Search

To develop a deep learning model to accurately detect anterior cruciate ligament (ACL) ruptures on magnetic resonance imaging (MRI) and to evaluate its effect on the diagnostic accuracy and efficiency of clinicians. A training dataset was built from MRIs acquired from January 2017 to June 2021, including patients with knee symptoms, irrespective of ACL ruptures. An external validation dataset was built from MRIs acquired from January 2021 to June 2022, including patients who underwent knee arthroscopy or arthroplasty. Patients with fractures or prior knee surgeries were excluded in both datasets. Subsequently, a deep learning model was developed and validated using these datasets. Clinicians of varying expertise levels in sports medicine and radiology were recruited, and their capacities in diagnosing ACL injuries in terms of accuracy and diagnosing time were evaluated both with and without artificial intelligence (AI) assistance. A deep learning model was developed based on the training dataset of 22,767 MRIs from 5 centers and verified with external validation dataset of 4,086 MRIs from 6 centers. The model achieved an area under the receiver operating characteristic curve of 0.987 and a sensitivity and specificity of 95.1%. Thirty-eight clinicians from 25 centers were recruited to diagnose 3,800 MRIs. The AI assistance significantly improved the accuracy of all clinicians, exceeding 96%. Additionally, a notable reduction in diagnostic time was observed. The most significant improvements in accuracy and time efficiency were observed in the trainee groups, suggesting that AI support is particularly beneficial for clinicians with moderately limited diagnostic expertise. This deep learning model demonstrated expert-level diagnostic performance for ACL ruptures, serving as a valuable tool to assist clinicians of various specialties and experience levels in making accurate and efficient diagnoses. Level III, retrospective comparative case series. [ABSTRACT FROM AUTHOR]

Abstract: Titanomagnetite concentrates and pre-oxidized titanomagnetite concentrates were reduced isothermally at 1000–1200°C by pulverized coal. XRD, SEM and EDS were used to characterize the samples. The influence of reduction conditions on the metallization degree of the samples, such as reduction temperature, C/Fe molar ratio, pre-oxidation and additives were studied. It was found that the pre-oxidation and additives played a considerable role in the metallization degree of titanomagnetite concentrates. During the pre-oxidation of titanomagnetite concentrates in air, the magnetite was oxidized to hematite and ilmenite was oxidized to hematite–ilmenite solid solution, hematite and TiO2. The pre-oxidation destroyed the crystal lattice of raw titanomagnetite concentrates and formed pores in the particles, which accelerated the reduction process. The effect of different additives on the metallization degree of pre-oxidized titanomagnetite concentrates was also discussed. The results show that when 1.5wt.% Na2CO3 is used as an additive, the metallization degree of pre-oxidized titanomagnetite concentrates reaches 96.4%, after heating for 1h at 1200°C. The final reduced sample was composed of metallic iron, pseudobrookite solid solution and TiO2. [Copyright &y& Elsevier]

Abstract: Typical floorplanning concerns a series of objectives, such as area, wirelength, and routability, etc., with various aspect ratios of modules in a free-outline regime. However, in a hierarchical design flow for very large ASICs and SoCs, a floorplan can be completely useless for a situation where its outline is dissatisfied. In this paper, we study the fixed-outline floorplanning problem that is more applicable to the hierarchical design style. We develop an efficient algorithm based on robust evolutionary search and achieve substantially improved success rate. We also propose a new approach to handle soft modules to further adjust the generated floorplan to fit into the prescribed chip outline. The effectiveness of our methods is demonstrated on several large cases of MCNC and GSRC benchmarks. [Copyright &y& Elsevier]

Butterfly valve is widely used to transport cryogenic medium such as liquid natural gas (LNG), liquid nitrogen and so on. When the pressure of cryogenic fluid is lower than the saturated vapor pressure corresponding to the local temperature, the cryogenic fluid will produce the phase transformation from liquid to gas, which is called as cryogenic cavitation. Cavitation phenomenon is the main cause of cavitation erosion, vibration and noise, which seriously affects the stable operation of the system and the lifetime of the valves. Cryogenic medium is more easily cavitated in the process of transportation and regulation due to its unique thermal sensitivity. In order to explore the evolution mechanism of cryogenic cavitation through butterfly valves, numerical simulations were carried out to study the dynamic evolution of cryogenic cavitation through a butterfly valve model at different valve opening degrees. By considering the thermal effect of cryogenic medium, the traditional cavitation model is modified and verified by experimental results. The evolution including generation, development and collapse of cryogenic cavitation is observed and discussed in details at each valve opening degree. The relationship of cryogenic cavitation and vortex structure is revealed and entropy production is obtained to indicate the intensity of dynamic evolution of cryogenic cavitation through butterfly valve. • A modified cavitation model was proposed and verified by experimental results. • The periodic evolution of cryogenic cavitation was observed and discussed in details. • The spatial and temporal relationship between cryogenic cavitation and vortex was revealed. • The irreversible energy loss induced by cryogenic cavitation was investigated. [ABSTRACT FROM AUTHOR]