Optimization and evaluation of facial recognition models for Williams-Beuren syndrome.

Williams-Beuren syndrome (WBS) is a rare genetic disorder characterized by special facial gestalt, delayed development, and supravalvular aortic stenosis or/and stenosis of the branches of the pulmonary artery. We aim to develop and optimize accurate models of facial recognition to assist in the diagnosis of WBS, and to evaluate their effectiveness by using both five-fold cross-validation and an external test set. We used a total of 954 images from 135 patients with WBS, 124 patients suffering from other genetic disorders, and 183 healthy children. The training set comprised 852 images of 104 WBS cases, 91 cases of other genetic disorders, and 145 healthy children from September 2017 to December 2021 at the Guangdong Provincial People's Hospital. We constructed six binary classification models of facial recognition for WBS by using EfficientNet-b3, ResNet-50, VGG-16, VGG-16BN, VGG-19, and VGG-19BN. Transfer learning was used to pre-train the models, and each model was modified with a variable cosine learning rate. Each model was first evaluated by using five-fold cross-validation and then assessed on the external test set. The latter contained 102 images of 31 children suffering from WBS, 33 children with other genetic disorders, and 38 healthy children. To compare the capabilities of these models of recognition with those of human experts in terms of identifying cases of WBS, we recruited two pediatricians, a pediatric cardiologist, and a pediatric geneticist to identify the WBS patients based solely on their facial images. We constructed six models of facial recognition for diagnosing WBS using EfficientNet-b3, ResNet-50, VGG-16, VGG-16BN, VGG-19, and VGG-19BN. The model based on VGG-19BN achieved the best performance in terms of five-fold cross-validation, with an accuracy of 93.74% ± 3.18%, precision of 94.93% ± 4.53%, specificity of 96.10% ± 4.30%, and F1 score of 91.65% ± 4.28%, while the VGG-16BN model achieved the highest recall value of 91.63% ± 5.96%. The VGG-19BN model also achieved the best performance on the external test set, with an accuracy of 95.10%, precision of 100%, recall of 83.87%, specificity of 93.42%, and F1 score of 91.23%. The best performance by human experts on the external test set yielded values of accuracy, precision, recall, specificity, and F1 scores of 77.45%, 60.53%, 77.42%, 83.10%, and 66.67%, respectively. The F1 score of each human expert was lower than those of the EfficientNet-b3 (84.21%), ResNet-50 (74.51%), VGG-16 (85.71%), VGG-16BN (85.71%), VGG-19 (83.02%), and VGG-19BN (91.23%) models. CONCLUSION: The results showed that facial recognition technology can be used to accurately diagnose patients with WBS. Facial recognition models based on VGG-19BN can play a crucial role in its clinical diagnosis. Their performance can be improved by expanding the size of the training dataset, optimizing the CNN architectures applied, and modifying them with a variable cosine learning rate. WHAT IS KNOWN: • The facial gestalt of WBS, often described as "elfin," includes a broad forehead, periorbital puffiness, a flat nasal bridge, full cheeks, and a small chin. • Recent studies have demonstrated the potential of deep convolutional neural networks for facial recognition as a diagnostic tool for WBS. WHAT IS NEW: • This study develops six models of facial recognition, EfficientNet-b3, ResNet-50, VGG-16, VGG-16BN, VGG-19, and VGG-19BN, to improve WBS diagnosis. • The VGG-19BN model achieved the best performance, with an accuracy of 95.10% and specificity of 93.42%. The facial recognition model based on VGG-19BN can play a crucial role in the clinical diagnosis of WBS.

The Regulatory Effects of Taurine on Neurogenesis and Apoptosis of Neural Stem Cells in the Hippocampus of Rats.

The promotion of neurogenesis from neural stem cells (NSCs) in the hippocampus was found to be the most fundamental and effective therapy for depression. Our previous studies proved an antidepressive effect of taurine on rats, but the exact mechanism remains unclear. In this study, CUMS model was established in rats, and NSCs were cultured in vitro to investigate the protective effect and mechanisms of taurine on neurogenesis and apoptosis in CUMS rats and glutamate-injured NSCs. The results showed that ki67-positive cells were significantly increased by taurine, while apoptosis in the DG of CUMS rats was significantly inhibited by taurine. In vitro study, cell viability, Brdu+, ß-tubulin III+, and GFAP+ cells in taurine-treated cells were significantly higher, while apoptosis rate was lower than the glutamate-treated cells. The protein expression of BDNF and its downstream pathway was upregulated by taurine administration. The results demonstrated that taurine can increase the survival, proliferation, and differentiation of NSCs; this protective effect of taurine may be due to the upregulation of BDNF/ERK/CREB signaling pathway. On the other hand, taurine can also inhibit abnormal apoptosis induced by CUMS or glutamate, the mechanism of which may be due to its antioxidative ability.

Active Nrf2 signaling flexibly regulates HO-1 and NQO-1 in hypoxic Gansu Zokor (Eospalax cansus).

Gansu zokor (Eospalax cansus) is a typical subterranean rodent species with resistance to ambient hypoxia. The nuclear factor erythroid 2-related factor 2 (Nrf2) signaling plays a key role in regulating redox homeostasis. However, little is known about the regulation of Nrf2 signaling in Gansu zokor. We exposed Gansu zokors and SD rats to chronic hypoxia (44 h at 10.5% O2) or acute hypoxia (6 h at 6.5% O2) andmeasured the activities of heme oxygenase-1 (HO-1) and NAD(P)H quinone oxidoreductase-1 (NQO-1)，gene expression of HO-1, NQO-1, Nrf2, Kelch-like ECH-associated protein-1 (KEAP1), and ß-transducin repeat-containing protein (ß-TRCP) in the brain and liver. We found that Gansu zokor increased the NQO-1 protein content and activity, HO-1 protein content in the brain, and increased HO-1 activity and mRNA level, NQO-1 activity and protein content in the liver by up regulating Nrf2 gene expression under chronic hypoxia. Although acute hypoxia enhanced the expression of Nrf2 gene, only the level of HO-1 mRNA in the liver increased. Besides, the HO-1 and NQO-1 genes in the brain, HO-1 genes and NQO-1 mRNA in the Gansu zokor liver were significantly higher than those in SD rats under normoxia. Negative regulators of Nrf2 signaling were tissue specific: KEAP1 protein decreased in the brain, and ß-TRCP decreased in the liver. The Nrf2 signaling and expression of downstream antioxidant enzymes were different under different oxygen concentrations, reflecting the flexible characteristics of Gansu zokor to deal with the hypoxic environment.

Evolution of Precipitated Phases during Creep of G115/Sanicro25 Dissimilar Steel Welded Joints.

This paper studies the evolution of the microstructure and microhardness in the G115 side of the G115/Sanicro25 dissimilar steel welded joint during the creep process. The joints were subjected to creep tests at 675 °C, 140 MPa, 120 MPa and 100 MPa. A scanning electron microscope equipped with an electron backscattering diffraction camera was used to observe the microstructure of the cross-section. The fracture position of the joint and the relationship between the cavity and the second phase were analyzed. The microstructure morphology of the fracture, the base metal and the thread end was compared and the composition and size of the Laves phase were statistically analyzed. The results show that the fracture locations are all located in the fine-grain heat-affected zone (FGHAZ) zone, and the microstructure near the fracture is tempered martensite. There are two kinds of cavity in the fracture section. Small cavities sprout adjacent to the Laves phase; while large cavities occupy the entire prior austenite grain, there are more precipitated phases around the cavities. The Laves phase nucleates at the boundary of the M23C6 carbide and gradually grows up by merging the M23C6 carbide. Creep accelerates the coarsening rate of the Laves phase; aging increases the content of W element in the Laves phase.