Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
Add more filters










Database
Publication year range
1.
Front Genet ; 12: 669841, 2021.
Article in English | MEDLINE | ID: mdl-34163525

ABSTRACT

BACKGROUND: Noonan syndrome (NS), a genetically heterogeneous disorder, presents with hypertelorism, ptosis, dysplastic pulmonary valve stenosis, hypertrophic cardiomyopathy, and small stature. Early detection and assessment of NS are crucial to formulating an individualized treatment protocol. However, the diagnostic rate of pediatricians and pediatric cardiologists is limited. To overcome this challenge, we propose an automated facial recognition model to identify NS using a novel deep convolutional neural network (DCNN) with a loss function called additive angular margin loss (ArcFace). METHODS: The proposed automated facial recognition models were trained on dataset that included 127 NS patients, 163 healthy children, and 130 children with several other dysmorphic syndromes. The photo dataset contained only one frontal face image from each participant. A novel DCNN framework with ArcFace loss function (DCNN-Arcface model) was constructed. Two traditional machine learning models and a DCNN model with cross-entropy loss function (DCNN-CE model) were also constructed. Transfer learning and data augmentation were applied in the training process. The identification performance of facial recognition models was assessed by five-fold cross-validation. Comparison of the DCNN-Arcface model to two traditional machine learning models, the DCNN-CE model, and six physicians were performed. RESULTS: At distinguishing NS patients from healthy children, the DCNN-Arcface model achieved an accuracy of 0.9201 ± 0.0138 and an area under the receiver operator characteristic curve (AUC) of 0.9797 ± 0.0055. At distinguishing NS patients from children with several other genetic syndromes, it achieved an accuracy of 0.8171 ± 0.0074 and an AUC of 0.9274 ± 0.0062. In both cases, the DCNN-Arcface model outperformed the two traditional machine learning models, the DCNN-CE model, and six physicians. CONCLUSION: This study shows that the proposed DCNN-Arcface model is a promising way to screen NS patients and can improve the NS diagnosis rate.

3.
Zhonghua Er Ke Za Zhi ; 50(12): 925-8, 2012 Dec.
Article in Chinese | MEDLINE | ID: mdl-23324151

ABSTRACT

OBJECTIVE: To assess the safety and efficacy of transcatheter intervention for critical pulmonary stenosis (CPS) and pulmonary atresia with intact ventricular septum (PA/IVS) in neonates. METHOD: From June 2006 to September 2011, 27 neonates including CPS in 19 patients and PA/IVS in 8 patients underwent transcatheter intervention. All patients had membranous stenosis or atresia without severe Ebstein's anomaly and severe right ventricle and pulmonary valve hypoplasia, without right ventricle-dependent coronary circulation in PA/IVS. The mean age was (16.8 ± 9.9) d. The mean weight was (3.3 ± 0.5) kg. Two of them were premature neonates, the weight was 2.3 kg and 2.5 kg, respectively. The procedural success, early outcome, complication rates, midterm results and pulmonary regurgitation were retrospectively studied. RESULT: Twenty-six patients were successfully treated with transcatheter intervention. Right ventricular pressure fell from (112.0 ± 21.0) mm Hg (1 mm Hg = 0.133 kPa) to (50.4 ± 15.9) mm Hg (P < 0.001). The ratio of right ventricular pressure and aortic pressure fell from 1.7 ± 0.1 to 0.7 ± 0.3 (P < 0.001). One patient died early of PA/IVS. Complication occurred in 5 patients. Hemopericardium occurred in 3 patients, tachyarrhythmia in 2 patients. Five patients needed prolonged prostaglandin E(1) infusion for 3 to 14 days because of desaturation after the procedure. No patient needed surgery in neonatal period. At a mean follow-up of (33.5 ± 18.3) months (from 6 months to 5 years), 21 patients had no further transcatheter or surgical intervention. Four patients with CPS had moderate to severe residual pulmonary stenosis after the procedure, 3 of them underwent a second balloon dilation at 3 months of follow-up, the other one was waiting for the second balloon dilation. One patient with PA/IVS was waiting for a bidirectional Glenn procedure because of chronic right ventricular failure. Mild pulmonary regurgitation occurred in 18 patients (69.2%), and moderate pulmonary regurgitation in 8 patients (30.8%). CONCLUSION: Transcatheter intervention for CPS and PA/IVS in neonates is safe and effective. It can avoid neonatal surgery. Some patients may require repeat balloon valvuloplasty in infant period. In most patients surgical or transcatheter intervention could be avoided and mild pulmonary regurgitation was the common finding in midterm follow-up.


Subject(s)
Catheterization/methods , Heart Defects, Congenital/surgery , Pulmonary Atresia/surgery , Pulmonary Valve Stenosis/surgery , Pulmonary Valve/surgery , Catheterization/instrumentation , Female , Follow-Up Studies , Humans , Infant, Newborn , Male , Reoperation , Retrospective Studies , Treatment Outcome
SELECTION OF CITATIONS
SEARCH DETAIL
...