{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T14:46:27Z","timestamp":1791557187183,"version":"4.3.4"},"reference-count":38,"publisher":"BMJ","issue":"8","license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"unspecified","delay-in-days":18,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Joint Funds for the Innovation of Science and Technology, Fujian Province","award":["2020Y9060"],"award-info":[{"award-number":["2020Y9060"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2025,7,9]]},"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>This study aims to develop a deep learning algorithm (DLA) using the InceptionV3 architecture for effective diabetic peripheral neuropathy (DPN) screening via corneal confocal microscopy (CCM) images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>Retrospective study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Ophthalmology Centre of General Hospital.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>127 participants enrolled: 33 healthy participants, 57 diabetic patients with DPN (DPN+) and 37 diabetic patients without DPN (DPN\u2212).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Interventions<\/jats:title>\n                    <jats:p>Not applicable.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Main outcome measures<\/jats:title>\n                    <jats:p>The CCM image dataset, which was collected from participants (with five images per eye), was randomly divided into training, validation and test subsets in a 7:1:2 ratio. The images were preprocessed, augmented and used to train the InceptionV3 model. We compared its performance against the ResNet, DenseNet and Swin Transformer models. Performance was evaluated using accuracy, recall, F1 score and area under the curve (AUC) metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>For single-participant predictions, the InceptionV3 model achieved the highest accuracy (0.9231), recall (0.8846), F1 score (0.9020) and AUC (0.9534) compared with the other models. For single-image predictions in the three-class classification task of CCM images, the InceptionV3 model achieved a precision of 0.8385, a recall of 0.9083, an F1 score of 0.8720 and an AUC of 0.8769 for predicting DPN+.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The InceptionV3-based DLA model achieved superior performance compared with traditional convolutional neural network architectures like ResNet and DenseNet, and the Swin transformer model, highlighting its potential for effective DPN screening.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2024-095342","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T15:15:16Z","timestamp":1755616516000},"page":"e095342","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":6,"title":["Comparative performance of deep learning architectures for diabetic peripheral neuropathy detection using corneal confocal microscopy: a retrospective single-centre study"],"prefix":"10.1136","volume":"15","author":[{"given":"Wenqu","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Ophthalmology, Fujian Medical University Union Hospital, Fuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Fujian Medical University Union Hospital, Fuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weihuang","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Fujian Medical University Union Hospital, Fuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0610-7856","authenticated-orcid":false,"given":"Jianzhang","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Fujian Medical University Union Hospital, Fuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"2025123106464058000_15.8.e095342.1","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1016\/S2213-8587(19)30081-6","article-title":"Diabetic peripheral neuropathy: advances in diagnosis and strategies for screening and early intervention","volume":"7","author":"Selvarajah","year":"2019","journal-title":"Lancet Diabetes Endocrinol"},{"key":"2025123106464058000_15.8.e095342.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecl.2013.06.001"},{"key":"2025123106464058000_15.8.e095342.3","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1007\/s00702-020-02145-7","article-title":"Challenges of neuropathic pain: focus on diabetic neuropathy","volume":"127","author":"Rosenberger","year":"2020","journal-title":"J Neural Transm"},{"key":"2025123106464058000_15.8.e095342.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41574-021-00496-z"},{"key":"2025123106464058000_15.8.e095342.5","doi-asserted-by":"publisher","DOI":"10.1007\/s00125-021-05617-x"},{"key":"2025123106464058000_15.8.e095342.6","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2559.2008.03096.x"},{"key":"2025123106464058000_15.8.e095342.7","doi-asserted-by":"crossref","DOI":"10.2337\/diacare.23.7.887","article-title":"The 10-g monofilament: the diagnostic divining rod for the diabetic foot?","volume":"23","author":"Armstrong","year":"2000","journal-title":"Diabetes Care"},{"key":"2025123106464058000_15.8.e095342.8","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1007\/s00592-024-02299-w","article-title":"Comprehensive assessment of ocular parameters for identifying diagnostic indicators of diabetic peripheral neuropathy","volume":"61","author":"Chen","year":"2024","journal-title":"Acta Diabetol"},{"key":"2025123106464058000_15.8.e095342.9","doi-asserted-by":"crossref","DOI":"10.3389\/fendo.2021.671257","article-title":"Advances in Screening, Early Diagnosis and Accurate Staging of Diabetic Neuropathy","volume":"12","author":"Carmichael","year":"2021","journal-title":"Front Endocrinol (Lausanne)"},{"key":"2025123106464058000_15.8.e095342.10","doi-asserted-by":"publisher","DOI":"10.1007\/s00125-003-1086-8"},{"key":"2025123106464058000_15.8.e095342.11","doi-asserted-by":"crossref","first-page":"2821","DOI":"10.1111\/ene.15852","article-title":"Corneal confocal microscopy reveals small nerve fibre loss correlating with motor function in adult spinal muscular atrophy","volume":"30","author":"Thimm","year":"2023","journal-title":"Eur J Neurol"},{"key":"2025123106464058000_15.8.e095342.12","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1111\/cxo.12887","article-title":"Corneal confocal microscopy: ready for prime time","volume":"103","author":"Petropoulos","year":"2020","journal-title":"Clin Exp Optom"},{"key":"2025123106464058000_15.8.e095342.13","doi-asserted-by":"crossref","first-page":"101039","DOI":"10.1016\/j.preteyeres.2021.101039","article-title":"The impact of sensory neuropathy and inflammation on epithelial wound healing in diabetic corneas","volume":"89","author":"Yu","year":"2022","journal-title":"Prog Retin Eye Res"},{"key":"2025123106464058000_15.8.e095342.14","doi-asserted-by":"publisher","DOI":"10.2337\/db12-0574"},{"key":"2025123106464058000_15.8.e095342.15","doi-asserted-by":"crossref","DOI":"10.1016\/j.xcrm.2023.101213","article-title":"Artificial intelligence in diabetes management: Advancements, opportunities, and challenges","volume":"4","author":"Guan","year":"2023","journal-title":"Cell Rep Med"},{"key":"2025123106464058000_15.8.e095342.16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-bioeng-071516-044442"},{"key":"2025123106464058000_15.8.e095342.17","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1109\/TBME.2016.2573642","article-title":"An Automatic Tool for Quantification of Nerve Fibers in Corneal Confocal Microscopy Images","volume":"64","author":"Chen","year":"2017","journal-title":"IEEE Trans Biomed Eng"},{"key":"2025123106464058000_15.8.e095342.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2011.05.016"},{"key":"2025123106464058000_15.8.e095342.19","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.13-13787"},{"key":"2025123106464058000_15.8.e095342.20","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/s00125-019-05023-4","article-title":"An artificial intelligence-based deep learning algorithm for the diagnosis of diabetic neuropathy using corneal confocal microscopy: a development and validation study","volume":"63","author":"Williams","year":"2020","journal-title":"Diabetologia"},{"key":"2025123106464058000_15.8.e095342.21","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"2025123106464058000_15.8.e095342.22","doi-asserted-by":"publisher","DOI":"10.2337\/dc20-2012"},{"key":"2025123106464058000_15.8.e095342.23","doi-asserted-by":"crossref","unstructured":"Szegedy C , Vanhoucke V , Ioffe S , et al . Rethinking the inception architecture for computer vision. In: Wojna Z , ed. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV, USA, 2016 doi:10.1109\/CVPR.2016.308","DOI":"10.1109\/CVPR.2016.308"},{"key":"2025123106464058000_15.8.e095342.24","doi-asserted-by":"publisher","DOI":"10.2337\/dc20-S002"},{"key":"2025123106464058000_15.8.e095342.25","doi-asserted-by":"publisher","DOI":"10.2337\/dc10-1303"},{"key":"2025123106464058000_15.8.e095342.26","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0183040","article-title":"Corneal confocal microscopy is a rapid reproducible ophthalmic technique for quantifying corneal nerve abnormalities","volume":"12","author":"Kalteniece","year":"2017","journal-title":"PLoS One"},{"key":"2025123106464058000_15.8.e095342.27","unstructured":"Srivastava N , Hinton G , Krizhevsky A , et al . Dropout: A Simple Way to Prevent Neural Networks from Overfitting. 2014;15:1929\u201358."},{"key":"2025123106464058000_15.8.e095342.28","doi-asserted-by":"crossref","unstructured":"Shorten C , Khoshgoftaar TM . A survey on Image Data Augmentation for Deep Learning. J Big Data 2019;6. doi:10.1186\/s40537-019-0197-0","DOI":"10.1186\/s40537-019-0197-0"},{"key":"2025123106464058000_15.8.e095342.29","doi-asserted-by":"crossref","unstructured":"Deng J , Dong W , Socher R , et al . ImageNet: a large-scale hierarchical image database. 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops); Miami, FL, June 20, 2009 doi:10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2025123106464058000_15.8.e095342.30","doi-asserted-by":"crossref","unstructured":"He K , Zhang X , Ren S , et al . Deep residual learning for image recognition. In: Sun J , ed. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV, USA, 2016 doi:10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2025123106464058000_15.8.e095342.31","doi-asserted-by":"crossref","unstructured":"Huang G , Liu Z , Van Der Maaten L , et al . Densely connected convolutional networks. In: Weinberger KQ , ed. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Honolulu, HI, 2017 doi:10.1109\/CVPR.2017.243 Available: https:\/\/ieeexplore.ieee.org\/xpl\/mostRecentIssue.jsp?punumber=8097368","DOI":"10.1109\/CVPR.2017.243"},{"key":"2025123106464058000_15.8.e095342.32","doi-asserted-by":"crossref","unstructured":"Liu Z , Lin Y , Cao Y , et al . Swin transformer: hierarchical vision transformer using shifted windows. In: Zhang Z , ed. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV); Montreal, QC, Canada, 2021 doi:10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2025123106464058000_15.8.e095342.33","unstructured":"Vaswani A , Shazeer N , Parmar N , et al . Attention is all you need. 2017. doi:10.48550\/arXiv.1706.03762"},{"key":"2025123106464058000_15.8.e095342.34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"2025123106464058000_15.8.e095342.35","unstructured":"Oakley JD , Russakoff DB , Weinberg R , et al . Automated analysis of in vivo confocal microscopy corneal images using deep learning. 2018;59."},{"key":"2025123106464058000_15.8.e095342.36","doi-asserted-by":"crossref","DOI":"10.3390\/jcm12041284","article-title":"Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model","volume":"12","author":"Meng","year":"2023","journal-title":"J Clin Med"},{"key":"2025123106464058000_15.8.e095342.37","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1097\/ICO.0000000000002181","article-title":"Multiple-Image Deep Learning Analysis for Neuropathy Detection in Corneal Nerve Images","volume":"39","author":"Scarpa","year":"2020","journal-title":"Cornea"},{"key":"2025123106464058000_15.8.e095342.38","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2018.2665","article-title":"Evaluation of Artificial Intelligence-Based Grading of Diabetic Retinopathy in Primary Care","volume":"1","author":"Kanagasingam","year":"2018","journal-title":"JAMA Netw Open"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2024-095342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T14:48:06Z","timestamp":1767192486000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2024-095342"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":38,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8,19]]},"published-print":{"date-parts":[[2025,8]]}},"alternative-id":["10.1136\/bmjopen-2024-095342"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2024-095342","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}