Computer-based facial recognition as an assisting diagnostic tool to identify children with Noonan syndrome

• Published in: BMC pediatrics Vol. 24; no. 1; pp. 361 - 9
• Main Authors: Huang, Yulu, Sun, Haomiao, Chen, Qinchang, Shen, Junjun, Han, Jin, Shan, Shiguang, Wang, Shushui
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 24.05.2024; BioMed Central; BMC
• Subjects: Accuracy; Adolescent; Automated Facial Recognition - methods; Back propagation; Batch normalization; Case-Control Studies; Child; Child, Preschool; Convolution neural network; Datasets; Diagnosis; Diagnosis, Computer-Assisted - methods; Facial recognition; Female; Genetic engineering; Genetic syndrome; Genetic testing; Humans; Infant; Kinases; Machine learning; Male; Medical diagnosis; Neural networks; Neural Networks, Computer; Noonan syndrome; Noonan Syndrome - diagnosis; Patients; Pediatric research; Pediatrics; Performance evaluation; Sensitivity and Specificity; China; Genetic syndrome; Convolution neural network; Noonan syndrome; Batch normalization; Facial recognition
• DOI: 10.1186/s12887-024-04827-7
• ISSN: 1471-2431

Noonan syndrome (NS) is a rare genetic disease, and patients who suffer from it exhibit a facial morphology that is characterized by a high forehead, hypertelorism, ptosis, inner epicanthal folds, down-slanting palpebral fissures, a highly arched palate, a round nasal tip, and posteriorly rotated ears. Facial analysis technology has recently been applied to identify many genetic syndromes (GSs). However, few studies have investigated the identification of NS based on the facial features of the subjects. This study develops advanced models to enhance the accuracy of diagnosis of NS. A total of 1,892 people were enrolled in this study, including 233 patients with NS, 863 patients with other GSs, and 796 healthy children. We took one to 10 frontal photos of each subject to build a dataset, and then applied the multi-task convolutional neural network (MTCNN) for data pre-processing to generate standardized outputs with five crucial facial landmarks. The ImageNet dataset was used to pre-train the network so that it could capture generalizable features and minimize data wastage. We subsequently constructed seven models for facial identification based on the VGG16, VGG19, VGG16-BN, VGG19-BN, ResNet50, MobileNet-V2, and squeeze-and-excitation network (SENet) architectures. The identification performance of seven models was evaluated and compared with that of six physicians. All models exhibited a high accuracy, precision, and specificity in recognizing NS patients. The VGG19-BN model delivered the best overall performance, with an accuracy of 93.76%, precision of 91.40%, specificity of 98.73%, and F1 score of 78.34%. The VGG16-BN model achieved the highest AUC value of 0.9787, while all models based on VGG architectures were superior to the others on the whole. The highest scores of six physicians in terms of accuracy, precision, specificity, and the F1 score were 74.00%, 75.00%, 88.33%, and 61.76%, respectively. The performance of each model of facial recognition was superior to that of the best physician on all metrics. Models of computer-assisted facial recognition can improve the rate of diagnosis of NS. The models based on VGG19-BN and VGG16-BN can play an important role in diagnosing NS in clinical practice.