{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:08:06Z","timestamp":1753891686579,"version":"3.41.2"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,4,19]],"date-time":"2022-04-19T00:00:00Z","timestamp":1650326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:p>Retinopathy of prematurity and ischemic brain injury resulting in periventricular white matter damage are the main causes of visual impairment in premature infants. Accurate optic disc (OD) segmentation has important prognostic significance for the auxiliary diagnosis of the above two diseases of premature infants. Because of the complexity and non-uniform illumination and low contrast between background and the target area of the fundus images, the segmentation of OD for infants is challenging and rarely reported in the literature. In this article, to tackle these problems, we propose a novel attention fusion enhancement network (AFENet) for the accurate segmentation of OD in the fundus images of premature infants by fusing adjacent high-level semantic information and multiscale low-level detailed information from different levels based on encoder\u2013decoder network. Specifically, we first design a dual-scale semantic enhancement (DsSE) module between the encoder and the decoder inspired by self-attention mechanism, which can enhance the semantic contextual information for the decoder by reconstructing skip connection. Then, to reduce the semantic gaps between the high-level and low-level features, a multiscale feature fusion (MsFF) module is developed to fuse multiple features of different levels at the top of encoder by using attention mechanism. Finally, the proposed AFENet was evaluated on the fundus images of preterm infants for OD segmentation, which shows that the proposed two modules are both promising. Based on the baseline (Res34UNet), using DsSE or MsFF module alone can increase Dice similarity coefficients by 1.51 and 1.70%, respectively, whereas the integration of the two modules together can increase 2.11%. Compared with other state-of-the-art segmentation methods, the proposed AFENet achieves a high segmentation performance.<\/jats:p>","DOI":"10.3389\/fnins.2022.836327","type":"journal-article","created":{"date-parts":[[2022,4,19]],"date-time":"2022-04-19T12:31:27Z","timestamp":1650371487000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["AFENet: Attention Fusion Enhancement Network for Optic Disc Segmentation of Premature Infants"],"prefix":"10.3389","volume":"16","author":[{"given":"Yuanyuan","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyue","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhe","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daoman","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinjian","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,4,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"906","DOI":"10.1001\/archopht.1987.01060070042025","article-title":"An international classification of retinopathy of prematurity: II. The classification of retinal detachment.","volume":"105","author":"Aaberg","year":"1987","journal-title":"Arch. Ophthalmol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1007\/s10278-021-00477-8","article-title":"Assistive framework for automatic detection of all the zones in retinopathy of prematurity using deep learning.","volume":"34","author":"Agrawal","year":"2021","journal-title":"J. Digit. Imag."},{"key":"B3","doi-asserted-by":"crossref","first-page":"87","DOI":"10.3390\/sym10040087","article-title":"Dense fully convolutional segmentation of the optic disc and cup in color fundus for glaucoma diagnosis.","volume":"10","author":"Al-Bander","year":"2018","journal-title":"Symmetry"},{"key":"B4","doi-asserted-by":"publisher","first-page":"97","DOI":"10.3109\/01658109509009649","article-title":"Ophthalmological sequelae following post-haemorrhagic hydrocephalus.","volume":"15","author":"Algawi","year":"1995","journal-title":"Neuro-ophthalmology"},{"key":"B5","first-page":"294","article-title":"Pathological oct retinal layer segmentation using branch residual u-shape networks","author":"Apostolopoulos","year":"2017","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1131335","DOI":"10.1109\/TMI.2022.3142048","article-title":"Attention multi-scale network for pigment epithelial detachment segmentation in OCT images.","volume":"11313","author":"Bao","year":"2020","journal-title":"Image Process."},{"key":"B7","doi-asserted-by":"publisher","first-page":"29299","DOI":"10.1109\/access.2020.2972318","article-title":"Improving the performance of convolutional neural network for the segmentation of optic disc in fundus images using attention gates and conditional random fields.","volume":"8","author":"Bhatkalkar","year":"2020","journal-title":"IEEE Access"},{"key":"B8","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1001\/archopht.1993.01090010070029","article-title":"Optic nerve hypoplasia: clinical significance of associated central nervous system abnormalities on magnetic resonance imaging.","volume":"111","author":"Brodsky","year":"1993","journal-title":"Arch. Ophthalmol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1136\/bjo.75.4.236","article-title":"Optic nerve hypoplasia, encephalopathy, and neurodevelopmental handicap.","volume":"75","author":"Burke","year":"1991","journal-title":"Br. J. Ophthalmol."},{"key":"B10","article-title":"Transunet: Transformers make strong encoders for medical image segmentation.","author":"Chen","year":"2021","journal-title":"arXiv arXiv:2102.04306."},{"key":"B11","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s10456-007-9066-0","article-title":"Retinopathy of prematurity.","volume":"10","author":"Chen","year":"2007","journal-title":"Angiogenesis"},{"key":"B12","article-title":"Rethinking atrous convolution for semantic image segmentation.","author":"Chen","year":"2017","journal-title":"arXiv arXiv:1706.05587."},{"key":"B13","first-page":"1131332","article-title":"Group-wise attention fusion network for choroid segmentation in OCT images.","volume":"2020","author":"Cheng","year":"2020","journal-title":"Image Process."},{"key":"B14","first-page":"263","article-title":"Optic disc segmentation in retinal images.","volume":"2002","author":"Chrastek","year":"2002","journal-title":"Bildverarbeitung fur die Medizin"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1109\/TMI.2006.880587","article-title":"Generalized overlap measures for evaluation and validation in medical image analysis.","volume":"25","author":"Crum","year":"2006","journal-title":"IEEE Transact. Med. Imaging"},{"key":"B16","doi-asserted-by":"publisher","first-page":"3008","DOI":"10.1109\/TMI.2020.2983721","article-title":"CPFNet: Context pyramid fusion network for medical image segmentation.","volume":"39","author":"Feng","year":"2020","journal-title":"IEEE Transact. Med. Imaging"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1109\/TMI.2004.829331","article-title":"Detection of optic disc in retinal images by means of a geometrical model of vessel structure.","volume":"23","author":"Foracchia","year":"2004","journal-title":"IEEE Transact. Med. Imaging"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1109\/TMI.2018.2791488","article-title":"Joint optic disc and cup segmentation based on multi-label deep network and polar transformation.","volume":"37","author":"Fu","year":"2018","journal-title":"IEEE Transact. Med. Imaging"},{"key":"B19","doi-asserted-by":"publisher","first-page":"3146","DOI":"10.1109\/TNNLS.2020.3006524","article-title":"Dual Attention Network for Scene Segmentation","author":"Fu","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1109\/TMI.2019.2903562","article-title":"CE-Net: Context encoder network for 2D medical image segmentation.","volume":"38","author":"Gu","year":"2019","journal-title":"IEEE Transact. Med. Imaging"},{"key":"B21","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1109\/TMI.2003.815900","article-title":"Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels.","volume":"22","author":"Hoover","year":"2003","journal-title":"IEEE Transact. Med. Imaging"},{"key":"B22","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1001\/archopht.123.7.991","article-title":"The international classification of retinopathy of prematurity revisited.","volume":"123","year":"2005","journal-title":"Arch. Ophthalmol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"64483","DOI":"10.1109\/TMI.2019.2899910","article-title":"Optic disc and cup segmentation based on deep convolutional generative adversarial networks.","volume":"7","author":"Jiang","year":"2019","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1007\/s11548-020-02144-9","article-title":"Wgan domain adaptation for the joint optic disc-and-cup segmentation in fundus images.","volume":"15","author":"Kadambi","year":"2020","journal-title":"Int. J. Comput. Assist. Radiol. Surgery"},{"key":"B25","doi-asserted-by":"publisher","first-page":"84","DOI":"10.3928\/0191-3913-19930301-05","article-title":"Ocular findings in premature infants with grade IV intraventricular hemorrhage.","volume":"30","author":"King","year":"1993","journal-title":"J. Pediatr. Ophthalmol. Strabismus"},{"key":"B26","first-page":"837","article-title":"Automatic location of optic disk in retinal images","author":"Li","year":"2001","journal-title":"Proceedings 2001 International Conference on Image Processing (Cat. No. 01CH37205)"},{"key":"B27","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s12880-020-00528-6","article-title":"Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network.","volume":"21","author":"Liu","year":"2021","journal-title":"BMC Med. Imaging"},{"key":"B28","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B29","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1136\/bjo.2005.078519","article-title":"RetCam image analysis of optic disc morphology in premature infants and its relation to ischaemic brain injury.","volume":"90","author":"Mcloone","year":"2006","journal-title":"Digest World Core Med. J."},{"key":"B30","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1109\/3DV.2016.79","article-title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016","journal-title":"2016 Fourth International Conference on 3D Vision (3DV)."},{"key":"B31","doi-asserted-by":"publisher","first-page":"4038","DOI":"10.1016\/j.bspc.2019.01.022","article-title":"High-Performance optic disc segmentation using convolutional neural networks","author":"Mohan","year":"2018","journal-title":"2018 25th IEEE International Conference on Image Processing (ICIP)"},{"key":"B32","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/ICIP.2019.8804267","article-title":"Optic Disc Segmentation Using Cascaded Multiresolution Convolutional Neural Networks","author":"Mohan","year":"2019","journal-title":"2019 IEEE International Conference on Image Processing (ICIP)"},{"key":"B33","doi-asserted-by":"crossref","first-page":"101874","DOI":"10.1016\/j.media.2020.101874","article-title":"CS2-Net: Deep learning segmentation of curvilinear structures in medical imaging.","volume":"67","author":"Mou","year":"2021","journal-title":"Med. Image Anal."},{"key":"B34","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1136\/bjo.2005.085019","article-title":"Optic disc morphology in relation to stage of retinopathy of prematurity.","volume":"47","author":"Oberacher-Velten","year":"2006","journal-title":"Investigat. Ophthalmol. Visual Sci."},{"key":"B35","article-title":"Attention u-net: Learning where to look for the pancreas.","author":"Oktay","year":"2018","journal-title":"arXiv arXiv:1804.03999."},{"key":"B36","first-page":"4353","article-title":"Large Kernel Matters \u2013 Improve Semantic Segmentation by Global Convolutional Network","author":"Peng","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B37","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1094928","DOI":"10.1186\/s12880-020-00528-6","article-title":"Stack-u-net: refnement network for improved optic disc and cup image segmentation.","volume":"10949","author":"Sevastopolsky","year":"2019","journal-title":"Med. Imaging"},{"key":"B39","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.cmpb.2012.06.006","article-title":"Segmentation of color fundus images of the human retina: Detection of the optic disc and the vascular tree using morphological techniques","author":"Walter","year":"2001","journal-title":"International Symposium on Medical Data Analysis"},{"key":"B40","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","article-title":"Deep High-Resolution Representation Learning for Visual Recognition.","volume":"43","author":"Wang","year":"2019","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"B41","first-page":"1","article-title":"Cu-Segnet: corneal ulcer segmentation network","author":"Wang","year":"2021","journal-title":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)"},{"key":"B42","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/TMI.2007.900326","article-title":"Optic disc detection from normalized digital fundus images by means of a vessels direction matched fifilter.","volume":"27","author":"Youssif","year":"2007","journal-title":"IEEE Transact. Med. Imaging"},{"key":"B43","first-page":"6230","article-title":"Pyramid scene parsing network","author":"Zhao","year":"2017","journal-title":"IEEE Computer Vision and Pattern Recognition"},{"key":"B44","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-00889-5_1","article-title":"UNet++: A nested U-Net architecture for medical image segmentation","author":"Zhou","year":"2018","journal-title":"4th Deep Learning in Medical Image Analysis (DLMIA) Workshop."},{"key":"B45","first-page":"113108","article-title":"ASNet: An adaptive scale network for skin lesion segmentation in dermoscopy images.","volume":"11313","author":"Zhu","year":"2020","journal-title":"Biomed. Appl. Mol. Structural Func. Imaging"},{"key":"B46","first-page":"115960000","article-title":"Joint optic disc and cup segmentation based on multi-module U-shaped network.","volume":"115961","author":"Zhu","year":"2021","journal-title":"Image Process."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2022.836327\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,19]],"date-time":"2022-04-19T12:31:51Z","timestamp":1650371511000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2022.836327\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,19]]},"references-count":46,"alternative-id":["10.3389\/fnins.2022.836327"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2022.836327","relation":{},"ISSN":["1662-453X"],"issn-type":[{"type":"electronic","value":"1662-453X"}],"subject":[],"published":{"date-parts":[[2022,4,19]]},"article-number":"836327"}}