Development and Validation of a Deep Learning-Based Model Using Computed Tomography Imaging for Predicting Disease Severity of Coronavirus Disease 2019.

OBJECTIVES: Coronavirus disease 2019 (COVID-19) is sweeping the globe and has resulted in infections in millions of people. Patients with COVID-19 face a high fatality risk once symptoms worsen; therefore, early identification of severely ill patients can enable early intervention, prevent disease progression, and help reduce mortality. This study aims to develop an artificial intelligence-assisted tool using computed tomography (CT) imaging to predict disease severity and further estimate the risk of developing severe disease in patients suffering from COVID-19. MATERIALS AND METHODS: Initial CT images of 408 confirmed COVID-19 patients were retrospectively collected between January 1, 2020 and March 18, 2020 from hospitals in Honghu and Nanchang. The data of 303 patients in the People's Hospital of Honghu were assigned as the training data, and those of 105 patients in The First Affiliated Hospital of Nanchang University were assigned as the test dataset. A deep learning based-model using multiple instance learning and residual convolutional neural network (ResNet34) was developed and validated. The discrimination ability and prediction accuracy of the model were evaluated using the receiver operating characteristic curve and confusion matrix, respectively. RESULTS: The deep learning-based model had an area under the curve (AUC) of 0.987 (95% confidence interval [CI]: 0.968-1.00) and an accuracy of 97.4% in the training set, whereas it had an AUC of 0.892 (0.828-0.955) and an accuracy of 81.9% in the test set. In the subgroup analysis of patients who had non-severe COVID-19 on admission, the model achieved AUCs of 0.955 (0.884-1.00) and 0.923 (0.864-0.983) and accuracies of 97.0 and 81.6% in the Honghu and Nanchang subgroups, respectively. CONCLUSION: Our deep learning-based model can accurately predict disease severity as well as disease progression in COVID-19 patients using CT imaging, offering promise for guiding clinical treatment.

Application of CCG Sensors to a High-Temperature Structure Subjected to Thermo-Mechanical Load.

This paper presents a simple methodology to perform a high temperature coupled thermo-mechanical test using ultra-high temperature ceramic material specimens (UHTCs), which are equipped with chemical composition gratings sensors (CCGs). The methodology also considers the presence of coupled loading within the response provided by the CCG sensors. The theoretical strain of the UHTCs specimens calculated with this technique shows a maximum relative error of 2.15% between the analytical and experimental data. To further verify the validity of the results from the tests, a Finite Element (FE) model has been developed to simulate the temperature, stress and strain fields within the UHTC structure equipped with the CCG. The results show that the compressive stress exceeds the material strength at the bonding area, and this originates a failure by fracture of the supporting structure in the hot environment. The results related to the strain fields show that the relative error with the experimental data decrease with an increase of temperature. The relative error is less than 15% when the temperature is higher than 200 °C, and only 6.71% at 695 °C.

ZrB2-CNTs Nanocomposites Fabricated by Spark Plasma Sintering.

ZrB2-based nanocomposites with and without carbon nanotubes (CNTs) as reinforcement were prepared at 1600 °C by spark plasma sintering. The effects of CNTs on the microstructure and mechanical properties of nano-ZrB2 matrix composites were studied. The results indicated that adding CNTs can inhibit the abnormal grain growth of ZrB2 grains and improve the fracture toughness of the composites. The toughness mechanisms were crack deflection, crack bridging, debonding, and pull-out of CNTs. The experimental results of the nanograined ZrB2-CNTs composites were compared with those of the micro-grained ZrB2-CNTs composites. Due to the small size and surface effects, the nanograined ZrB2-CNTs composites exhibited stronger mechanical properties: the hardness, flexural strength and fracture toughness were 18.7 ± 0.2 GPa, 1016 ± 75 MPa, and 8.5 ± 0.4 MPa·m1/2, respectively.

Neutron irradiation and post annealing effect on sapphire by positron annihilation.

Sapphire single crystals grown by an improved Kyropoulos-like method are irradiated by fast neutron flux. The irradiated doses of neutron are 10(18) and 10(19)n/cm(2). The infrared transmission spectra of sapphire were studied before and after irradiation. The irradiated samples were annealed at 200, 400, 600, 800 and 1000 degrees C for 10min in ambient atmosphere. Positron annihilation studies have been carried out before and after neutron irradiation. The experimentally measured positron lifetime in the pristine specimen is 143ps. There were aluminum vacancies produced in sapphire crystals after neutron irradiation. The positron lifetime increased with the dose of neutron flux. A longer value tau(2) was found after annealing at 600 degrees C, which indicated vacancies were aggregated with each other. The second long-time component tau(2) has been found to increase with the annealing temperature. There was almost no change in peak position of the CDB spectra after neutron irradiation and isothermal annealing. The chemical environment of core in sapphire did not change greatly after neutron irradiation.