Dementia of Alzheimer's type (DAT) is associated with devastating and irreversible cognitive decline. Predicting which patients with mild cognitive impairment (MCI) will progress to DAT is an ongoing challenge in the field. We developed a deep learning model to predict conversion from MCI to DAT. Structural magnetic resonance imaging scans were used as input to a 3-dimensional convolutional neural network. The 3-dimensional convolutional neural network was trained using transfer learning; in the source task, normal control and DAT scans were used to pretrain the model. This pretrained model was then retrained on the target task of classifying which MCI patients converted to DAT. Our model resulted in 82.4% classification accuracy at the target task, outperforming current models in the field. Next, we visualized brain regions that significantly contribute to the prediction of MCI conversion using an occlusion map approach. Contributory regions included the pons, amygdala, and hippocampus. Finally, we showed that the model's prediction value is significantly correlated with rates of change in clinical assessment scores, indicating that the model is able to predict an individual patient's future cognitive decline. This information, in conjunction with the identified anatomical features, will aid in building a personalized therapeutic strategy for individuals with MCI. Crown Copyright (C) 2020 Published by Elsevier Inc. All rights reserved.

Genetic factors play a key role in the pathogenesis of autoimmune diseases, whereas the disease-causing variants remain largely unknown. Herein, we performed an exome-wide association study of systemic sclerosis in a Han Chinese population. In the discovery stage, 527 patients with systemic sclerosis and 5,024 controls were recruited and genotyped. In the validation study, an independent sample set of 479 patients and 1,096 controls were examined. In total, we found that four independent signals reached genome-wide significance. Among them, rs7574865 (Pcombined = 3.87 x 10(-12)) located within signal transducer and activator of transcription 4 gene was identified previously using samples of European ancestry. Additionally, another signal including three SNPs in linkage disequilibrium might be unreported susceptibility loci located in the epidermis differentiation complex region. Furthermore, two SNPs located within exon 3 of IGHM (rs45471499, Pcombined = 1.15 x 10(-9)) and upstream of LRP2BP (rs4317244, Pcombined = 4.17 x 10(-8)) were found. Moreover, rs4317244 was identified as an expression quantitative trait locus for LRP2BP that regulates tight junctions, cell cycle, and apoptosis in endothelial cell lines. Collectively, our results revealed three signals associated with systemic sclerosis in Han Chinese and suggested the importance of LRP2BP in systemic sclerosis pathogenesis. Given the limited sample size and discrepancies between previous results and our study, further studies in multiethnic populations are required for verification.

Excessive activation of CD4(+) T cells and T helper type (Th) 17/Th1 cell differentiation are critical events in psoriasis pathogenesis, but the associated molecular mechanism is still unclear. Here, using quantitative proteomics analysis, we found that cyclin-dependent kinase 7 (CDK7) expression was markedly increased in CD4(+) T cells from patients with psoriasis compared with healthy controls and was positively correlated with psoriasis severity. Meanwhile, genetic or pharmacological inhibition of CDK7 ameliorated the severity of psoriasis in the imiquimod-induced psoriasis-like mouse model and suppressed CD4(+) T-cell activation as well as Th17/Th1 cell differentiation in vivo and in vitro. Furthermore, the CDK7 inhibitor also reduced the enhanced glycolysis of CD4(+) T cells from patients with psoriasis. Proinflammatory cytokine IL-23 induced increased CDK7 expression in CD4(+) T cells and activated the protein kinase B/mTOR/HIF-1 alpha signaling pathway, enhancing glycolytic metabolism. Correspondingly, CDK7 inhibition significantly impaired IL-23-induced glycolysis via the protein kinase B/mTOR/HIF-1 alpha pathway. In summary, this study shows that CDK7 promotes CD4(+) T-cell activation and Th17/Th1 cell differentiation by regulating glycolysis, thus contributing to the pathogenesis of psoriasis. Targeting CDK7 might be a promising immunosuppressive strategy to control skin inflammation mediated by IL-23.

Accurate segmentation of the optic disc (OD) regions from colour fundus images is a critical procedure for computer-aided diagnosis of glaucoma. We present a novel deep learning network to automatically identify the OD regions. On the basis of the classical U-Net framework, we define a unique sub-network and a decoding convolutional block. The sub-network is used to preserve important textures and facilitate their detections, while the decoding block is used to improve the contrast of the regions-of-interest with their background. We integrate these two components into the classical U-Net framework to improve the accuracy and reliability of segmenting the OD regions depicted on colour fundus images. We train and evaluate the developed network using three publicly available datasets (i.e., MESSIDOR, ORIGA, and REFUGE). The results on an independent testing set (n = 1,970 images) show a segmentation performance with an average Dice similarity coefficient (DSC), intersection over union (IOU), and Matthew's correlation coefficient (MCC) of 0.9377, 0.8854, and 0.9383 when trained on the global field-of-view images, respectively, and 0.9735, 0.9494, and 0.9594 when trained on the local disc region images. When compared with the other three classical networks (i.e., the U-Net, M-Net, and Deeplabv3) on the same testing datasets, the developed network demonstrates a relatively higher performance. (c) 2021 Elsevier Ltd. All rights reserved.

Accurate segmentation of corneal layers depicted on optical coherence tomography (OCT) images is very helpful for quantitatively assessing and diagnosing corneal diseases (e.g., keratoconus and dry eye). In this study, we presented a novel boundary-guided convolutional neural network (CNN) architecture (BGCNN) to simultaneously extract different corneal layers and delineate their boundaries. The developed BG-CNN architecture used three convolutional blocks to construct two network modules on the basis of the classical U-Net network. We trained and validated the network on a dataset consisting of 1,712 OCT images acquired on 121 subjects using a 10-fold cross-validation method. Our experiments showed an average dice similarity coefficient (DSC) of 0.9691, an intersection over union (IOU) of 0.9411, and a Hausdorff distance (HD) of 7.4423 pixels. Compared with several other classical networks, namely U Net, Attention U-Net, Asymmetric U-Net, BiO-Net, CE-Net, CPFnte, M-Net, and Deeplabv3, on the same dataset, the developed network demonstrated a promising performance, suggesting its unique strength in segmenting corneal layers depicted on OCT images. (c) 2021 Elsevier Ltd. All rights reserved.

Compared to single-crystal SiC, nanocrystalline SiC with high densities of stacking faults has been reported to be much more resistant to amorphization under self-ion and electron irradiations. This study examines H-2(+) ion irradiation-induced amorphization in nanocrystalline 3C-SiC with dense stacking faults using transmission electron microscopy. The results show that full amorphization at room temperature occurs at a comparable dose to that for its single-crystal SiC counterpart under the identical irradiation conditions. Both materials are amorphized as a result of local damage accumulation. The formation of the nucleation sites for amorphization is not appreciably affected by the presence of stacking faults and grain boundaries. The behavior may be attributed to the significant chemical effects of the implanted H atoms that may completely immobilize the point defects in SiC at room temperature. The results suggest cautions be excised to use nanocrystalline SiC materials in high H irradiation environment at room temperature. Further studies of the H behavior at elevated temperatures are warranted.