{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:07:57Z","timestamp":1753891677196,"version":"3.41.2"},"reference-count":50,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T00:00:00Z","timestamp":1669248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["19ZDA364"],"award-info":[{"award-number":["19ZDA364"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009558","name":"University Natural Science Research Project of Anhui Province","doi-asserted-by":"publisher","award":["tzpyxj137"],"award-info":[{"award-number":["tzpyxj137"]}],"id":[{"id":"10.13039\/501100009558","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:p>Corneal ulcer is the most common symptom of corneal disease, which is one of the main causes of corneal blindness. The accurate classification of corneal ulcer has important clinical importance for the diagnosis and treatment of the disease. To achieve this, we propose a deep learning method based on multi-scale information fusion and label smoothing strategy. Firstly, the proposed method utilizes the densely connected network (DenseNet121) as backbone for feature extraction. Secondly, to fully integrate the shallow local information and the deep global information and improve the classification accuracy, we develop a multi-scale information fusion network (MIF-Net), which uses multi-scale information for joint learning. Finally, to reduce the influence of the inter-class similarity and intra-class diversity on the feature representation, the learning strategy of label smoothing is introduced. Compared with other state-of-the-art classification networks, the proposed MIF-Net with label smoothing achieves high classification performance, which reaches 87.07 and 83.84% for weighted-average recall (W_R) on the general ulcer pattern and specific ulcer pattern, respectively. The proposed method holds promise for corneal ulcer classification in fluorescein staining slit lamp images, which can assist ophthalmologists in the objective and accurate diagnosis of corneal ulcer.<\/jats:p>","DOI":"10.3389\/fnins.2022.993234","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T08:04:35Z","timestamp":1669277075000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Multi-scale information fusion network with label smoothing strategy for corneal ulcer classification in slit lamp images"],"prefix":"10.3389","volume":"16","author":[{"given":"Linquan","family":"Lv","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengle","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanjun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICCIT48885.2019.9038389","article-title":"An efficient automated corneal ulcer detection method using convolutional neural network","author":"Akram","year":"2019","journal-title":"Proceedings of the 2019 22nd international conference on computer and information technology"},{"key":"B2","article-title":"Rethinking atrous convolution for semantic image segmentation.","author":"Chen","year":"2017","journal-title":"arXiv"},{"key":"B3","doi-asserted-by":"publisher","first-page":"7896","DOI":"10.1167\/iovs.14-15618","article-title":"Objective assessment of corneal staining using digital image analysis.","volume":"55","author":"Chun","year":"2014","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"B4","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/S0161-6420(87)33491-8","article-title":"Corneal ulcers associated with cosmetic extended wear soft contact lenses.","volume":"94","author":"Cohen","year":"1987","journal-title":"Ophthalmology"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1117\/12.2293270","article-title":"Automatic segmentation of corneal ulcer area based on ocular staining images. Medical imaging 2018: Biomedical applications in molecular, structural, and functional imaging.","volume":"10578","author":"Deng","year":"","journal-title":"Int. Soc. Opt. Photonics"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICDSP.2018.8631795","article-title":"Superpixel based automatic segmentation of corneal ulcers from ocular staining images","author":"Deng","year":"","journal-title":"Proceedings of the IEEE 23rd international conference on digital signal processing"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-0360-7","article-title":"The SUSTech-SYSU dataset for automatically segmenting and classifying corneal ulcers.","volume":"7","author":"Deng","year":"2020","journal-title":"Sci. Data"},{"key":"B8","doi-asserted-by":"publisher","first-page":"ND01","DOI":"10.7860\/JCDR\/2017\/24149.9645","article-title":"A case of bilateral corneal perforation in a patient with severe dry eye.","volume":"11","author":"Deswal","year":"2017","journal-title":"J. Clin. Diagn. Res."},{"key":"B9","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1038\/eye.1999.135","article-title":"Corneal biopsy with tissue micro homogenisation for isolation of organisms in bacterial keratitis.","volume":"13","author":"Diamond","year":"1999","journal-title":"Eye"},{"key":"B10","first-page":"1","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"George","year":"2018","journal-title":"Proceedings of the conference on computer vision and pattern recognition"},{"key":"B11","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B12","doi-asserted-by":"publisher","first-page":"7132","DOI":"10.1109\/CVPR.2018.00745","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B13","doi-asserted-by":"publisher","first-page":"4700","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B14","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"Proceedings of the international conference on machine learning"},{"key":"B15","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1001\/archopht.1960.01840010384009","article-title":"The diagnosis of corneal herpes simplex infection by fluorescent antibody staining.","volume":"64","author":"Kaufman","year":"1960","journal-title":"Arch. Ophthalmol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1407","DOI":"10.1167\/iovs.07-0635","article-title":"Dry eye diagnosis.","volume":"49","author":"Khanal","year":"2008","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"B17","doi-asserted-by":"publisher","first-page":"55","DOI":"10.4103\/2320-3897.106288","article-title":"Use of dyes in ophthalmology.","volume":"1","author":"Kumar","year":"2013","journal-title":"J. Clin. Ophthalmol. Res."},{"key":"B18","first-page":"562","article-title":"Deeply-supervised nets.","volume":"39","author":"Lee","year":"2015","journal-title":"Artif. Intell. Stat."},{"key":"B19","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/978-3-030-20873-8_40","article-title":"DeepAMD: Detect early age-related macular degeneration by applying deep learning in a multiple instance learning framework","author":"Liu","year":"2018","journal-title":"Proceedings of the Asian conference on computer vision"},{"key":"B20","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/s40135-019-00218-9","article-title":"Artificial intelligence in corneal diagnosis: Where are we?","volume":"7","author":"Lopes","year":"2019","journal-title":"Curr. Ophthalmol. Rep."},{"key":"B21","doi-asserted-by":"publisher","first-page":"121685","DOI":"10.1109\/ACCESS.2019.2936215","article-title":"Multi-layers feature fusion of convolutional neural network for scene classification of remote sensing.","volume":"7","author":"Ma","year":"2019","journal-title":"IEEE Access"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/6395840","article-title":"Fungal keratitis: Epidemiology, rapid detection, and antifungal susceptibilities of Fusarium and Aspergillus isolates from corneal scrapings.","volume":"2019","author":"Manikandan","year":"2019","journal-title":"Biomed Res. Int."},{"key":"B23","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: The kappa statistic.","volume":"22","author":"McHugh","year":"2012","journal-title":"Biochem. Med."},{"key":"B24","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.clae.2008.09.004","article-title":"Corneal staining: Do we really understand what we are seeing.","volume":"32","author":"Morgan","year":"2009","journal-title":"Cont. Lens Anterior Eye"},{"key":"B25","article-title":"When does label smoothing help?.","author":"M\u00fcller","year":"2019","journal-title":"arXiv"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning.","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"B27","doi-asserted-by":"publisher","first-page":"4087","DOI":"10.1364\/BOE.461411","article-title":"ADS-net: Attention-awareness and deep supervision based network for automatic detection of retinopathy of prematurity.","volume":"13","author":"Peng","year":"","journal-title":"Biomed. Opt. Express"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1968","DOI":"10.1364\/BOE.447224","article-title":"Automatic zoning for retinopathy of prematurity with semi-supervised feature calibration adversarial learning.","volume":"13","author":"Peng","year":"","journal-title":"Biomed. Opt. Express"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.836327","article-title":"AFENet: Attention fusion enhancement network for optical disc segmentation of prematurity infants.","volume":"13","author":"Peng","year":"","journal-title":"Front. Neurosci."},{"key":"B30","doi-asserted-by":"publisher","first-page":"1131321","DOI":"10.1117\/12.2548290","article-title":"Automated retinopathy of prematurity screening using deep neural network with attention mechanism.","volume":"11313","author":"Peng","year":"2020","journal-title":"Proc. Med. Imaging"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1750","DOI":"10.1109\/TMI.2021.3065753","article-title":"Automatic staging for retinopathy of prematurity with deep feature fusion and ordinal classification strategy.","volume":"40","author":"Peng","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B32","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1097\/OPX.0b013e3181981976","article-title":"Objective grading of the anterior eye.","volume":"86","author":"Peterson","year":"2009","journal-title":"Optom. Vis. Sci."},{"key":"B33","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S1367-0484(02)00083-8","article-title":"Subjective and objective measures of corneal staining related to multipurpose care systems.","volume":"26","author":"Pritchard","year":"2003","journal-title":"Cont. Lens Anterior Eye"},{"key":"B34","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1001\/archopht.1967.00980020550021","article-title":"A fluorescein colored polygonal pattern in the human cornea.","volume":"77","author":"Schweitzer","year":"1967","journal-title":"Arch. Ophthalmol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-319-46478-7_29","article-title":"Relay backpropagation for effective learning of deep convolutional neural networks","author":"Shen","year":"2016","journal-title":"Proceedings of the European conference on computer vision"},{"article-title":"Very deep convolutional networks for large-scale image recognition.","year":"2014","author":"Simonyan","key":"B36"},{"journal-title":"BMA AZ family medical encyclopedia.","year":"2004","author":"Smith","key":"B37"},{"key":"B38","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/978-3-319-67561-9_11","article-title":"Patch-based deep convolutional neural network for corneal ulcer area segmentation","author":"Sun","year":"2017","journal-title":"Fetal, infant and ophthalmic medical image analysis"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, Inception-resnet and the impact of residual connections on learning","author":"Szegedy","year":"2017","journal-title":"Proceedings of the thirty-first AAAI conference on artificial intelligence"},{"key":"B40","doi-asserted-by":"publisher","first-page":"2818","DOI":"10.1109\/CVPR.2016.308","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B41","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1007\/978-3-030-01424-7_27","article-title":"A survey on deep transfer learning","author":"Tan","year":"2018","journal-title":"Proceedings of the international conference on artificial neural networks"},{"key":"B42","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks.","author":"Tan","year":"2019","journal-title":"arXiv"},{"key":"B43","doi-asserted-by":"publisher","first-page":"94586","DOI":"10.1109\/ACCESS.2021.3093308","article-title":"Lightweight channel attention and multiscale feature fusion discrimination for remote sensing scene classification.","volume":"9","author":"Wan","year":"2021","journal-title":"IEEE Access"},{"key":"B44","article-title":"Training deeper convolutional networks with deep supervision.","author":"Wang","year":"2015","journal-title":"arXiv"},{"key":"B45","first-page":"1","article-title":"Diabetic retinopathy diagnosis using multichannel generative adversarial network with semi-supervision.","volume":"13","author":"Wang","year":"2020","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"B46","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/S1367-0484(02)00062-0","article-title":"Clinical monitoring of ocular physiology using digital image analysis.","volume":"26","author":"Wolffsohn","year":"2003","journal-title":"Cont. Lens Anterior Eye"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1109\/CVPR.2017.634","article-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24506-9","article-title":"Netrin-1 promotes diabetic corneal wound healing through molecular mechanisms mediated via the adenosine 2b receptor.","volume":"8","author":"Zhang","year":"2018","journal-title":"Sci. Rep."},{"key":"B49","doi-asserted-by":"publisher","first-page":"2881","DOI":"10.1109\/CVPR.2017.660","article-title":"Pyramid scene parsing network","author":"Zhao","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B50","doi-asserted-by":"publisher","first-page":"2921","DOI":"10.1109\/CVPR.2016.319","article-title":"Learning deep features for discriminative localization","author":"Zhou","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2022.993234\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T08:04:45Z","timestamp":1669277085000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2022.993234\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,24]]},"references-count":50,"alternative-id":["10.3389\/fnins.2022.993234"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2022.993234","relation":{},"ISSN":["1662-453X"],"issn-type":[{"type":"electronic","value":"1662-453X"}],"subject":[],"published":{"date-parts":[[2022,11,24]]},"article-number":"993234"}}