{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T21:11:35Z","timestamp":1790629895142,"version":"4.1.0"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,3,15]],"date-time":"2023-03-15T00:00:00Z","timestamp":1678838400000},"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. Physiol."],"abstract":"<jats:p><jats:bold>Objective:<\/jats:bold> To analyze the cranial computed tomography (CT) imaging features of patients with primary ciliary dyskinesia (PCD) who have exudative otitis media (OME) and sinusitis using a deep learning model for early intervention in PCD.<\/jats:p><jats:p><jats:bold>Methods:<\/jats:bold> Thirty-two children with PCD diagnosed at the Children\u2019s Hospital of Fudan University, Shanghai, China, between January 2010 and January 2021 who had undergone cranial CT were retrospectively analyzed. Thirty-two children with OME and sinusitis diagnosed using cranial CT formed the control group. Multiple deep learning neural network training models based on PyTorch were built, and the optimal model was trained and selected to observe the differences between the cranial CT images of patients with PCD and those of general patients and to screen patients with PCD.<\/jats:p><jats:p><jats:bold>Results:<\/jats:bold> The Swin-Transformer, ConvNeXt, and GoogLeNet training models had optimal results, with an accuracy of approximately 0.94; VGG11, VGG16, VGG19, ResNet 34, and ResNet 50, which are neural network models with fewer layers, achieved relatively strong results; and Transformer and other neural networks with more layers or neural network models with larger receptive fields exhibited a relatively weak performance. A heat map revealed the differences in the sinus, middle ear mastoid, and fourth ventricle between the patients with PCD and the control group. Transfer learning can improve the modeling effect of neural networks.<\/jats:p><jats:p><jats:bold>Conclusion:<\/jats:bold> Deep learning-based CT imaging models can accurately screen for PCD and identify differences between the cranial CT images.<\/jats:p>","DOI":"10.3389\/fphys.2023.1098893","type":"journal-article","created":{"date-parts":[[2023,3,15]],"date-time":"2023-03-15T05:50:01Z","timestamp":1678859401000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Deep learning for the screening of primary ciliary dyskinesia based on cranial computed tomography"],"prefix":"10.3389","volume":"14","author":[{"given":"Bo","family":"Duan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui-Ying","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng-Min","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Xia","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,3,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1126\/science.1084576","article-title":"A human syndrome caused by immotile cilia","volume":"193","author":"Afzelius","year":"1976","journal-title":"Science"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e22394","DOI":"10.2196\/22394","article-title":"Radiomic and genomic machine learning method performance for prostate cancer diagnosis: Systematic literature review","volume":"23","author":"Castaldo","year":"2021","journal-title":"J. Med. Internet Res."},{"key":"B3","unstructured":"OpenMMLab's image classification toolbox and benchmark\n            ContributorsM.\n          2020"},{"key":"B4","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1768","DOI":"10.1016\/j.chest.2021.02.006","article-title":"Clinical and genetic spectrum of children with primary ciliary dyskinesia in China","volume":"159","author":"Guan","year":"2021","journal-title":"Chest"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1109\/TMI.2015.2508280","article-title":"Deformable MR prostate segmentation via deep feature learning and sparse patch matching","volume":"35","author":"Guo","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B7","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B8","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1164\/rccm.201301-0059CI","article-title":"Primary ciliary dyskinesia. Recent advances in diagnostics, genetics, and characterization of clinical disease","volume":"188","author":"Knowles","year":"2013","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1109\/MOCAST.2019.8741677","article-title":"Simplified hardware implementation of the softmax activation function","author":"Kouretas","year":"2019"},{"key":"B10","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"B11","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","article-title":"Radiomics: The bridge between medical imaging and personalized medicine","volume":"14","author":"Lambin","year":"2017","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: Extracting more information from medical images using advanced feature analysis","volume":"48","author":"Lambin","year":"2012","journal-title":"Eur. J. Cancer"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1002\/jnr.23238","article-title":"Riding the wave of ependymal cilia: Genetic susceptibility to hydrocephalus in primary ciliary dyskinesia","volume":"91","author":"Lee","year":"2013","journal-title":"J. Neurosci. Res."},{"key":"B14","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1097\/GIM.0b013e3181a53562","article-title":"Clinical and genetic aspects of primary ciliary dyskinesia\/Kartagener syndrome","volume":"11","author":"Leigh","year":"2009","journal-title":"Genet. Med."},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"B16","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01167","article-title":"A ConvNet for the 2020s","author":"Liu","year":"2022"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1601090","DOI":"10.1183\/13993003.01090-2016","article-title":"European Respiratory Society guidelines for the diagnosis of primary ciliary dyskinesia","volume":"49","author":"Lucas","year":"2017","journal-title":"Eur. Respir. J."},{"key":"B18","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/S2213-2600(19)30374-1","article-title":"Primary ciliary dyskinesia in the genomics age","volume":"8","author":"Lucas","year":"2020","journal-title":"Lancet Respir. Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"135","DOI":"10.3389\/fped.2017.00135","article-title":"Primary ciliary dyskinesia: An update on clinical aspects, genetics, diagnosis, and future treatment strategies","volume":"5","author":"Mirra","year":"2017","journal-title":"Front. Pediatr."},{"key":"B20","doi-asserted-by":"publisher","first-page":"3784","DOI":"10.1109\/JBHI.2021.3051470","article-title":"Distant domain transfer learning for medical imaging","volume":"25","author":"Niu","year":"2021","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B21","first-page":"75","article-title":"Rhinosinusitis, symptomatology & absence of polyposis in children with primary ciliary dyskinesia","volume":"47","author":"Rollin","year":"2009","journal-title":"Rhinology"},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.74","article-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"B23","doi-asserted-by":"publisher","first-page":"101085","DOI":"10.1016\/j.ecoinf.2020.101085","article-title":"How many images do I need?\" Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoring","volume":"57","author":"Shahinfar","year":"2020","journal-title":"Ecol. Inf."},{"key":"B24","doi-asserted-by":"publisher","first-page":"e24","DOI":"10.1164\/rccm.201805-0819ST","article-title":"Diagnosis of primary ciliary dyskinesia. An official American thoracic society clinical practice guideline","volume":"197","author":"Shapiro","year":"2018","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"B25","doi-asserted-by":"publisher","first-page":"103854","DOI":"10.1016\/j.ridd.2021.103854","article-title":"The future of General Movement Assessment: The role of computer vision and machine learning - a scoping review","volume":"110","author":"Silva","year":"2021","journal-title":"Res. Dev. Disabil."},{"key":"B26","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015"},{"key":"B27","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s00405-010-1341-9","article-title":"ENT manifestations in patients with primary ciliary dyskinesia: Prevalence and significance of otorhinolaryngologic co-morbidities","volume":"268","author":"Sommer","year":"2011","journal-title":"Eur. Arch. Otorhinolaryngol."},{"key":"B28","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e451","DOI":"10.1097\/MAO.0000000000001599","article-title":"Analysis of otologic features of patients with primary ciliary dyskinesia","volume":"38","author":"Takeuchi","year":"2017","journal-title":"Otol. Neurotol."},{"key":"B30","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1016\/S2213-2600(18)30304-7","article-title":"Guideline provides new diagnostic insights for PCD","volume":"6","author":"The Lancet Respiratory Medicine","year":"2018","journal-title":"Lancet Respir. Med."},{"key":"B31","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1109\/jproc.2010.2050290","article-title":"LabelMe: Online image annotation and applications","volume":"98","author":"Torralba","year":"2010","journal-title":"Proc. IEEE"},{"key":"B32","article-title":"Attention is all you need","volume-title":"Advances in neural information processing systems","author":"Vaswani","year":"2017"},{"key":"B33","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.rmed.2015.01.015","article-title":"Clinical features of primary ciliary dyskinesia in Cyprus with emphasis on lobectomized patients","volume":"109","author":"Yiallouros","year":"2015","journal-title":"Respir. Med."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2023.1098893\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,15]],"date-time":"2023-03-15T05:50:11Z","timestamp":1678859411000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2023.1098893\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,15]]},"references-count":33,"alternative-id":["10.3389\/fphys.2023.1098893"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2023.1098893","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,15]]},"article-number":"1098893"}}