9790 and 0.9680 were achieved on DRIVE and STARE databases, respectively. Results are also compared to other state-of-the-art methods, demonstrating that the performance of the proposed method is superior to that of other methods and showing its competitive results.<\/jats:p>","DOI":"10.3390\/e22080811","type":"journal-article","created":{"date-parts":[[2020,7,24]],"date-time":"2020-07-24T09:06:09Z","timestamp":1595581569000},"page":"811","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["A Multi-Scale Feature Fusion Method Based on U-Net for Retinal Vessel Segmentation"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9790-0851","authenticated-orcid":false,"given":"Dan","family":"Yang","sequence":"first","affiliation":[{"name":"Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University), Ministry of Education, Shenyang 110819, China"},{"name":"Key Laboratory of Infrared Optoelectric Materials and Micro-Nano Devices, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0869-1024","authenticated-orcid":false,"given":"Guoru","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengcheng","family":"Ren","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,7,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Khawaja, A., Khan, T.M., Khan, M.A.U., and Nawaz, S.J. (2019). A Multi-Scale Directional Line Detector for Retinal Vessel Segmentation. Sensors, 19.","DOI":"10.3390\/s19224949"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Mostafiz, T., Jarin, I., Fattah, S.A., and Shahnaz, C. (2018, January 14\u201316). Retinal Blood Vessel Segmentation Using Residual Block Incorporated U-Net Architecture and Fuzzy Inference System. Proceedings of the 2018 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE), Chonburi, Thailand.","DOI":"10.1109\/WIECON-ECE.2018.8783182"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1112","DOI":"10.1166\/jmihi.2019.2733","article-title":"Retinal Blood Vessel Segmentation with Improved Convolutional Neural Networks","volume":"9","author":"Yang","year":"2019","journal-title":"J. Med. Imaging Health Inf."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Dasgupta, A., and Singh, S. (2017, January 18\u201321). A fully convolutional neural network based structured prediction approach towards the retinal vessel segmentation. Proceedings of the 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), Melbourne, Australia.","DOI":"10.1109\/ISBI.2017.7950512"},{"key":"ref_5","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_6","doi-asserted-by":"crossref","first-page":"103352","DOI":"10.1016\/j.compbiomed.2019.103352","article-title":"Multi-proportion channel ensemble model for retinal vessel segmentation","volume":"111","author":"Tang","year":"2019","journal-title":"Comput. Biol. Med."},{"key":"ref_7","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_8","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/42.34715","article-title":"Detection of blood vessels in retinal images using two-dimensional matched filters","volume":"8","author":"Chaudhuri","year":"1989","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1109\/42.845178","article-title":"Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response","volume":"19","author":"Hoover","year":"2000","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1109\/TBME.2010.2097599","article-title":"Retinal Image Analysis Using Curvelet Transform and Multistructure Elements Morphology by Reconstruction","volume":"58","author":"Miri","year":"2010","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2117","DOI":"10.1016\/j.patcog.2012.12.014","article-title":"Retinal vessel segmentation using multiwavelet kernels and multiscale hierarchical decomposition","volume":"46","author":"Wang","year":"2013","journal-title":"Pattern Recognit."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1109\/TMI.2006.879955","article-title":"Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction","volume":"25","author":"Campilho","year":"2006","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Espona, L., Carreira, M.J., Penedo, M.G.G., and Ortega, M. (2008, January 8\u201311). Retinal vessel tree segmentation using a deformable contour model. Proceedings of the 2008 19th International Conference on Pattern Recognition, Tampa, FL, USA.","DOI":"10.1109\/ICPR.2008.4761762"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.compmedimag.2009.09.006","article-title":"Multi-scale retinal vessel segmentation using line tracking","volume":"34","author":"Vlachos","year":"2010","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"122634","DOI":"10.1109\/ACCESS.2019.2935138","article-title":"A Fundus Retinal Vessels Segmentation Scheme Based on the Improved Deep Learning U-Net Model","volume":"7","author":"Xiuqin","year":"2019","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1109\/TMI.2004.825627","article-title":"Ridge-Based Vessel Segmentation in Color Images of the Retina","volume":"23","author":"Staal","year":"2004","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2314","DOI":"10.1016\/j.patcog.2011.01.007","article-title":"Segmentation of retinal blood vessels using the radial projection and semi-supervised approach","volume":"44","author":"You","year":"2011","journal-title":"Pattern Recognit."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.ins.2017.08.050","article-title":"Automated segmentation of exudates, haemorrhages, microaneurysms using single convolutional neural network","volume":"420","author":"Tan","year":"2017","journal-title":"Inf. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2538","DOI":"10.1109\/TBME.2012.2205687","article-title":"An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation","volume":"59","author":"Fraz","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/TBME.2016.2535311","article-title":"A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images","volume":"64","author":"Orlando","year":"2017","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation Learning: A Review and New Perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Pdf ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Lecture Notes in Computer Science, Springer Science and Business Media LLC.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Fu, H., Xu, Y., Wong, D., and Liu, J. (2016, January 13\u201316). Retinal vessel segmentation via deep learning network and fully-connected conditional random fields. Proceedings of the 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), Prague, Czech Republic.","DOI":"10.1109\/ISBI.2016.7493362"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1109\/TMI.2010.2064333","article-title":"A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Gray-Level and Moment Invariants-Based Features","volume":"30","author":"Marin","year":"2010","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_26","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_27","doi-asserted-by":"crossref","first-page":"76342","DOI":"10.1109\/ACCESS.2019.2922365","article-title":"Retinal Vessels Segmentation Based on Dilated Multi-Scale Convolutional Neural Network","volume":"7","author":"Jiang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Koshy, R., and Mahmood, A. (2019). Optimizing Deep CNN Architectures for Face Liveness Detection. Entropy, 21.","DOI":"10.3390\/e21040423"},{"key":"ref_31","unstructured":"Ioffe, S., and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"71696","DOI":"10.1109\/ACCESS.2019.2920616","article-title":"Deep Learning Models for Retinal Blood Vessels Segmentation: A Review","volume":"7","author":"Soomro","year":"2019","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"10","DOI":"10.3389\/fpls.2019.01404","article-title":"Learning Semantic Graphics Using Convolutional Encoder\u2013Decoder Network for Autonomous Weeding in Paddy","volume":"10","author":"Adhikari","year":"2019","journal-title":"Front. Plant Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from Imbalanced Data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Wang, E., Jiang, Y., Li, Y., Yang, J., Ren, M., and Zhang, Q. (2019). MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images. Appl. Sci., 9.","DOI":"10.3390\/app9194043"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/TPAMI.2003.1159954","article-title":"Adaptive local thresholding by verification-based multithreshold probing with application to vessel detection in retinal images","volume":"25","author":"Jiang","year":"2003","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"143402","DOI":"10.1109\/ACCESS.2019.2945556","article-title":"Micro-Vessel Image Segmentation Based on the AD-UNet Model","volume":"7","author":"Luo","year":"2019","journal-title":"IEEE Access"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"44","DOI":"10.3389\/fncom.2019.00044","article-title":"Inception Modules Enhance Brain Tumor Segmentation","volume":"13","author":"Cahall","year":"2019","journal-title":"Front. Comput. Neurosci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"164344","DOI":"10.1109\/ACCESS.2019.2953259","article-title":"An Improved Retinal Vessel Segmentation Framework Using Frangi Filter Coupled With the Probabilistic Patch Based Denoiser","volume":"7","author":"Khawaja","year":"2019","journal-title":"IEEE Access"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.media.2014.08.002","article-title":"Trainable COSFIRE filters for vessel delineation with application to retinal images","volume":"19","author":"Azzopardi","year":"2015","journal-title":"Med. Image Anal."},{"key":"ref_41","first-page":"970","article-title":"Automatic segmentation for retinal vessel based on multi-scale 2D Gabor wavelet","volume":"41","author":"Wang","year":"2015","journal-title":"Acta Autom. Sin."},{"key":"ref_42","first-page":"1","article-title":"Blood Vessel Segmentation of Fundus Images by Major Vessel Extraction and Sub-Image Classification","volume":"19","author":"Roychowdhury","year":"2014","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"2369","DOI":"10.1109\/TMI.2016.2546227","article-title":"Segmenting Retinal Blood Vessels With_newline Deep Neural Networks","volume":"35","author":"Liskowski","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/TMI.2015.2457891","article-title":"A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images","volume":"35","author":"Li","year":"2015","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_45","first-page":"140","article-title":"Deep Retinal Image Understanding","volume":"Volume 9901","author":"Maninis","year":"2016","journal-title":"Proceedings of the Computer Vision"},{"key":"ref_46","unstructured":"Chen, Y. (2017). A labeling-free approach to supervising deep neural networks for retinal blood vessel segmentation. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/j.neucom.2018.05.011","article-title":"Retinal vessel segmentation of color fundus images using multiscale convolutional neural network with an improved cross-entropy loss function","volume":"309","author":"Hu","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"3132","DOI":"10.1002\/mp.12953","article-title":"Retinal vascular segmentation using superpixel-based line operator and its application to vascular topology estimation","volume":"45","author":"Na","year":"2018","journal-title":"Med. Phys."},{"key":"ref_49","first-page":"568","article-title":"Blood vessel segmentation in retinal fundus images using Gabor filters, fractional derivatives, and Expectation Maximization","volume":"339","author":"Ledesma","year":"2018","journal-title":"Appl. Math. Comput."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.1007\/s11760-017-1114-7","article-title":"Contrast normalization steps for increased sensitivity of a retinal image segmentation method","volume":"11","author":"Soomro","year":"2017","journal-title":"Signal Image Video Process."},{"key":"ref_51","first-page":"597475","article-title":"Adaptive Thresholding Technique for Retinal Vessel Segmentation Based on GLCM-Energy Information","volume":"2015","author":"Mapayi","year":"2015","journal-title":"Comput. Math. Methods Med."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.1109\/TMI.2006.879967","article-title":"Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification","volume":"25","author":"Soares","year":"2006","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Xie, S., and Tu, Z. (2015, January 7\u201313). Holistically-Nested Edge Detection. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"61973","DOI":"10.1109\/ACCESS.2018.2869858","article-title":"Mapping Functions Driven Robust Retinal Vessel Segmentation via Training Patches","volume":"6","author":"Xia","year":"2018","journal-title":"IEEE Access"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/22\/8\/811\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:51:22Z","timestamp":1760176282000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/22\/8\/811"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,24]]},"references-count":54,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2020,8]]}},"alternative-id":["e22080811"],"URL":"https:\/\/doi.org\/10.3390\/e22080811","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,24]]}}}