{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T17:10:23Z","timestamp":1789837823721,"version":"4.0.1"},"reference-count":29,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"1","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7]]},"abstract":"<jats:sec>\n            <jats:title>Background:<\/jats:title>\n            <jats:p>Despite the wide range of cleft lip morphology, consistent scales to categorize preoperative severity do not exist. Machine learning has been used to increase accuracy and efficiency in detection and rating of multiple conditions, yet it has not been applied to cleft disease. The authors tested a machine learning approach to automatically detect and measure facial landmarks and assign severity grades using preoperative photographs.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods:<\/jats:title>\n            <jats:p>Preoperative images were collected from 800 unilateral cleft lip patients, manually annotated for cleft-specific landmarks, and rated using a previously validated severity scale by eight expert reviewers. Five convolutional neural network models were trained for landmark detection and severity grade assignment. Mean squared error loss and Pearson correlation coefficient for cleft width ratio, nostril width ratio, and severity grade assignment were calculated.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results:<\/jats:title>\n            <jats:p>All five models performed well in landmark detection and severity grade assignment, with the largest and most complex model, Residual Network, performing best (mean squared error, 24.41; cleft width ratio correlation, 0.943; nostril width ratio correlation, 0.879; severity correlation, 0.892). The mobile device\u2013compatible network, MobileNet, also showed a high degree of accuracy (mean squared error, 36.66; cleft width ratio correlation, 0.901; nostril width ratio correlation, 0.705; severity correlation, 0.860).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions:<\/jats:title>\n            <jats:p>Machine learning models demonstrate the ability to accurately measure facial features and assign severity grades according to validated scales. Such models hold promise for the creation of a simple, automated approach to classifying cleft lip morphology. Further potential exists for a mobile telephone\u2013based application to provide real-time feedback to improve clinical decision making and patient counseling.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1097\/prs.0000000000008063","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T20:07:13Z","timestamp":1624910833000},"page":"162-169","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":32,"title":["Convolutional Neural Network Models for Automatic Preoperative Severity Assessment in Unilateral Cleft Lip"],"prefix":"10.1097","volume":"148","author":[{"given":"Meghan","family":"McCullough","sequence":"first","affiliation":[{"name":"From the Division of Plastic Surgery, Keck School of Medicine, and Department of Computer Science, University of Southern California; Division of Plastic Surgery, Children\u2019s Hospital of Los Angeles; Operation Smile; and Department of Plastic and Reconstructive Surgery, Shriners Hospital for Children."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven","family":"Ly","sequence":"additional","affiliation":[{"name":"From the Division of Plastic Surgery, Keck School of Medicine, and Department of Computer Science, University of Southern California; Division of Plastic Surgery, Children\u2019s Hospital of Los Angeles; Operation Smile; and Department of Plastic and Reconstructive Surgery, Shriners Hospital for Children."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allyn","family":"Auslander","sequence":"additional","affiliation":[{"name":"From the Division of Plastic Surgery, Keck School of Medicine, and Department of Computer Science, University of Southern California; Division of Plastic Surgery, Children\u2019s Hospital of Los Angeles; Operation Smile; and Department of Plastic and Reconstructive Surgery, Shriners Hospital for Children."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caroline","family":"Yao","sequence":"additional","affiliation":[{"name":"From the Division of Plastic Surgery, Keck School of Medicine, and Department of Computer Science, University of Southern California; Division of Plastic Surgery, Children\u2019s Hospital of Los Angeles; Operation Smile; and Department of Plastic and Reconstructive Surgery, Shriners Hospital for Children."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Campbell","sequence":"additional","affiliation":[{"name":"From the Division of Plastic Surgery, Keck School of Medicine, and Department of Computer Science, University of Southern California; Division of Plastic Surgery, Children\u2019s Hospital of Los Angeles; Operation Smile; and Department of Plastic and Reconstructive Surgery, Shriners Hospital for Children."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Scherer","sequence":"additional","affiliation":[{"name":"From the Division of Plastic Surgery, Keck School of Medicine, and Department of Computer Science, University of Southern California; Division of Plastic Surgery, Children\u2019s Hospital of Los Angeles; Operation Smile; and Department of Plastic and Reconstructive Surgery, Shriners Hospital for Children."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William P.","family":"Magee","sequence":"additional","affiliation":[{"name":"From the Division of Plastic Surgery, Keck School of Medicine, and Department of Computer Science, University of Southern California; Division of Plastic Surgery, Children\u2019s Hospital of Los Angeles; Operation Smile; and Department of Plastic and Reconstructive Surgery, Shriners Hospital for Children."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2021,6,29]]},"reference":[{"key":"R1-20250501","first-page":"e10","article-title":"A cross-sectional comparison of cleft lip severity in 3 regional populations.","volume":"12","author":"Lanteri","year":"2012","journal-title":"Eplasty"},{"key":"R2-20250501","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/s12663-011-0298-6","article-title":"Assessment of deformities of the lip and nose in cleft lip alveolus and palate patients by a rating scale.","volume":"11","author":"Rajanikanth","year":"2012","journal-title":"J Maxillofac Oral Surg"},{"key":"R3-20250501","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1597\/1545-1569_1991_028_0419_dososo_2.3.co_2","article-title":"Development of scales of severity of facial cleft impairment.","volume":"28","author":"Tobiasen","year":"1991","journal-title":"Cleft Palate Craniofac J"},{"key":"R4-20250501","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1097\/PRS.0b013e3181811a52","article-title":"Objective measurements for grading the primary unilateral cleft lip nasal deformity.","volume":"122","author":"Fisher","year":"2008","journal-title":"Plast Reconstr Surg"},{"key":"R5-20250501","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1097\/PRS.0000000000001369","article-title":"Unilateral cleft lip repair using the anatomical subunit approximation: Modifications and analysis of early results in 100 consecutive cases.","volume":"136","author":"Tse","year":"2015","journal-title":"Plast Reconstr Surg"},{"key":"R6-20250501","doi-asserted-by":"crossref","first-page":"e198","DOI":"10.1597\/14-274","article-title":"Preoperative cleft lip measurements and maxillary growth in patients with unilateral cleft lip and palate.","volume":"53","author":"Antonarakis","year":"2016","journal-title":"Cleft Palate Craniofac J"},{"key":"R7-20250501","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1097\/PRS.0b013e318200aa2e","article-title":"Presurgical unilateral cleft lip anthropometrics: Implications for the choice of repair technique.","volume":"127","author":"Boorer","year":"2011","journal-title":"Plast Reconstr Surg"},{"key":"R8-20250501","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1597\/13-099","article-title":"Objective measurements for grading the nasal esthetics on basal view in individuals with secondary cleft nasal deformity.","volume":"52","author":"He","year":"2015","journal-title":"Cleft Palate Craniofac J"},{"key":"R9-20250501","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1097\/PRS.0000000000003931","article-title":"The Smile Index: Part 1. A large-scale study of phenotypic norms for preoperative and postoperative unilateral cleft lip.","volume":"141","author":"Yao","year":"2018","journal-title":"Plast Reconstr Surg"},{"key":"R10-20250501","doi-asserted-by":"crossref","first-page":"e0148195","DOI":"10.1371\/journal.pone.0148195","article-title":"Fusing data mining, machine learning and traditional statistics to detect biomarkers associated with depression.","volume":"11","author":"Dipnall","year":"2016","journal-title":"PLoS One"},{"key":"R11-20250501","doi-asserted-by":"crossref","first-page":"e0179790","DOI":"10.1371\/journal.pone.0179790","article-title":"Applying artificial intelligence to disease staging: Deep learning for improved staging of diabetic retinopathy.","volume":"12","author":"Takahashi","year":"2017","journal-title":"PLoS One"},{"key":"R12-20250501","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1136\/bjophthalmol-2018-313156","article-title":"Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity.","volume":"103","author":"Redd","year":"2019","journal-title":"Br J Ophthalmol"},{"key":"R13-20250501","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/s10278-017-9994-1","article-title":"Machine learning: Discovering the future of medical imaging.","volume":"30","author":"Erickson","year":"2017","journal-title":"J Digit Imaging"},{"key":"R14-20250501","doi-asserted-by":"crossref","first-page":"2113","DOI":"10.1148\/rg.2017170077","article-title":"Deep learning: A primer for radiologists.","volume":"37","author":"Chartrand","year":"2017","journal-title":"Radiographics"},{"key":"R15-20250501","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.ijcard.2017.05.067","article-title":"Machine learning for prediction of 30-day mortality after ST elevation myocardial infraction: An acute coronary syndrome Israeli survey data mining study.","volume":"246","author":"Shouval","year":"2017","journal-title":"Int J Cardiol"},{"key":"R16-20250501","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1111\/echo.14220","article-title":"Deep learning for predicting in-hospital mortality among heart disease patients based on echocardiography.","volume":"36","author":"Kwon","year":"2019","journal-title":"Echocardiography"},{"key":"R17-20250501","first-page":"abs\/1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition.","author":"Simonyan","year":"2014","journal-title":"CoRR"},{"key":"R20-20250501","first-page":"abs\/1704.04861","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications.","author":"Howard","year":"2017","journal-title":"ArXiv"},{"key":"R21-20250501","doi-asserted-by":"crossref","first-page":"e1479","DOI":"10.1097\/GOX.0000000000001479","article-title":"Validation of the unilateral cleft lip severity index for surgeons and laypersons.","volume":"5","author":"Campbell","year":"2017","journal-title":"Plast Reconstr Surg Glob Open"},{"key":"R22-20250501","article-title":"Adam: A method for stochastic optimization.","author":"Kingma","year":"2015","journal-title":"CoRR"},{"key":"R23-20250501","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1109\/42.932741","article-title":"An artificial intelligent algorithm for tumor detection in screening mammogram.","volume":"20","author":"Zheng","year":"2001","journal-title":"IEEE Trans Med Imaging"},{"key":"R25-20250501","doi-asserted-by":"crossref","first-page":"1172","DOI":"10.1109\/TMI.2017.2655486","article-title":"Detecting cardiovascular disease from mammograms with deep learning.","volume":"36","author":"Wang","year":"2017","journal-title":"IEEE Trans Med Imaging"},{"key":"R26-20250501","first-page":"143","article-title":"Effective diagnosis and monitoring of heart disease.","volume":"9","author":"Otoom","year":"2015","journal-title":"International Journal of Software Engineering and Its Applications"},{"key":"R28-20250501","first-page":"680","article-title":"Comparative study for analysis the prognostic in hepatitis data: Data mining approach.","volume":"4","author":"Ba-Alwi","year":"2013","journal-title":"International Journal of Scientific & Engineering Research"},{"key":"R29-20250501","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1109\/JBHI.2016.2538559","article-title":"Voxel-based diagnosis of Alzheimer\u2019s disease using classifier ensembles.","volume":"21","author":"Arma\u00f1anzas","year":"2017","journal-title":"IEEE J Biomed Health Inform"},{"key":"R30-20250501","doi-asserted-by":"crossref","first-page":"1102","DOI":"10.1109\/TCYB.2016.2644718","article-title":"Relational-regularized discriminative sparse learning for Alzheimer\u2019s disease diagnosis.","volume":"47","author":"Lei","year":"2017","journal-title":"IEEE Trans Cybern"},{"key":"R31-20250501","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1080\/00207721.2012.724114","article-title":"New machine-learning algorithms for prediction of Parkinson\u2019s disease.","volume":"45","author":"Mandal","year":"2014","journal-title":"International Journal of Systems Science"},{"key":"R32-20250501","doi-asserted-by":"crossref","first-page":"2177","DOI":"10.1109\/TBME.2015.2512941","article-title":"Automatic quantification of radiographic finger joint space width of patients with early rheumatoid arthritis.","volume":"63","author":"Huo","year":"2016","journal-title":"IEEE Trans Biomed Eng"},{"key":"R33-20250501","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1597\/15-053","article-title":"Measuring symmetry in children with unrepaired cleft lip: Defining a standard for the three-dimensional midfacial reference plane.","volume":"53","author":"Wu","year":"2016","journal-title":"Cleft Palate Craniofac J"}],"container-title":["Plastic &amp; Reconstructive Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/PRS.0000000000008063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T00:20:00Z","timestamp":1746145200000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/PRS.0000000000008063"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,29]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.1097\/prs.0000000000008063","relation":{},"ISSN":["0032-1052"],"issn-type":[{"value":"0032-1052","type":"print"}],"subject":[],"published":{"date-parts":[[2021,6,29]]}}}