Generally speaking,the precursors of ozone(O_(3)),nitrogen oxides and volatile organic compounds are very low in desert areas due to the lack of anthropogenic emissions and natural emissions,and thus O_(3)concentratio...Generally speaking,the precursors of ozone(O_(3)),nitrogen oxides and volatile organic compounds are very low in desert areas due to the lack of anthropogenic emissions and natural emissions,and thus O_(3)concentrations are relatively low.However,high summer background concentrations of about 100μg/m^(3)or 60 ppb were found in the Alxa Desert in the highland of northwest China based on continuous summer observations from 2019 to 2021,which was higher than the most of natural background areas or clean areas in world for summer O_(3)background concentrations.The high O_(3)background concentrations were related to surface features and altitude.Heavy-intensity anthropogenic activity areas in desert areas can cause increased O_(3)concentrations or pollution,but also generated O_(3)depleting substances such as nitrous oxide,which eventually reduced the regional O_(3)baseline values.Nitrogen dioxide(NO2)also had a dual effect on O_(3)generation,showing promotion at low concentrations and inhibition at high concentrations.In addition,sand-dust weather reduced O_(3)clearly,but O_(3)eventually stabilized around the background concentration values and did not vary with sand-dust particulate matter.展开更多
PI3 kinases are important for KIT signaling and KIT mutants mediated cell transformation.In order to know the difference of PI3 kinase isoforms p110αand p110δin the signaling of wild-type KIT and the often occurred ...PI3 kinases are important for KIT signaling and KIT mutants mediated cell transformation.In order to know the difference of PI3 kinase isoforms p110αand p110δin the signaling of wild-type KIT and the often occurred KIT mutation D816V in hematopoietic malignancy mastocytosis,the predominant PI3 kinase isoform p110δin hematopoietic tissues was knocked out in hematopoietic cells.We found that loss of p110δexpression dramatically inhibits PI3 kinase activation mediated by both wild-type KIT and KIT/D816V.By over expression of p110αin p110δknock out cells,wild-type KIT mediated PI3 kinase activation was not changed while over expression of p110δincreased PI3 kinase activation.Similarly,in KIT/D816V expressing cells without p110δexpression,over expression of p110δbut not p110αrestored PI3 kinase activation.In agreement with the signaling results,cell proliferation,cell survival and cell cycle assay further showed that over expression of p110δbut not p110αin p110δknock out cells increases both wild-type KIT and KIT/D816V mediated cell survival and proliferation.These results suggested that p110δplays a more important role than p110αin KIT signaling and KIT mutant mediated cell transformation in hematopoietic cells.展开更多
Purpose: To develop a fast landmark-based deformable registration method to capture the soft tissue transformation between the planning 3D CT images and treatment 3D cone-beam CT (CBCT) images for the adaptive externa...Purpose: To develop a fast landmark-based deformable registration method to capture the soft tissue transformation between the planning 3D CT images and treatment 3D cone-beam CT (CBCT) images for the adaptive external beam radiotherapy (EBRT). Method and Materials: The developed method was based on a global-to-local landmark-based deformable registration algorithm. The landmarks were first acquired by applying a fast segmentation method using the active shape model. The global registration method was applied to establish a registration framework. The Laplacian surface deformation (LSD) and Laplacian surface optimization (LSO) method were then employed for local deformation and remeshing respectively to reach an optimal registration solution. In LSD, the deformed mesh is generated by minimizing the quadratic energy to keep the shape and to move control points to the target position. In LSO, a mesh is reconstructed by minimizing the quadratic energy to smooth the object by minimizing the difference while keeping the landmarks unchanged. The method was applied on 8 EBRT prostate datasets. The distance and volume based estimators were used to evaluate the results. The target volumes delineated by physicians were used as gold standards in the evaluation. Results: The entire segmentation and registration processing time was within 1 minute for all the datasets. The mean distance estimators ranged from 0.43 mm to 2.23 mm for the corresponding model points between the treatment CBCT images and the registered planning images. The mean overlap ratio ranged from 85.5% to 93.2% of the prostate volumes after registration. These results demonstrated reasonably good agreement between the developed method and the gold standards. Conclusion: A novel and fast landmark-based deformable registration method is developed to capture the soft tissue transformation between the planning and treatment images for prostate target volumes. The results show that with the method the image registration and transformation can be completed within one minute and has the potential to be applied to real-time adaptive radiotherapy.展开更多
Artificial intelligence(AI)has revolutionized the protein engineering process from multiple aspects,including representing protein information,generating protein designs,and evaluating protein properties.This review a...Artificial intelligence(AI)has revolutionized the protein engineering process from multiple aspects,including representing protein information,generating protein designs,and evaluating protein properties.This review aims to introduce the recent progress of AI in protein research.We first introduce how AI models represent protein sequences,structures,and other properties.Further,the applications of generative models in protein design are introduced.The use of predictive models and smart agents in the evaluation process is then discussed,including high-precision protein property simulation and wet lab experimental design.Additionally,we discuss the future development of AI in protein research and the potential challenges it may encounter.展开更多
Aims:Bleeding from gastroesophageal varices(GEV)is a medical emergency associated with high mortality.We aim to construct an artificial intelligence-based model of two-dimensional shear wave elastography(2D-SWE)of the...Aims:Bleeding from gastroesophageal varices(GEV)is a medical emergency associated with high mortality.We aim to construct an artificial intelligence-based model of two-dimensional shear wave elastography(2D-SWE)of the liver and spleen to precisely assess the risk of GEV and high-risk GEV(HRV).Methods:This was a multicenter,prospective study conducted from October 2020 to September 2022 across 12 hospitals in China.Patients with compensated advanced chronic liver disease(cACLD)were enrolled,with informed consent obtained.A total of 1136 liver stiffness measurement(LSM)images and 1042 spleen stiffness measurement(SSM)images generated by 2D SWE.Weleveraged deep learning methods to uncover associations between image features and patient risk;in this manner,we constructed models to predict GEV and HRV.Results:A multimodality deep learning risk prediction(DLRP)model was constructed to assess GEV and HRV based on LSM and SSM images and clinical information.Validation analysis revealed that the area under the curve(AUC)values of DLRP were 0.91 for GEV(95%confidence interval[CI],0.90-0.93,p<0.05)and 0.88 for HRV(95%CI,0.86-0.89,p<0.01),which were significantly and robustly better than those of canonical risk indicators,including the values of LSM(0.63 and 0.68 for GEV and HRV)andSSM(0.75for both GEV andHRV).Moreover,the DLRP model outperformed the model using individual parameters.In HRV prediction,the 2D-SWE SSM images(0.75)were more informative than LSM(0.68,p<0.01).Conclusion:Our DLRP model shows excellent performance in predicting GEV and HRV,outperforming the canonical risk indicators LSM and SSM.Additionally,the 2D-SWE SSM images provided more information and thus better accuracy in HRV prediction than the LSM images.展开更多
Ensuring the general efficacy and benefit for human beings from medical Large Language Models(LLM)before real-world deployment is crucial.However,a widely accepted and accessible evaluation process for medical LLM,esp...Ensuring the general efficacy and benefit for human beings from medical Large Language Models(LLM)before real-world deployment is crucial.However,a widely accepted and accessible evaluation process for medical LLM,especially in the Chinese context,remains to be established.In this work,we introduce“MedBench”,a comprehensive,standardized,and reliable benchmarking system for Chinese medical LLM.First,MedBench assembles the currently largest evaluation dataset(300901 questions)to cover 43 clinical specialties,and performs multi-faceted evaluation on medical LLM.Second,MedBench provides a standardized and fully automatic cloud-based evaluation infrastructure,with physical separations between question and ground truth.Third,MedBench implements dynamic evaluation mechanisms to prevent shortcut learning and answer memorization.Applying MedBench to popular general and medical LLMs,we observe unbiased,reproducible evaluation results largely aligning with medical professionals’perspectives.This study establishes a significant foundation for preparing the practical applications of Chinese medical LLMs.展开更多
基金supported by the Ministry of Science and Technology of China(No.2022YFF0802501)Inner Mongolia Autonomous Region Science and Technology Program(Nos.2021GG0100 and 2022YFHH0116).
文摘Generally speaking,the precursors of ozone(O_(3)),nitrogen oxides and volatile organic compounds are very low in desert areas due to the lack of anthropogenic emissions and natural emissions,and thus O_(3)concentrations are relatively low.However,high summer background concentrations of about 100μg/m^(3)or 60 ppb were found in the Alxa Desert in the highland of northwest China based on continuous summer observations from 2019 to 2021,which was higher than the most of natural background areas or clean areas in world for summer O_(3)background concentrations.The high O_(3)background concentrations were related to surface features and altitude.Heavy-intensity anthropogenic activity areas in desert areas can cause increased O_(3)concentrations or pollution,but also generated O_(3)depleting substances such as nitrous oxide,which eventually reduced the regional O_(3)baseline values.Nitrogen dioxide(NO2)also had a dual effect on O_(3)generation,showing promotion at low concentrations and inhibition at high concentrations.In addition,sand-dust weather reduced O_(3)clearly,but O_(3)eventually stabilized around the background concentration values and did not vary with sand-dust particulate matter.
基金supported by National Natural Science Foundation of China(82160521)Natural Science Foundation of Ningxia Province(2018A0089)Key Research and Development Program of Ningxia Province(2019BEH03003).
文摘PI3 kinases are important for KIT signaling and KIT mutants mediated cell transformation.In order to know the difference of PI3 kinase isoforms p110αand p110δin the signaling of wild-type KIT and the often occurred KIT mutation D816V in hematopoietic malignancy mastocytosis,the predominant PI3 kinase isoform p110δin hematopoietic tissues was knocked out in hematopoietic cells.We found that loss of p110δexpression dramatically inhibits PI3 kinase activation mediated by both wild-type KIT and KIT/D816V.By over expression of p110αin p110δknock out cells,wild-type KIT mediated PI3 kinase activation was not changed while over expression of p110δincreased PI3 kinase activation.Similarly,in KIT/D816V expressing cells without p110δexpression,over expression of p110δbut not p110αrestored PI3 kinase activation.In agreement with the signaling results,cell proliferation,cell survival and cell cycle assay further showed that over expression of p110δbut not p110αin p110δknock out cells increases both wild-type KIT and KIT/D816V mediated cell survival and proliferation.These results suggested that p110δplays a more important role than p110αin KIT signaling and KIT mutant mediated cell transformation in hematopoietic cells.
文摘Purpose: To develop a fast landmark-based deformable registration method to capture the soft tissue transformation between the planning 3D CT images and treatment 3D cone-beam CT (CBCT) images for the adaptive external beam radiotherapy (EBRT). Method and Materials: The developed method was based on a global-to-local landmark-based deformable registration algorithm. The landmarks were first acquired by applying a fast segmentation method using the active shape model. The global registration method was applied to establish a registration framework. The Laplacian surface deformation (LSD) and Laplacian surface optimization (LSO) method were then employed for local deformation and remeshing respectively to reach an optimal registration solution. In LSD, the deformed mesh is generated by minimizing the quadratic energy to keep the shape and to move control points to the target position. In LSO, a mesh is reconstructed by minimizing the quadratic energy to smooth the object by minimizing the difference while keeping the landmarks unchanged. The method was applied on 8 EBRT prostate datasets. The distance and volume based estimators were used to evaluate the results. The target volumes delineated by physicians were used as gold standards in the evaluation. Results: The entire segmentation and registration processing time was within 1 minute for all the datasets. The mean distance estimators ranged from 0.43 mm to 2.23 mm for the corresponding model points between the treatment CBCT images and the registered planning images. The mean overlap ratio ranged from 85.5% to 93.2% of the prostate volumes after registration. These results demonstrated reasonably good agreement between the developed method and the gold standards. Conclusion: A novel and fast landmark-based deformable registration method is developed to capture the soft tissue transformation between the planning and treatment images for prostate target volumes. The results show that with the method the image registration and transformation can be completed within one minute and has the potential to be applied to real-time adaptive radiotherapy.
基金supported by the Shanghai Agricultural Science and Technology Innovation Program(K2023001)the Key Research and Development Program of Shandong ProvinceChina(2024CXGC010213).
文摘Artificial intelligence(AI)has revolutionized the protein engineering process from multiple aspects,including representing protein information,generating protein designs,and evaluating protein properties.This review aims to introduce the recent progress of AI in protein research.We first introduce how AI models represent protein sequences,structures,and other properties.Further,the applications of generative models in protein design are introduced.The use of predictive models and smart agents in the evaluation process is then discussed,including high-precision protein property simulation and wet lab experimental design.Additionally,we discuss the future development of AI in protein research and the potential challenges it may encounter.
基金funded by the Key Research and Development Program of Jiangsu Province(No.BE2023767a)The Fundamental Research Fund of Southeast University(No.3290002303A2)+5 种基金Changjiang Scholars Talent Cultivation Project of Zhongda Hospital of Southeast University(No.2023YJXYYRCPY03)Research Personnel Cultivation Programme of Zhongda Hospital Southeast University(No.CZXM-GSP-RC125,CZXM-GSP-RC119)China Postdoctoral Science Foundation(No.2024M750461)National Natural Science Foundation of China(No.82402413)Natural Science Foundation of Jiangsu Province(No.BK20241681)National Natural Science Foundation of China(No.62061160369).
文摘Aims:Bleeding from gastroesophageal varices(GEV)is a medical emergency associated with high mortality.We aim to construct an artificial intelligence-based model of two-dimensional shear wave elastography(2D-SWE)of the liver and spleen to precisely assess the risk of GEV and high-risk GEV(HRV).Methods:This was a multicenter,prospective study conducted from October 2020 to September 2022 across 12 hospitals in China.Patients with compensated advanced chronic liver disease(cACLD)were enrolled,with informed consent obtained.A total of 1136 liver stiffness measurement(LSM)images and 1042 spleen stiffness measurement(SSM)images generated by 2D SWE.Weleveraged deep learning methods to uncover associations between image features and patient risk;in this manner,we constructed models to predict GEV and HRV.Results:A multimodality deep learning risk prediction(DLRP)model was constructed to assess GEV and HRV based on LSM and SSM images and clinical information.Validation analysis revealed that the area under the curve(AUC)values of DLRP were 0.91 for GEV(95%confidence interval[CI],0.90-0.93,p<0.05)and 0.88 for HRV(95%CI,0.86-0.89,p<0.01),which were significantly and robustly better than those of canonical risk indicators,including the values of LSM(0.63 and 0.68 for GEV and HRV)andSSM(0.75for both GEV andHRV).Moreover,the DLRP model outperformed the model using individual parameters.In HRV prediction,the 2D-SWE SSM images(0.75)were more informative than LSM(0.68,p<0.01).Conclusion:Our DLRP model shows excellent performance in predicting GEV and HRV,outperforming the canonical risk indicators LSM and SSM.Additionally,the 2D-SWE SSM images provided more information and thus better accuracy in HRV prediction than the LSM images.
基金supported by the National Key R&D Program of China(Nos.2022ZD0160705 and 2022ZD0160704)the Three-year Action Program of Shanghai Municipality for Strengthening the Construction of Public Health System(No.GWVI-11.1-49)the Health Industry National Intelligent Social Governance Experiment Base(Shanghai)——Medical Artificial Intelligence Scenario Application Case Study and Social Experiment Survey,and Shanghai Artificial Intelligence Laboratory.
文摘Ensuring the general efficacy and benefit for human beings from medical Large Language Models(LLM)before real-world deployment is crucial.However,a widely accepted and accessible evaluation process for medical LLM,especially in the Chinese context,remains to be established.In this work,we introduce“MedBench”,a comprehensive,standardized,and reliable benchmarking system for Chinese medical LLM.First,MedBench assembles the currently largest evaluation dataset(300901 questions)to cover 43 clinical specialties,and performs multi-faceted evaluation on medical LLM.Second,MedBench provides a standardized and fully automatic cloud-based evaluation infrastructure,with physical separations between question and ground truth.Third,MedBench implements dynamic evaluation mechanisms to prevent shortcut learning and answer memorization.Applying MedBench to popular general and medical LLMs,we observe unbiased,reproducible evaluation results largely aligning with medical professionals’perspectives.This study establishes a significant foundation for preparing the practical applications of Chinese medical LLMs.
