Objective To develope a deep learning algorithm for pathological classification of chronic gastritis and assess its performance using whole-slide images(WSIs).Methods We retrospectively collected 1,250 gastric biopsy ...Objective To develope a deep learning algorithm for pathological classification of chronic gastritis and assess its performance using whole-slide images(WSIs).Methods We retrospectively collected 1,250 gastric biopsy specimens(1,128 gastritis,122 normal mucosa)from PLA General Hospital.The deep learning algorithm based on DeepLab v3(ResNet-50)architecture was trained and validated using 1,008 WSIs and 100 WSIs,respectively.The diagnostic performance of the algorithm was tested on an independent test set of 142 WSIs,with the pathologists’consensus diagnosis as the gold standard.Results The receiver operating characteristic(ROC)curves were generated for chronic superficial gastritis(CSuG),chronic active gastritis(CAcG),and chronic atrophic gastritis(CAtG)in the test set,respectively.The areas under the ROC curves(AUCs)of the algorithm for CSuG,CAcG,and CAtG were 0.882,0.905 and 0.910,respectively.The sensitivity and specificity of the deep learning algorithm for the classification of CSuG,CAcG,and CAtG were 0.790 and 1.000(accuracy 0.880),0.985 and 0.829(accuracy 0.901),0.952 and 0.992(accuracy 0.986),respectively.The overall predicted accuracy for three different types of gastritis was 0.867.By flagging the suspicious regions identified by the algorithm in WSI,a more transparent and interpretable diagnosis can be generated.Conclusion The deep learning algorithm achieved high accuracy for chronic gastritis classification using WSIs.By pre-highlighting the different gastritis regions,it might be used as an auxiliary diagnostic tool to improve the work efficiency of pathologists.展开更多
Cardiovascular diseases(CVDs)are major disease burdens with high mortality worldwide.Early prediction of cardiovascular events can reduce the incidence of acute myocardial infarction and decrease the mortality rates o...Cardiovascular diseases(CVDs)are major disease burdens with high mortality worldwide.Early prediction of cardiovascular events can reduce the incidence of acute myocardial infarction and decrease the mortality rates of patients with CVDs.The pathological mechanisms and multiple factors involved in CVDs are complex;thus,traditional data analysis is insufficient and inefficient to manage multidimensional data for the risk prediction of CVDs and heart attacks,medical image interpretations,therapeutic decision-making,and disease prognosis prediction.Meanwhile,traditional Chinese medicine(TCM)has been widely used for treating CVDs.TCM offers unique theoretical and practical applications in the diagnosis and treatment of CVDs.Big data have been generated to investigate the scientific basis of TCM diagnostic methods.TCM formulae contain multiple herbal items.Elucidating the complicated interactions between the active compounds and network modulations requires advanced data-analysis capability.Recent progress in artificial intelligence(AI)technology has allowed these challenges to be resolved,which significantly facilitates the development of integrative diagnostic and therapeutic strategies for CVDs and the understanding of the therapeutic principles of TCM formulae.Herein,we briefly introduce the basic concept and current progress of AI and machine learning(ML)technology,and summarize the applications of advanced AI and ML for the diagnosis and treatment of CVDs.Furthermore,we review the progress of AI and ML technology for investigating the scientific basis of TCM diagnosis and treatment for CVDs.We expect the application of AI and ML technology to promote synergy between western medicine and TCM,which can then boost the development of integrative medicine for the diagnosis and treatment of CVDs.展开更多
With the rapid development of artificial intelligence techniques such as neural networks,data-driven machine learning methods are popular in improving and constructing turbulence models.For high Reynolds number turbul...With the rapid development of artificial intelligence techniques such as neural networks,data-driven machine learning methods are popular in improving and constructing turbulence models.For high Reynolds number turbulence in aerodynamics,our previous work built a data-driven model applicable to subsonic airfoil flows with different free stream conditions.The results calculated by the proposed model are encouraging.In this work,we aim to model the turbulence of transonic wing flows with fully connected deep neural networks,where there is less research at present.The proposed model is driven by two flow cases of the ONERA(Office National d'Etudes et de Recherches Aerospatiales)wing and coupled with the Navier-Stokes equation solver.Four subcritical and transonic benchmark cases of different wings are used to evaluate the model performance.The iteration process is stable,and final convergence is achieved.The proposed model can be used to surrogate the traditional Reynolds averaged Navier-Stokes turbulence model.Compared with the data calculated by the Spallart-Allmaras model,the results show that the proposed model can be well generalized to the test cases.The mean relative error of the drag coefficient at different sections is below 4%for each case.This work demonstrates that modeling turbulence by data-driven methods is feasible and that our modeling pattern is effective.展开更多
文摘Objective To develope a deep learning algorithm for pathological classification of chronic gastritis and assess its performance using whole-slide images(WSIs).Methods We retrospectively collected 1,250 gastric biopsy specimens(1,128 gastritis,122 normal mucosa)from PLA General Hospital.The deep learning algorithm based on DeepLab v3(ResNet-50)architecture was trained and validated using 1,008 WSIs and 100 WSIs,respectively.The diagnostic performance of the algorithm was tested on an independent test set of 142 WSIs,with the pathologists’consensus diagnosis as the gold standard.Results The receiver operating characteristic(ROC)curves were generated for chronic superficial gastritis(CSuG),chronic active gastritis(CAcG),and chronic atrophic gastritis(CAtG)in the test set,respectively.The areas under the ROC curves(AUCs)of the algorithm for CSuG,CAcG,and CAtG were 0.882,0.905 and 0.910,respectively.The sensitivity and specificity of the deep learning algorithm for the classification of CSuG,CAcG,and CAtG were 0.790 and 1.000(accuracy 0.880),0.985 and 0.829(accuracy 0.901),0.952 and 0.992(accuracy 0.986),respectively.The overall predicted accuracy for three different types of gastritis was 0.867.By flagging the suspicious regions identified by the algorithm in WSI,a more transparent and interpretable diagnosis can be generated.Conclusion The deep learning algorithm achieved high accuracy for chronic gastritis classification using WSIs.By pre-highlighting the different gastritis regions,it might be used as an auxiliary diagnostic tool to improve the work efficiency of pathologists.
基金The Health and Medical Research Fund,Hong Kong(17181811)。
文摘Cardiovascular diseases(CVDs)are major disease burdens with high mortality worldwide.Early prediction of cardiovascular events can reduce the incidence of acute myocardial infarction and decrease the mortality rates of patients with CVDs.The pathological mechanisms and multiple factors involved in CVDs are complex;thus,traditional data analysis is insufficient and inefficient to manage multidimensional data for the risk prediction of CVDs and heart attacks,medical image interpretations,therapeutic decision-making,and disease prognosis prediction.Meanwhile,traditional Chinese medicine(TCM)has been widely used for treating CVDs.TCM offers unique theoretical and practical applications in the diagnosis and treatment of CVDs.Big data have been generated to investigate the scientific basis of TCM diagnostic methods.TCM formulae contain multiple herbal items.Elucidating the complicated interactions between the active compounds and network modulations requires advanced data-analysis capability.Recent progress in artificial intelligence(AI)technology has allowed these challenges to be resolved,which significantly facilitates the development of integrative diagnostic and therapeutic strategies for CVDs and the understanding of the therapeutic principles of TCM formulae.Herein,we briefly introduce the basic concept and current progress of AI and machine learning(ML)technology,and summarize the applications of advanced AI and ML for the diagnosis and treatment of CVDs.Furthermore,we review the progress of AI and ML technology for investigating the scientific basis of TCM diagnosis and treatment for CVDs.We expect the application of AI and ML technology to promote synergy between western medicine and TCM,which can then boost the development of integrative medicine for the diagnosis and treatment of CVDs.
基金supported by the National Natural Science Foundation of China(Grant Nos.92152301,and 91852115)the National Numerical Wind tunnel Project(Grand No.NNW2018-ZT1B01).
文摘With the rapid development of artificial intelligence techniques such as neural networks,data-driven machine learning methods are popular in improving and constructing turbulence models.For high Reynolds number turbulence in aerodynamics,our previous work built a data-driven model applicable to subsonic airfoil flows with different free stream conditions.The results calculated by the proposed model are encouraging.In this work,we aim to model the turbulence of transonic wing flows with fully connected deep neural networks,where there is less research at present.The proposed model is driven by two flow cases of the ONERA(Office National d'Etudes et de Recherches Aerospatiales)wing and coupled with the Navier-Stokes equation solver.Four subcritical and transonic benchmark cases of different wings are used to evaluate the model performance.The iteration process is stable,and final convergence is achieved.The proposed model can be used to surrogate the traditional Reynolds averaged Navier-Stokes turbulence model.Compared with the data calculated by the Spallart-Allmaras model,the results show that the proposed model can be well generalized to the test cases.The mean relative error of the drag coefficient at different sections is below 4%for each case.This work demonstrates that modeling turbulence by data-driven methods is feasible and that our modeling pattern is effective.