The Establishment And Application Of An Intelligent Diagnosis System For Facial Images Of Turner Syndrome

BackgroundTechnologies applied for the recognition of facial features in diagnosing certain disorders seem to be promising in reducing the medical burden and improve the efficiency.This pilot study aimed to develop a computer-assisted tool for the pattern recognition of facial features for diagnosing Turner syndrome(TS).Materials and MethodsPhotographs of 54 patients with TS and 158 female controls were collected from July 2016 to May 2017.Finally,photographs of 32 patients with TS and 96 age-matched controls were included in the study that were further divided equally into training and testing groups.The process of automatic classification consisted of image preprocessing,facial feature extraction,feature reduction and fusion,automatic classification,and result presentation.A total of 27 physicians and 21 medical students completed a web-based test including the same photographs used in computer testing.ResultsAfter training,the automatic facial classification system for diagnosing TS achieved a 68.8%sensitivity and 87.5%specificity(and a 67.6%average sensitivity and 87.9%average specificity after resampling),which was significantly higher than the average sensitivity(57.4%,P<0.001)and specificity(75.4%,P<0.001)of 48 participants,respectively.ConclusionThe accuracy of this system was satisfactory and better than the diagnosis by clinicians.However,the system necessitates further improvement for achieving a high diagnostic accuracy in clinical practice.BackgroundAutomated facial recognition technology based on deep learning has achieved high accuracy in diagnosing some endocrine diseases and genetic syndromes.No study is yet published on the application of deep convolutional neural networks for the diagnosis of Turner syndrome(TS).Materials and MethodsPhotographs of 207 patients with TS and 1074 female controls were collected from July 2016 to April 16th 2019.Finally,205 patients diagnosed with TS and 1053 female controls were included.deep convolutional neural networks were used to develop the diagnostic system.After that,a prospective study were conducted to test the efficacy in the real clinical setting.That is,the photographs collected from April 16th 2019 to May 23 rd 2019 were used as test samples.ResultsAmong the results of 40 runs,the best AUC(area under curve)was 0.9876,and the best sensitivity/specificity was 97.94%/95.66%.ConclusionThe diagnostic system has achieved high accuracy.The results of the prospective study proved the application value of this system,which is promising in the screening of turner syndrome.