Objective: The aim of this study was to analyze the CT and pathology features of pulmonary lymphoma and to improve the understanding of this disease. Methods: The CT findings of 23 cases with pulmonary lymphoma were r...Objective: The aim of this study was to analyze the CT and pathology features of pulmonary lymphoma and to improve the understanding of this disease. Methods: The CT findings of 23 cases with pulmonary lymphoma were retrospectively analyzed and correlated with histopathology. Results: Of the 23 cases with pulmonary lymphoma, there were Hodgkin lymphoma (5 cases) and non-Hodgkin lymphoma (18 cases). Multiple lesions were assessed in 16 cases and single lesion in 7 cases. The imaging findings were classified into 3 types: lobar and segmental involvement type (9/23 cases, 39.13%), nodular or mass-like involvement type (8/23 cases, 34.78%) and mixed type (6/23 cases, 26.09%). Air bronchogram sign (14/23 cases, 60.8%), CT angiogram sign (12/23 cases, 52.17%), ground glass opacity nodules (3/23 cases, 13.04%) and lesion across pulmonary lobes (4/23,17.39%) were the characteristic features of pulmonary lymphoma. Conclusion: Relative characteristic CT features of pulmonary lymphoma could be revealed, which shows clinical significance in the diagnosis of the disease.展开更多
The discovery and study of skyrmion materials play an important role in basic frontier physics research and future information technology.The database of 196 materials,including 64 skyrmions,was established and predic...The discovery and study of skyrmion materials play an important role in basic frontier physics research and future information technology.The database of 196 materials,including 64 skyrmions,was established and predicted based on machine learning.A variety of intrinsic features are classified to optimize the model,and more than a dozen methods had been used to estimate the existence of skyrmion in magnetic materials,such as support vector machines,k-nearest neighbor,and ensembles of trees.It is found that magnetic materials can be more accurately divided into skyrmion and non-skyrmion classes by using the classification of electronic layer.Note that the rare earths are the key elements affecting the production of skyrmion.The accuracy and reliability of random undersampling bagged trees were 87.5%and 0.89,respectively,which have the potential to build a reliable machine learning model from small data.The existence of skyrmions in LaBaMnO is predicted by the trained model and verified by micromagnetic theory and experiments.展开更多
文摘Objective: The aim of this study was to analyze the CT and pathology features of pulmonary lymphoma and to improve the understanding of this disease. Methods: The CT findings of 23 cases with pulmonary lymphoma were retrospectively analyzed and correlated with histopathology. Results: Of the 23 cases with pulmonary lymphoma, there were Hodgkin lymphoma (5 cases) and non-Hodgkin lymphoma (18 cases). Multiple lesions were assessed in 16 cases and single lesion in 7 cases. The imaging findings were classified into 3 types: lobar and segmental involvement type (9/23 cases, 39.13%), nodular or mass-like involvement type (8/23 cases, 34.78%) and mixed type (6/23 cases, 26.09%). Air bronchogram sign (14/23 cases, 60.8%), CT angiogram sign (12/23 cases, 52.17%), ground glass opacity nodules (3/23 cases, 13.04%) and lesion across pulmonary lobes (4/23,17.39%) were the characteristic features of pulmonary lymphoma. Conclusion: Relative characteristic CT features of pulmonary lymphoma could be revealed, which shows clinical significance in the diagnosis of the disease.
基金This work was supported by the National Natural Science Foundation of China(grant nos.52001012,52088101,and 51925605)the National Key Research and Development Program of China(2021YFB3501202)+6 种基金the Beijing Natural Science Foundation(grant no.2214070)the National Key Research and Development Program of China(2021YFB3501504,2022YFB3505201,2020YFA0711502,and 2019YFA0704900)the National Natural Science Foundation of China(grant nos.92263202 and 51971240)the Heye Health Technology Chong Ming Project(HYCMP-2022002 and HYCMP-2022003)the Natural Science Foundation of Inner Mongolia Autonomous Region(2019MS05040)the Strategic Priority Research Program B(XDB33030200)the Key Program of the Chinese Academy of Sciences(CAS)。
文摘The discovery and study of skyrmion materials play an important role in basic frontier physics research and future information technology.The database of 196 materials,including 64 skyrmions,was established and predicted based on machine learning.A variety of intrinsic features are classified to optimize the model,and more than a dozen methods had been used to estimate the existence of skyrmion in magnetic materials,such as support vector machines,k-nearest neighbor,and ensembles of trees.It is found that magnetic materials can be more accurately divided into skyrmion and non-skyrmion classes by using the classification of electronic layer.Note that the rare earths are the key elements affecting the production of skyrmion.The accuracy and reliability of random undersampling bagged trees were 87.5%and 0.89,respectively,which have the potential to build a reliable machine learning model from small data.The existence of skyrmions in LaBaMnO is predicted by the trained model and verified by micromagnetic theory and experiments.