{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T18:53:51Z","timestamp":1790535231704,"version":"4.1.0"},"reference-count":40,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Facial Plastic Surgery &amp; Aesthetic Medicine"],"published-print":{"date-parts":[[2020,2,1]]},"abstract":"<jats:sec>\n                    <jats:title>Importance:<\/jats:title>\n                    <jats:p>Quantitative assessment of facial function is challenging, and subjective grading scales such as House\u2013Brackmann, Sunnybrook, and eFACE have well-recognized limitations. Machine learning (ML) approaches to facial landmark localization carry great clinical potential as they enable high-throughput automated quantification of relevant facial metrics from photographs and videos. However, the translation from research settings to clinical application still requires important improvements.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective:<\/jats:title>\n                    <jats:p>To develop a novel ML algorithm for fast and accurate localization of facial landmarks in photographs of facial palsy patients and utilize this technology as part of an automated computer-aided diagnosis system.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design, Setting, and Participants:<\/jats:title>\n                    <jats:p>Portrait photographs of 8 expressions obtained from 200 facial palsy patients and 10 healthy participants were manually annotated by localizing 68 facial landmarks in each photograph and by 3 trained clinicians using a custom graphical user interface. A novel ML model for automated facial landmark localization was trained using this disease-specific database. Algorithm accuracy was compared with manual markings and the output of a model trained using a larger database consisting only of healthy subjects.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Main Outcomes and Measurements:<\/jats:title>\n                    <jats:p>Root mean square error normalized by the interocular distance (NRMSE) of facial landmark localization between prediction of ML algorithm and manually localized landmarks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>\n                      Publicly available algorithms for facial landmark localization provide poor localization accuracy when applied to photographs of patients compared with photographs of healthy controls (NRMSE, 8.56\u2009\u00b1\u20092.16 vs. 7.09\u2009\u00b1\u20092.34,\n                      <jats:italic toggle=\"yes\">p<\/jats:italic>\n                      \u2009\u226a\u20090.01). We found significant improvement in facial landmark localization accuracy for the facial palsy patient population when using a model trained with a relatively small number photographs (1440) of patients compared with a model trained using several thousand more images of healthy faces (NRMSE, 6.03\u2009\u00b1\u20092.43 vs. 8.56\u2009\u00b1\u20092.16,\n                      <jats:italic toggle=\"yes\">p<\/jats:italic>\n                      \u2009\u226a\u20090.01).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions and Relevance:<\/jats:title>\n                    <jats:p>Retraining a computer vision facial landmark detection model with fewer than 1600 annotated images of patients significantly improved landmark detection performance in frontal view photographs of this population. The new annotated database and facial landmark localization model represent the first steps toward an automatic system for computer-aided assessment in facial palsy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of Evidence:<\/jats:title>\n                    <jats:p>4<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1089\/fpsam.2019.29000.gua","type":"journal-article","created":{"date-parts":[[2020,2,10]],"date-time":"2020-02-10T09:58:55Z","timestamp":1581328735000},"page":"42-49","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":94,"title":["Toward an Automatic System for Computer-Aided Assessment in Facial Palsy"],"prefix":"10.1177","volume":"22","author":[{"given":"Diego L.","family":"Guarin","sequence":"first","affiliation":[{"name":"KITE | Toronto Rehabilitation Institute\u2014University Health Network, Toronto, Canada."},{"name":"Department of Otolaryngology\/Head and Neck Surgery, Massachusetts Eye and Ear Infirmary and Harvard Medical School, Boston, Massachusetts."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yana","family":"Yunusova","sequence":"additional","affiliation":[{"name":"KITE | Toronto Rehabilitation Institute\u2014University Health Network, Toronto, Canada."},{"name":"Department of Speech Language Pathology, University of Toronto, Toronto, Canada."},{"name":"Hurvitz Brain Sciences Program, Sunnybrook Research Institute, Toronto, Canada."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Babak","family":"Taati","sequence":"additional","affiliation":[{"name":"KITE | Toronto Rehabilitation Institute\u2014University Health Network, Toronto, Canada."},{"name":"Department of Computer Science, University of Toronto, Toronto, Canada."},{"name":"Institute of Biomaterials and Biomedical Engineering, University of Toronto, Toronto, Canada."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph R.","family":"Dusseldorp","sequence":"additional","affiliation":[{"name":"Department of Plastic and Reconstructive Surgery, Royal Australasian College of Surgeons and University of Sydney, Sydney, Australia."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suresh","family":"Mohan","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\/Head and Neck Surgery, Massachusetts Eye and Ear Infirmary and Harvard Medical School, Boston, Massachusetts."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joana","family":"Tavares","sequence":"additional","affiliation":[{"name":"Faculty of Health Sciences, Brasilia University, Brasilia, Brazil."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martinus M.","family":"van Veen","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\/Head and Neck Surgery, Massachusetts Eye and Ear Infirmary and Harvard Medical School, Boston, Massachusetts."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily","family":"Fortier","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\/Head and Neck Surgery, Massachusetts Eye and Ear Infirmary and Harvard Medical School, Boston, Massachusetts."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tessa A.","family":"Hadlock","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\/Head and Neck Surgery, Massachusetts Eye and Ear Infirmary and Harvard Medical School, Boston, Massachusetts."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nate","family":"Jowett","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\/Head and Neck Surgery, Massachusetts Eye and Ear Infirmary and Harvard Medical School, Boston, Massachusetts."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2020,2,10]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1001\/archfaci.2012.111"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1177\/014556139607500608"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1001\/archfaci.2010.69"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1177\/000348949910800308"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1097\/PRS.0b013e31818a9a8d"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2016.03.011"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2707588"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2015.11.004"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamafacial.2018.0030"},{"key":"e_1_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Kazemi V Sullivan J. One millisecond face alignment with an ensemble of regression trees. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New Jersey: IEEE Publishing; 2014.","DOI":"10.1109\/CVPR.2014.241"},{"key":"e_1_3_3_13_2","doi-asserted-by":"crossref","unstructured":"Sagonas C Tzimiropoulos G Zafeiriou S Pantic M. 300 faces in-the-wild challenge: the first facial landmark localization challenge. In Proceedings of the IEEE International Conference on Computer Vision Workshops. New Jersey: IEEE Publishing; 2013.","DOI":"10.1109\/ICCVW.2013.59"},{"key":"e_1_3_3_14_2","doi-asserted-by":"crossref","unstructured":"Zhang Z Luo P Loy CC Tang X. Facial landmark detection by deep multi-task learning. In European Conference on Computer Vision. New York: Springer; 2014.","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"e_1_3_3_15_2","article-title":"The spectrum of facial palsy: the MEEI facial palsy photo & video standard set [published online April 25, 2019]","author":"Greene JJ","unstructured":"Greene JJ, , Tavares J, , Guarin DL, et al. The spectrum of facial palsy: the MEEI facial palsy photo & video standard set [published online April 25, 2019]. Laryngoscope. doi: 10.1002\/lary.27986.","journal-title":"Laryngoscope"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1097\/SAP.0000000000001545"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpeds.2018.06.043"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.otc.2018.08.018"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12984-018-0446-z"},{"key":"e_1_3_3_20_2","doi-asserted-by":"crossref","unstructured":"Lanz C Olgay BS Denzler J Gross H-M. Facial landmark localization and feature extraction for therapeutic face exercise classification. In International Conference on Computer Vision Imaging and Computer Graphics. New York: Springer; 2013.","DOI":"10.1007\/978-3-662-44911-0_12"},{"key":"e_1_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Bandini A Green JR Taati B Orlandi S Zinman L Yunusova Y. Automatic detection of amyotrophic lateral sclerosis (ALS) from video-based analysis of facial movements: speech and non-speech tasks. In 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018). New Jersey: IEEE Publishing; 2018.","DOI":"10.1109\/FG.2018.00031"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2900022"},{"key":"e_1_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r P Welinder P Perona P. Cascaded pose regression. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New Jersey: IEEE Publishing; 2010.","DOI":"10.1109\/CVPR.2010.5540094"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-018-0324-4"},{"key":"e_1_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Sun Y Wang X Tang X. Deep convolutional network cascade for facial point detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New Jersey: IEEE Publishing; 2013.","DOI":"10.1109\/CVPR.2013.446"},{"key":"e_1_3_3_26_2","doi-asserted-by":"crossref","unstructured":"Tzimiropoulos G. Project-out cascaded regression with an application to face alignment. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New Jersey: IEEE Publishing; 2015.","DOI":"10.1109\/CVPR.2015.7298989"},{"key":"e_1_3_3_27_2","doi-asserted-by":"crossref","unstructured":"Bulat A Tzimiropoulos G. How far are we from solving the 2d & 3d face alignment problem?(and a dataset of 230 000 3d facial landmarks). In Proceedings of the IEEE International Conference on Computer Vision. New Jersey: IEEE Publishing; 2017.","DOI":"10.1109\/ICCV.2017.116"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/2181796.2206309"},{"key":"e_1_3_3_29_2","first-page":"1755","article-title":"Dlib-ml: a machine learning toolkit","volume":"10","author":"King DE.","year":"2009","unstructured":"King DE. Dlib-ml: a machine learning toolkit. J Mach Learn Res. 2009; 10(Jul):1755\u20131758.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.23"},{"key":"e_1_3_3_31_2","doi-asserted-by":"crossref","unstructured":"Le V Brandt J Lin Z Bourdev L Huang TS. Interactive facial feature localization. In European Conference on Computer Vision. New York: Springer; 2012.","DOI":"10.1007\/978-3-642-33712-3_49"},{"key":"e_1_3_3_32_2","unstructured":"Ramanan D Zhu X. Face detection pose estimation and landmark localization in the wild. In Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Citeseer. New Jersey: IEEE Publishing; 2012."},{"key":"e_1_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Sagonas C Tzimiropoulos G Zafeiriou S Pantic M. A semi-automatic methodology for facial landmark annotation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. New Jersey: IEEE Publishing; 2013.","DOI":"10.1109\/CVPRW.2013.132"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.08.002"},{"key":"e_1_3_3_35_2","unstructured":"Sim T Baker S Bsat M. The CMU pose illumination and expression (PIE) database. In Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition. New Jersey: IEEE Publishing; 2002."},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamafacial.2016.1883"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1177\/019459988509300202"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0194-59989670206-1"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1097\/PRS.0000000000001447"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1097\/PRS.0000000000002954"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.otohns.2008.11.021"}],"container-title":["Facial Plastic Surgery &amp; Aesthetic Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1089\/fpsam.2019.29000.gua","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1089\/fpsam.2019.29000.gua","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1089\/fpsam.2019.29000.gua","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T06:23:13Z","timestamp":1777443793000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1089\/fpsam.2019.29000.gua"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,1]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,2,1]]}},"alternative-id":["10.1089\/fpsam.2019.29000.gua"],"URL":"https:\/\/doi.org\/10.1089\/fpsam.2019.29000.gua","relation":{},"ISSN":["2689-3614","2689-3622"],"issn-type":[{"value":"2689-3614","type":"print"},{"value":"2689-3622","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,1]]}}}