{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T10:45:14Z","timestamp":1750675514824,"version":"3.37.3"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"1191","license":[{"start":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T00:00:00Z","timestamp":1722211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82070321"],"award-info":[{"award-number":["82070321"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Williams\u2013Beuren syndrome, Noonan syndrome, and Alagille syndrome are common types of genetic syndromes (GSs) characterized by distinct facial features, pulmonary stenosis, and delayed growth. In clinical practice, differentiating these three GSs remains a challenge. Facial gestalts serve as a diagnostic tool for recognizing Williams\u2013Beuren syndrome, Noonan syndrome, and Alagille syndrome. Pretrained foundation models (PFMs) can be considered the foundation for small-scale tasks. By pretraining with a foundation model, we propose facial recognition models for identifying these syndromes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>A total of 3297 (n = 1666) facial photos were obtained from children diagnosed with Williams\u2013Beuren syndrome (n = 174), Noonan syndrome (n = 235), and Alagille syndrome (n = 51), and from children without GSs (n = 1206). The photos were randomly divided into five subsets, with each syndrome and non-GS equally and randomly distributed in each subset. The proportion of the training set and the test set was 4:1. The ResNet-100 architecture was employed as the backbone model. By pretraining with a foundation model, we constructed two face recognition models: one utilizing the ArcFace loss function, and the other employing the CosFace loss function. Additionally, we developed two models using the same architecture and loss function but without pretraining. The accuracy, precision, recall, and F1 score of each model were evaluated. Finally, we compared the performance of the facial recognition models to that of five pediatricians.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Among the four models, ResNet-100 with a PFM and CosFace loss function achieved the best accuracy (84.8%). Of the same loss function, the performance of the PFMs significantly improved (from 78.5% to 84.5% for the ArcFace loss function, and from 79.8% to 84.8% for the CosFace loss function). With and without the PFM, the performance of the CosFace loss function models was similar to that of the ArcFace loss function models (79.8% vs 78.5% without PFM; 84.8% vs 84.5% with PFM). Among the five pediatricians, the highest accuracy (0.700) was achieved by the senior-most pediatrician with genetics training. The accuracy and F1 scores of the pediatricians were generally lower than those of the models.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>A facial recognition-based model has the potential to improve the identification of three common GSs with pulmonary stenosis. PFMs might be valuable for building screening models for facial recognition.<\/jats:p>\n                  <jats:p>Key messages What is already known on this topic:\u00a0 Early identification of genetic syndromes (GSs) is crucial for the management and prognosis of children with pulmonary stenosis (PS). Facial phenotyping with convolutional neural networks (CNNs) often requires large-scale training data, limiting its usefulness for GSs. What this study adds:\u00a0 We successfully built multi-classification models based on face recognition using a CNN to accurately identify three common PS-associated GSs. ResNet-100 with a pretrained foundation model (PFM) and CosFace loss function achieved the best accuracy (84.8%). Pretrained with the foundation model, the performance of the models significantly improved, although the impact of the type of loss function appeared to be minimal. How this study might affect research, practice, or policy:\u00a0 A facial recognition-based model has the potential to improve the identification of GSs in children with PS. The PFM might be valuable for building identification models for facial detection.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/postmj\/qgae095","type":"journal-article","created":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T12:31:58Z","timestamp":1722342718000},"page":"37-44","source":"Crossref","is-referenced-by-count":3,"title":["Facial recognition models for identifying genetic syndromes associated with pulmonary stenosis in children"],"prefix":"10.1093","volume":"101","author":[{"given":"Jun-Jun","family":"Shen","sequence":"first","affiliation":[{"name":"Department of Pediatric Surgery , Zhujiang Hospital, , No. 253, Industrial Avenue Middle, Guangzhou 510282, Guangdong,","place":["China"]},{"name":"Southern Medical University , Zhujiang Hospital, , No. 253, Industrial Avenue Middle, Guangzhou 510282, Guangdong,","place":["China"]},{"name":"Department of Pediatric Cardiology , Guangdong Provincial People\u2019s Hospital (Guangdong Academy of Medical Sciences), , No. 106, Zhongshan 2nd Road, Guangzhou 510000,","place":["China"]},{"name":"Southern Medical University , Guangdong Provincial People\u2019s Hospital (Guangdong Academy of Medical Sciences), , No. 106, Zhongshan 2nd Road, Guangzhou 510000,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1415-5148","authenticated-orcid":false,"given":"Qin-Chang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Pediatric Cardiology , Guangdong Provincial People\u2019s Hospital (Guangdong Academy of Medical Sciences), , No. 106, Zhongshan 2nd Road, Guangzhou 510000,","place":["China"]},{"name":"Southern Medical University , Guangdong Provincial People\u2019s Hospital (Guangdong Academy of Medical Sciences), , No. 106, Zhongshan 2nd Road, Guangzhou 510000,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Lu","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Pediatric Cardiology , Guangdong Provincial People\u2019s Hospital (Guangdong Academy of Medical Sciences), , No. 106, Zhongshan 2nd Road, Guangzhou 510000,","place":["China"]},{"name":"Southern Medical University , Guangdong Provincial People\u2019s Hospital (Guangdong Academy of Medical Sciences), , No. 106, Zhongshan 2nd Road, Guangzhou 510000,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Pediatric Surgery , Zhujiang Hospital, , No. 253, Industrial Avenue Middle, Guangzhou 510282, Guangdong,","place":["China"]},{"name":"Southern Medical University , Zhujiang Hospital, , No. 253, Industrial Avenue Middle, Guangzhou 510282, Guangdong,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liu-Cheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Pediatric Surgery , Zhujiang Hospital, , No. 253, Industrial Avenue Middle, Guangzhou 510282, Guangdong,","place":["China"]},{"name":"Southern Medical University , Zhujiang Hospital, , No. 253, Industrial Avenue Middle, Guangzhou 510282, Guangdong,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu-Shui","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Pediatric Cardiology , Guangdong Provincial People\u2019s Hospital (Guangdong Academy of Medical Sciences), , No. 106, Zhongshan 2nd Road, Guangzhou 510000,","place":["China"]},{"name":"Southern Medical University , Guangdong Provincial People\u2019s Hospital (Guangdong Academy of Medical Sciences), , No. 106, Zhongshan 2nd Road, Guangzhou 510000,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,7,29]]},"reference":[{"key":"2024122317360558100_ref1","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1111\/pan.13620","article-title":"Williams syndrome","volume":"29","author":"Twite","year":"2019","journal-title":"Paediatr. Anaesth"},{"key":"2024122317360558100_ref2","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1002\/ajmg.c.31765","article-title":"Congenital heart defects in Noonan syndrome: Diagnosis, management, and treatment","volume":"184","author":"Linglart","year":"2020","journal-title":"Am J Med Genet C"},{"key":"2024122317360558100_ref3","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1007\/s00247-016-3580-4","article-title":"CT-defined phenotype of pulmonary artery stenoses in Alagille syndrome","volume":"46","author":"Rodriguez","year":"2016","journal-title":"Pediatr Radiol"},{"key":"2024122317360558100_ref4","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1002\/ccd.30148","article-title":"Supravalvular pulmonary stenosis: a risk factor for reintervention in Noonan syndrome with pulmonary valve stenosis","volume":"99","author":"Abumehdi","year":"2022","journal-title":"Catheter Cardio Inte"},{"key":"2024122317360558100_ref5","article-title":"Joint involvement in Noonan syndrome. A retrospective paediatric descriptive study","volume":"89","author":"Le Quellec","year":"2021","journal-title":"Joint Bone Spine"},{"key":"2024122317360558100_ref6","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1111\/chd.12721","article-title":"Prevalence of Noonan spectrum disorders in a pediatric population with valvar pulmonary stenosis","volume":"14","author":"Anderson","year":"2018","journal-title":"Congenit Heart Dis"},{"key":"2024122317360558100_ref7","first-page":"92","article-title":"Cardiac defects, morbidity and mortality in patients affected by RASopathies","volume":"245","author":"Calcagni","year":"2017","journal-title":"CARNET study results. Int J Cardiol"},{"key":"2024122317360558100_ref8","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.02020","article-title":"Diagnostically relevant facial gestalt information from ordinary photos","volume":"3","author":"Ferry","year":"2014","journal-title":"Elife"},{"key":"2024122317360558100_ref9","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1038\/s41588-021-01010-x","article-title":"GestaltMatcher facilitates rare disease matching using facial phenotype descriptors","volume":"54","author":"Hsieh","year":"2022","journal-title":"Nat Genet"},{"key":"2024122317360558100_ref10","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s41591-018-0279-0","article-title":"Identifying facial phenotypes of genetic disorders using deep learning","volume":"25","author":"Gurovich","year":"2019","journal-title":"Nat Med"},{"key":"2024122317360558100_ref11","doi-asserted-by":"crossref","first-page":"6595","DOI":"10.3390\/s21196595","article-title":"Deep learning-based analysis of face images as a screening tool for genetic syndromes","volume":"21","author":"Geremek","year":"2021","journal-title":"Sensors (Basel)"},{"key":"2024122317360558100_ref12","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1080\/10408363.2018.1536111","article-title":"Deep learning for image analysis: Personalizing medicine closer to the point of care","volume":"56","author":"Xie","year":"2019","journal-title":"Crit Rev Clin Lab Sci"},{"key":"2024122317360558100_ref13","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1186\/s13073-019-0689-8","article-title":"Artificial intelligence in clinical and genomic diagnostics","volume":"11","author":"Dias","year":"2019","journal-title":"Genome Med"},{"article-title":"On the opportunities and risks of foundation models","year":"2021","author":"Bommasani","key":"2024122317360558100_ref14"},{"key":"2024122317360558100_ref15","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1186\/s13023-021-01979-y","article-title":"Genetic syndromes screening by facial recognition technology: VGG-16 screening model construction and evaluation","volume":"16","author":"Hong","year":"2021","journal-title":"Orphanet J Rare Dis"},{"article-title":"A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPT","year":"2023","author":"Zhou","key":"2024122317360558100_ref16"},{"key":"2024122317360558100_ref17","doi-asserted-by":"crossref","first-page":"117084","DOI":"10.1109\/ACCESS.2022.3218160","article-title":"Multiple genetic syndromes recognition based on a deep learning framework and cross-loss training","volume":"10","author":"Wang","year":"2022","journal-title":"IEEE Access"},{"key":"2024122317360558100_ref18","article-title":"Automated facial recognition for Noonan syndrome using novel deep convolutional neural network with additive angular margin loss","volume":"12","author":"Yang","year":"2021","journal-title":"Front Genet"},{"article-title":"PyTorch: An imperative style, high-performance deep learning library","year":"2019","author":"Adam","key":"2024122317360558100_ref19"},{"article-title":"Joint face detection and alignment using multi-task cascaded convolutional networks","year":"2016","author":"Zhang","key":"2024122317360558100_ref20"},{"key":"2024122317360558100_ref21","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00482","article-title":"ArcFace: Additive angular margin loss for deep face recognition","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Deng","year":"2019"},{"key":"2024122317360558100_ref22","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"He","year":"2016"},{"key":"2024122317360558100_ref23","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00552","article-title":"Cosface: Large margin cosine loss for deep face recognition","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Wang","year":"2018"},{"key":"2024122317360558100_ref24","article-title":"Automatic facial recognition of Williams-Beuren syndrome based on deep convolutional neural networks","volume":"9","author":"Liu","year":"2021","journal-title":"Front Pediatr"},{"issue":"4","key":"2024122317360558100_ref25","doi-asserted-by":"crossref","first-page":"e71","DOI":"10.1016\/j.jormas.2021.04.003","article-title":"Computational diagnostic methods on 2D photographs: a review of the literature","volume":"122","author":"Hennocq","year":"2021","journal-title":"J Stomatol Oral Maxillofac Surg"},{"key":"2024122317360558100_ref26","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.artmed.2014.08.003","article-title":"Biomedical visual data analysis to build an intelligent diagnostic decision support system in medical genetics","volume":"62","author":"Kuru","year":"2014","journal-title":"Artif Intell Med"},{"key":"2024122317360558100_ref27","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1007\/s10545-018-0174-3","article-title":"Advances in computer-assisted syndrome recognition by the example of inborn errors of metabolism","volume":"41","author":"Pantel","year":"2018","journal-title":"J Inherit Metab Dis"},{"key":"2024122317360558100_ref28","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1038\/s10038-019-0598-0","article-title":"The facial dysmorphology analysis technology in intellectual disability syndromes related to defects in the histones modifiers","volume":"64","author":"Pascolini","year":"2019","journal-title":"J Hum Genet"},{"key":"2024122317360558100_ref29","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1002\/ajmg.a.38630","article-title":"Natural history and genotype-phenotype correlations in 72 individuals with SATB2-associated syndrome","volume":"176","author":"Zarate","year":"2018","journal-title":"Am J Med Genet A"},{"key":"2024122317360558100_ref30","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2009"},{"key":"2024122317360558100_ref31","doi-asserted-by":"crossref","first-page":"6869","DOI":"10.1038\/s41598-023-33374-x","article-title":"Population-specific facial traits and diagnosis accuracy of genetic and rare diseases in an admixed Colombian population","volume":"13","author":"Echeverry-Quiceno","year":"2023","journal-title":"Sci Rep"}],"container-title":["Postgraduate Medical Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/pmj\/article-pdf\/101\/1191\/37\/58681914\/qgae095.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/pmj\/article-pdf\/101\/1191\/37\/58681914\/qgae095.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T17:36:26Z","timestamp":1734975386000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/pmj\/article\/101\/1191\/37\/7723586"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,29]]},"references-count":31,"journal-issue":{"issue":"1191","published-online":{"date-parts":[[2024,7,29]]},"published-print":{"date-parts":[[2024,12,23]]}},"URL":"https:\/\/doi.org\/10.1093\/postmj\/qgae095","relation":{},"ISSN":["0032-5473","1469-0756"],"issn-type":[{"type":"print","value":"0032-5473"},{"type":"electronic","value":"1469-0756"}],"subject":[],"published-other":{"date-parts":[[2025,1]]},"published":{"date-parts":[[2024,7,29]]}}}