The efficient and economical exploitation of polymers with high thermal conductivity(TC)is essential to solve the issue of heat dissipation in organic devices.Currently,the experimental preparation of functional polym...The efficient and economical exploitation of polymers with high thermal conductivity(TC)is essential to solve the issue of heat dissipation in organic devices.Currently,the experimental preparation of functional polymers with high TC remains a trial-and-error process due to the multi-degrees of freedom during the synthesis and characterization process.Polymer informatics equips machine learning(ML)as a powerful engine for the efficient design of polymers with desired properties.However,available polymer TC databases are rare,and establishing appropriate polymer representation is still challenging.In this work,we propose a high-throughput screening framework for polymer chains with high TC via interpretable ML and physical feature engineering.The hierarchical down-selection process stepwise optimizes the 320 initial physical descriptors to the final 20 dimensions and then assists the ML models to achieve a prediction accuracy R2 over 0.80,which is superior to traditional graph descriptors.Further,we analyze the contribution of the individual descriptors to TC and derive the explicit equation for TC prediction using symbolic regression.The high TC polymer structures are mostlyπ-conjugated,whose overlapping p-orbitals enable easy maintenance of strong chain stiffness and large group velocities.Ultimately,we establish the connections between the individual chains and the amorphous state of polymers.Polymer chains with high TC have strong intra-chain interactions,and their corresponding amorphous systems are favorable for obtaining a large radius of gyration and causing enhanced thermal transport.The proposed data-driven framework should facilitate the theoretical and experimental design of polymers with desirable properties.展开更多
Background and Aims:This study aimed to determine the performance of the non-invasive score using noncontrastenhanced MRI(CHESS-DIS score)for detecting portal hy-pertension in cirrhosis.Methods:In this international m...Background and Aims:This study aimed to determine the performance of the non-invasive score using noncontrastenhanced MRI(CHESS-DIS score)for detecting portal hy-pertension in cirrhosis.Methods:In this international multicenter,diagnostic study(ClinicalTrials.gov,NCT03766880),patients with cirrhosis who had hepatic venous pressure gradient(HVPG)measurement and noncontrast-enhanced MRI were prospectively recruited from four university hospitals in China(n=4)and Turkey(n=1)between December 2018 and April 2019.A cohort of patients was retrospectively recruited from a university hospital in Italy between March 2015 and November 2017.After segmentation of the liver on fat-suppressed T1-weighted MRI maps,CHESS-DIS score was calculated automatically by an in-house developed code based on the quantification of liver surface nodularity.Results:A total of 149 patients were included,of which 124 were from four Chinese hospitals(training cohort)and 25 were from two international hospitals(validation cohort).A positive correlation between CHESS-DIS score and HVPG was found with the correlation coefficients of 0.36(p<0.0001)and 0.55(p<0.01)for the training and validation cohorts,respectively.The area under the receiver operating characteristic curve of CHESS-DIS score in detection of clinically significant portal hypertension(CSPH)was 0.81 and 0.9 in the training and validation cohorts,respectively.The intra-class correlation coefficients for assessing the inter-and intra-observer agreement were 0.846 and 0.841,respectively.Conclusions:A non-invasive score using noncontrast-enhanced MRI was developed and proved to be significantly correlated with invasive HVPG.Besides,this score could be used to detect CSPH in patients with cirrhosis.展开更多
In recent years,with the development of artificial intelligence,especially deep learning technology,researches on automatic detection of cerebrovascular diseases on medical images have made tremendous progress and the...In recent years,with the development of artificial intelligence,especially deep learning technology,researches on automatic detection of cerebrovascular diseases on medical images have made tremendous progress and these models are gradually entering into clinical practice.However,because of the complexity and flexibility of the deep learning algorithms,these researches have great variability on model building,validation process,performance description and results interpretation.The lack of a reliable,consistent,standardized design protocol has,to a certain extent,affected the progress of clinical translation and technology development of computer aided detection systems.After reviewing a large number of literatures and extensive discussion with domestic experts,this position paper put forward recommendations of standardized design on the key steps of deep learning-based automatic image detection models for cerebrovascular diseases.With further research and application expansion,this position paper would continue to be updated and gradually extended to evaluate the generalizability and clinical application efficacy of such tools.展开更多
Objectives To construct a distribution atlas of coronavirus disease 2019(COVID-19)pneumonia on computed tomography(CT)and further explore the difference in distribution by location and disease severity through a retro...Objectives To construct a distribution atlas of coronavirus disease 2019(COVID-19)pneumonia on computed tomography(CT)and further explore the difference in distribution by location and disease severity through a retrospective study of 484 cases in Jiangsu,China.Methods All patients diagnosed with COVID-19 from January 10 to February 18 in Jiangsu Province,China,were enrolled in our study.The patients were further divided into asymptomatic/mild,moderate,and severe/critically ill groups.A deep learning algorithm was applied to the anatomic pulmonary segmentation and pneumonia lesion extraction.The frequency of opacity on CT was calculated,and a color-coded distribution atlas was built.A further comparison was made between the upper and lower lungs,between bilateral lungs,and between various severity groups.Additional lesion-based radiomics analysis was performed to ascertain the features associated with the disease severity.Results A total of 484 laboratory-confirmed patients with 945 repeated CT scans were included.Pulmonary opacity was mainly distributed in the subpleural and peripheral areas.The distances from the opacity to the nearest parietal/visceral pleura were shortest in the asymptomatic/mild group.More diffused lesions were found in the severe/critically ill group.The frequency of opacity increased with increased severity and peaked at about 3-4 or 7-8 o’clock direction in the upper lungs,as opposed to the 5 or 6 o’clock direction in the lower lungs.Lesions with greater energy,more circle-like,and greater surface area were more likely found in severe/critically ill cases than the others.Conclusion This study constructed a detailed distribution atlas of COVID-19 pneumonia and compared specific patterns in different parts of the lungs at various severities.The radiomics features most associated with the severity were also found.These results may be valuable in determining the COVID-19 sub-phenotype.展开更多
The pledge of achieving carbon peak before 2030 and carbon neutrality before 2060 is a strategic decision that responds to the inherent needs of China’s sustainable and high-quality development,and is an important dr...The pledge of achieving carbon peak before 2030 and carbon neutrality before 2060 is a strategic decision that responds to the inherent needs of China’s sustainable and high-quality development,and is an important driving force for promoting China’s ecological civilization constructions.As the consumption of fossil fuel energy is responsible for more than 90%of China’s greenhouse gases emissions,policies focusing on energy transition are vital for China accomplishing the goal of carbon neutrality.Considering the fact that China’s energy structure is dominated by fossil fuels,especially coal,it is urgent to accelerate the low-carbon transition of the energy system in a relatively short time,and dramatically increase the proportion of clean energy in the future energy supply.Although China has made notable progress in the clean energy transition in the past,its path to carbon neutrality still faces many significant challenges.During the process of energy transformation,advanced technologies and greater investment will play essential parts in this extensive and profound systemic reform for China’s economy and society.In the meantime,these changes will create immense economic opportunities and geopolitical advantages.展开更多
基金This work was supported by the Shanghai Pujiang Program(No.20PJ1407500)the National Natural Science Foundation of China(No.52006134)+1 种基金the Shanghai Key Fundamental Research Grant(No.21JC1403300)the SJTU Global Strategic Partnership Fund(2022 SJTU-Warwick).The computations in this paper were run on theπ2.0 cluster supported by the Center for High-Performance Computing at Shanghai Jiao Tong University。
文摘The efficient and economical exploitation of polymers with high thermal conductivity(TC)is essential to solve the issue of heat dissipation in organic devices.Currently,the experimental preparation of functional polymers with high TC remains a trial-and-error process due to the multi-degrees of freedom during the synthesis and characterization process.Polymer informatics equips machine learning(ML)as a powerful engine for the efficient design of polymers with desired properties.However,available polymer TC databases are rare,and establishing appropriate polymer representation is still challenging.In this work,we propose a high-throughput screening framework for polymer chains with high TC via interpretable ML and physical feature engineering.The hierarchical down-selection process stepwise optimizes the 320 initial physical descriptors to the final 20 dimensions and then assists the ML models to achieve a prediction accuracy R2 over 0.80,which is superior to traditional graph descriptors.Further,we analyze the contribution of the individual descriptors to TC and derive the explicit equation for TC prediction using symbolic regression.The high TC polymer structures are mostlyπ-conjugated,whose overlapping p-orbitals enable easy maintenance of strong chain stiffness and large group velocities.Ultimately,we establish the connections between the individual chains and the amorphous state of polymers.Polymer chains with high TC have strong intra-chain interactions,and their corresponding amorphous systems are favorable for obtaining a large radius of gyration and causing enhanced thermal transport.The proposed data-driven framework should facilitate the theoretical and experimental design of polymers with desirable properties.
基金the National Natural Science Foundation of China(81830053,82001780)Guangzhou Industry-Academia-Research Collaborative Innovation Major Project(201704020015)+2 种基金Natural Science Foundation of Jiangsu Province of China(BK20200361)President Foundation of Nanfang Hospital,Southern Medical University(2017Z012)Distinguished Young Scholars of Gansu Province(20JR10RA713).
文摘Background and Aims:This study aimed to determine the performance of the non-invasive score using noncontrastenhanced MRI(CHESS-DIS score)for detecting portal hy-pertension in cirrhosis.Methods:In this international multicenter,diagnostic study(ClinicalTrials.gov,NCT03766880),patients with cirrhosis who had hepatic venous pressure gradient(HVPG)measurement and noncontrast-enhanced MRI were prospectively recruited from four university hospitals in China(n=4)and Turkey(n=1)between December 2018 and April 2019.A cohort of patients was retrospectively recruited from a university hospital in Italy between March 2015 and November 2017.After segmentation of the liver on fat-suppressed T1-weighted MRI maps,CHESS-DIS score was calculated automatically by an in-house developed code based on the quantification of liver surface nodularity.Results:A total of 149 patients were included,of which 124 were from four Chinese hospitals(training cohort)and 25 were from two international hospitals(validation cohort).A positive correlation between CHESS-DIS score and HVPG was found with the correlation coefficients of 0.36(p<0.0001)and 0.55(p<0.01)for the training and validation cohorts,respectively.The area under the receiver operating characteristic curve of CHESS-DIS score in detection of clinically significant portal hypertension(CSPH)was 0.81 and 0.9 in the training and validation cohorts,respectively.The intra-class correlation coefficients for assessing the inter-and intra-observer agreement were 0.846 and 0.841,respectively.Conclusions:A non-invasive score using noncontrast-enhanced MRI was developed and proved to be significantly correlated with invasive HVPG.Besides,this score could be used to detect CSPH in patients with cirrhosis.
基金Project supported by the Key Program of the National Natural Sci-ence Foundation of China(Grant Nos.81830057 and 82230068)the Young Scientists Fund of the National Natural Science Foundation of China(Grant No.82102155).
文摘In recent years,with the development of artificial intelligence,especially deep learning technology,researches on automatic detection of cerebrovascular diseases on medical images have made tremendous progress and these models are gradually entering into clinical practice.However,because of the complexity and flexibility of the deep learning algorithms,these researches have great variability on model building,validation process,performance description and results interpretation.The lack of a reliable,consistent,standardized design protocol has,to a certain extent,affected the progress of clinical translation and technology development of computer aided detection systems.After reviewing a large number of literatures and extensive discussion with domestic experts,this position paper put forward recommendations of standardized design on the key steps of deep learning-based automatic image detection models for cerebrovascular diseases.With further research and application expansion,this position paper would continue to be updated and gradually extended to evaluate the generalizability and clinical application efficacy of such tools.
基金Partial financial support was received from the Ministry of Science and Technology of the People’s Republic of China[2020YFC084370067].
文摘Objectives To construct a distribution atlas of coronavirus disease 2019(COVID-19)pneumonia on computed tomography(CT)and further explore the difference in distribution by location and disease severity through a retrospective study of 484 cases in Jiangsu,China.Methods All patients diagnosed with COVID-19 from January 10 to February 18 in Jiangsu Province,China,were enrolled in our study.The patients were further divided into asymptomatic/mild,moderate,and severe/critically ill groups.A deep learning algorithm was applied to the anatomic pulmonary segmentation and pneumonia lesion extraction.The frequency of opacity on CT was calculated,and a color-coded distribution atlas was built.A further comparison was made between the upper and lower lungs,between bilateral lungs,and between various severity groups.Additional lesion-based radiomics analysis was performed to ascertain the features associated with the disease severity.Results A total of 484 laboratory-confirmed patients with 945 repeated CT scans were included.Pulmonary opacity was mainly distributed in the subpleural and peripheral areas.The distances from the opacity to the nearest parietal/visceral pleura were shortest in the asymptomatic/mild group.More diffused lesions were found in the severe/critically ill group.The frequency of opacity increased with increased severity and peaked at about 3-4 or 7-8 o’clock direction in the upper lungs,as opposed to the 5 or 6 o’clock direction in the lower lungs.Lesions with greater energy,more circle-like,and greater surface area were more likely found in severe/critically ill cases than the others.Conclusion This study constructed a detailed distribution atlas of COVID-19 pneumonia and compared specific patterns in different parts of the lungs at various severities.The radiomics features most associated with the severity were also found.These results may be valuable in determining the COVID-19 sub-phenotype.
文摘The pledge of achieving carbon peak before 2030 and carbon neutrality before 2060 is a strategic decision that responds to the inherent needs of China’s sustainable and high-quality development,and is an important driving force for promoting China’s ecological civilization constructions.As the consumption of fossil fuel energy is responsible for more than 90%of China’s greenhouse gases emissions,policies focusing on energy transition are vital for China accomplishing the goal of carbon neutrality.Considering the fact that China’s energy structure is dominated by fossil fuels,especially coal,it is urgent to accelerate the low-carbon transition of the energy system in a relatively short time,and dramatically increase the proportion of clean energy in the future energy supply.Although China has made notable progress in the clean energy transition in the past,its path to carbon neutrality still faces many significant challenges.During the process of energy transformation,advanced technologies and greater investment will play essential parts in this extensive and profound systemic reform for China’s economy and society.In the meantime,these changes will create immense economic opportunities and geopolitical advantages.
