Background:Human infections with zoonotic coronaviruses(CoVs),including severe acute respiratory syndrome(SARS)-CoV and Middle East respiratory syndrome(MERS)-CoV,have raised great public health concern globally.Here,...Background:Human infections with zoonotic coronaviruses(CoVs),including severe acute respiratory syndrome(SARS)-CoV and Middle East respiratory syndrome(MERS)-CoV,have raised great public health concern globally.Here,we report a novel batorigin CoV causing severe and fatal pneumonia in humans.Methods:We collected clinical data and bronchoalveolar lavage(BAL)specimens from five patients with severe pneumonia from Wuhan Jinyintan Hospital,Hubei province,China.Nucleic acids of the BAL were extracted and subjected to next-generation sequencing.Virus isolation was carried out,and maximum-likelihood phylogenetic trees were constructed.Results:Five patients hospitalized from December 18 to December 29,2019 presented with fever,cough,and dyspnea accompanied by complications of acute respiratory distress syndrome.Chest radiography revealed diffuse opacities and consolidation.One of these patients died.Sequence results revealed the presence of a previously unknownβ-CoV strain in all five patients,with 99.8%to 99.9%nucleotide identities among the isolates.These isolates showed 79.0%nucleotide identity with the sequence of SARS-CoV(GenBank NC_004718)and 51.8%identity with the sequence of MERS-CoV(GenBank NC_019843).The virus is phylogenetically closest to a bat SARS-like CoV(SL-ZC45,GenBank MG772933)with 87.6%to 87.7%nucleotide identity,but is in a separate clade.Moreover,these viruses have a single intact open reading frame gene 8,as a further indicator of bat-origin CoVs.However,the amino acid sequence of the tentative receptor-binding domain resembles that of SARS-CoV,indicating that these viruses might use the same receptor.Conclusion:A novel bat-borne CoV was identified that is associated with severe and fatal respiratory disease in humans.展开更多
Over the past few years, three photorespiratory bypasses have been introduced into plants, two of which led to observable in creases in photos yn thesis and biomass yield. However, most of the experiments were carried...Over the past few years, three photorespiratory bypasses have been introduced into plants, two of which led to observable in creases in photos yn thesis and biomass yield. However, most of the experiments were carried out using Arabidopsis under controlled environmental conditions, and the increases were only observed under low-light and short-day conditions. In this study, we designed a new photorespiratory bypass (called GOC bypass), characterized by no reducing equivalents being produced during a complete oxidation of glycolate into CO2 catalyzed by three rice-self-originating enzymes, i.e., glycolate oxidase, oxalate oxidase, and catalase. We successfully established this bypass in rice chloroplasts using a multi-gene assembly and transformation system. Transgenic rice plants carrying GOC bypass (GOC plants) showed significant increases in photosynthesis efficiency, biomass yield, and nitrogen content, as well as several other CO2-enriched phe no types under both greenhouse and field conditions .Grain yield of GOC plants varied depending on seeding season and was increased significantly in the spring. We further demonstrated that GOC plants had significant advantages under high-light conditions and that the improvements in GOC plants resulted primarily from a photosynthetic CO2-concentrating effect rather than from improved energy balance. Taken together, our results reveal that engineering a newly designed chloroplastic photorespiratory bypass could increase photosynthetic efficiency and yield of rice plants grown in field conditions, particularly under high light.展开更多
Based on decreasing the flexibility of the power grid through the integration of large-scale renewable energy,a multi-energy storage system architectural model and its coor-dination operational strategy with the same ...Based on decreasing the flexibility of the power grid through the integration of large-scale renewable energy,a multi-energy storage system architectural model and its coor-dination operational strategy with the same flexibility as in the pumped storage power station and battery energy storage system(BESS)are studied.According to the new energy fluctuation characteristics and the different peak valley parameters in the power grid,this paper proposes a electricity heat hydrogen multi-energy storage system(EHH-MESS)and its coordination and optimization operational model to reduce the curtailment of wind power and photovoltaic(PV)to the power grid and improve the flexibility of the power grid.Finally,this paper studied the simulation model of an energy storage optimization control strategy after the multi-energy storage system is connected to the distribution networks,and analyzed three operational modes of the multi-energy storage system.The simulation results show that the EHH-MESS proposed in this paper has a better power grid regulation flexibility and economy,and can be used to replace the battery energy storage system based on MATLAB.展开更多
针对具有电、氢充能需求的高速公路服务区内的多能源负荷需求及服务区与周边生活垃圾处理需求,提出一种全可再生能源供能的"无废"电-氢充能服务区多源微网模型。首先,在电制氢、燃料电池、热解炉等多能源转换与存储设备的能...针对具有电、氢充能需求的高速公路服务区内的多能源负荷需求及服务区与周边生活垃圾处理需求,提出一种全可再生能源供能的"无废"电-氢充能服务区多源微网模型。首先,在电制氢、燃料电池、热解炉等多能源转换与存储设备的能量输入输出特性模型基础上,建立无废充能服务区多源微网(zero-waste charging service area multi-energy microgrid,ZWSA-MEMG)模型;其次,研究ZWSA-MEMG中多种能源转换、存储特性及多能流协调关系,建立基于高速公路充能服务区多源微网功率平衡、充能时间、多源负荷供能可靠性、可提供的电网调节性能等约束下的运行成本优化模型及其求解方法。最后,以我国西北某高速服务区实际多能源运行数据为基础,建立"无废"电-氢充能服务区多源微网优化运行仿真模型,算例仿真结果表明,该文提出的ZWSA-MEMG优化运行模型可有效提升具有垃圾处理能力的电-氢充能多能源系统的经济性,并可为电网提供较好的调节特性。展开更多
Purpose： To investigate the usefulness of three-dimensional （3D） printing in complex spinal surgery. Methods： The study was conducted from October 2014 to March 2015 in Shenzhen Second Peoples＇ Hospital and 4 cas...Purpose： To investigate the usefulness of three-dimensional （3D） printing in complex spinal surgery. Methods： The study was conducted from October 2014 to March 2015 in Shenzhen Second Peoples＇ Hospital and 4 cases of complex severe spinal disorders were selected from our department. Among them one patient combined with congenital scoliosis, one with atlas neoplasm, one with atlantoaxial dislocation, and the rest one with atlantoaxial fracture-dislocation. The data of the diseased region was collected from computerized tomography scans for 3D digital reconstruction and rapid prototyping to prepare photosensitive resin models, which were applied in the treatment of these cases. Results： The use of 3D models reduced operating time and intraoperative blood loss as well as the risk of postoperative complications. Furthermore, no pedicle penetrations or screw misplacement occurred according to the postoperative planar radiographic images. Conclusion： The tactile models from 3D printing allow direct observation and measurement, helping the orthopedists to have accurate morphometric information to provide personalized surgical planning and better communication with the patient and coworkers. Moreover, the photosensitive resin models can also guide the actual surgery with the drilling of pedicle screws and safe resection of tumor.展开更多
The Lower Paleozoic shale in south China has a very high maturity and experienced strong tectonic defor- mation. This character is quite different from the North America shale and has inhibited the shale gas evaluatio...The Lower Paleozoic shale in south China has a very high maturity and experienced strong tectonic defor- mation. This character is quite different from the North America shale and has inhibited the shale gas evaluation and exploration in this area. The present paper reports a com- prehensive investigation of maturity, reservoir properties, fluid pressure, gas content, preservation conditions, and other relevant aspects of the Lower Paleozoic shale from the Sichuan Basin and its surrounding areas. It is found that within the main maturity range （2.5 % 〈 EqRo 〈 3.5 %） of the shale, its porosity develops well, having a positive cor- relation with the TOC content, and its gas content is con- trolled mainly by the preservation conditions related to the tectonic deformation, but shale with a super high maturity （EqRo 〉 3.5 %） is considered a high risk for shale gas exploration. Taking the southern area of the Sichuan Basin and the southeastern area of Chongqing as examples of uplifted/folded and faulted/folded areas, respectively, geo- logical models of shale gas content and loss were proposed. For the uplifted/folded area with a simple tectonic defor- mation, the shale system （with a depth 〉 2000 m） has lar- gely retained overpressure during uplifting without a great loss of gas, and an industrial shale gas potential is generally possible. However, for the faulted/folded area with a strong tectonic deformation, the sealing condition of the shale system was usually destroyed to a certain degree with a great loss of free gas, which decreased the pressure coefficient and resulted in a low production capacity. It is predicted that the deeply buried shale （〉3000 m） has a greater gas potential and will become the focus for further exploration and development in most of the south China region （outside the Sichuan Basin）.展开更多
In view of the problem of low self-service capability of the microgrid due to the high operating cost and low capacity of the traditional battery energy storage system.In this paper,an electrothermal hybrid energy sto...In view of the problem of low self-service capability of the microgrid due to the high operating cost and low capacity of the traditional battery energy storage system.In this paper,an electrothermal hybrid energy storage model based on electricity,hydrogen and thermal energy conversion and storage is introduced,and a microgrid autonomous operational strategy is proposed.First,the addition of the power to hydrogen transfer equipment in the traditional combined heat and power(TCHP)system without battery energy storage is studied,and a micro gas turbine,electric to hydrogen transfer equipment and electric boiler based electrothermal energy storage system(ETSS)model is established.Aiming at the lowest comprehen-sive operating cost of multiple energy sources in a microgrid and maximizing the consumption of curtailed wind,the multi-objective scheduling model of an electrothermal hybrid energy storage system is established,then the multi-energy autonomous operational strategy of a microgrid is proposed.Lastly,the simulation of a multi-energy microgrid in Northeast China is taken as an example.The results of the simulation showed that compared with a combined heat and power microgrid system considering conventiona battery energy storage,a multi-energy microgrid system using electrothermal hybrid energy storage has better flexibility and economy,and can improve wind power accommodation.展开更多
The middle Jurassic Zhiluo Formation in the Dongsheng is comprised of a big set of green sandstone/mudstone with most of uranium orebodies occurring in close proximity to its footwall.By synthesizing field observation...The middle Jurassic Zhiluo Formation in the Dongsheng is comprised of a big set of green sandstone/mudstone with most of uranium orebodies occurring in close proximity to its footwall.By synthesizing field observations,region analysis,data collected from previous coal and uranium borehole,a regional north-south geological profile across the entire orefield is conducted.Experiments on sandstone/mudstone including rock mineral identification,clastic micromorphology and element geochemistry were carried out.Information from the geological profile indicates that green sandstone/mudstone is widely present in a stable horizon with clear boundaries to the country rock.Microscopic observations and geochemical data on sandstone/mudstone exhibit similar mineral composition with almost identical slightly flat,minor Eu enriched,Ce depleted chondrite-normalized REE patterns.Furthermore,the green clay membrane of the clasts has a complex composition containing chlorite/smectite,green smectite,chlorite,and green kaolinite,with elements including Fe,Mg,Si,and Al.These above results indicate that the green sandstone/mudstone underwent resemble sedimentary diagenetic processes as the country rock without transformation by large-scale regional fluid,while the existence of Fe2+-rich membrane is the main factor to the green sandstone/mudstone.Further concentration of the pre-enrichment uranium during diagenetic process led to the final formation for uranium deposits.The above studies are conducive to enrich the metallogenic mechanism of sandstone type uranium deposits and could provide certain reference for uranium exploration and deployment.展开更多
Background:The current deep learning diagnosis of breast masses is mainly reflected by the diagnosis of benign and malignant lesions.In China,breast masses are divided into four categories according to the treatment m...Background:The current deep learning diagnosis of breast masses is mainly reflected by the diagnosis of benign and malignant lesions.In China,breast masses are divided into four categories according to the treatment method:inflammatory masses,adenosis,benign tumors,and malignant tumors.These categorizations are important for guiding clinical treatment.In this study,we aimed to develop a convolutional neural network(CNN)for classification of these four breast mass types using ultrasound(US)images.Methods:Taking breast biopsy or pathological examinations as the reference standard,CNNs were used to establish models for the four-way classification of 3623 breast cancer patients from 13 centers.The patients were randomly divided into training and test groups(n=1810 vs.n=1813).Separate models were created for two-dimensional(2D)images only,2D and color Doppler flow imaging(2D-CDFI),and 2D-CDFI and pulsed wave Doppler(2D-CDFI-PW)images.The performance of these three models was compared using sensitivity,specificity,area under receiver operating characteristic curve(AUC),positive(PPV)and negative predictive values(NPV),positive(LR+)and negative likelihood ratios(LR-),and the performance of the 2D model was further compared between masses of different sizes with above statistical indicators,between images from different hospitals with AUC,and with the performance of 37 radiologists.Results:The accuracies of the 2D,2D-CDFI,and 2D-CDFI-PW models on the test set were 87.9%,89.2%,and 88.7%,respectively.The AUCs for classification of benign tumors,malignant tumors,inflammatory masses,and adenosis were 0.90,0.91,0.90,and 0.89,respectively(95%confidence intervals[CIs],0.87-0.91,0.89-0.92,0.87-0.91,and 0.86-0.90).The 2D-CDFI model showed better accuracy(89.2%)on the test set than the 2D(87.9%)and 2D-CDFI-PW(88.7%)models.The 2D model showed accuracy of 81.7%on breast masses≤1 cm and 82.3%on breast masses>1 cm;there was a significant difference between the two groups(P<0.001).The accuracy of the CNN classifications for the test s展开更多
基金This study was supported by grants from the Chinese Academy of Medical Sciences(CAMS)Innovation Fund for Medical Sciences(No.2016-I2M-1-014)the National Major Science&Technology Project for Control and Prevention of Major Infectious Diseases in China(Nos.2017ZX10103004,2018ZX10305409,2017ZX10204401)the National Natural Science Foundation(No.81930063)
文摘Background:Human infections with zoonotic coronaviruses(CoVs),including severe acute respiratory syndrome(SARS)-CoV and Middle East respiratory syndrome(MERS)-CoV,have raised great public health concern globally.Here,we report a novel batorigin CoV causing severe and fatal pneumonia in humans.Methods:We collected clinical data and bronchoalveolar lavage(BAL)specimens from five patients with severe pneumonia from Wuhan Jinyintan Hospital,Hubei province,China.Nucleic acids of the BAL were extracted and subjected to next-generation sequencing.Virus isolation was carried out,and maximum-likelihood phylogenetic trees were constructed.Results:Five patients hospitalized from December 18 to December 29,2019 presented with fever,cough,and dyspnea accompanied by complications of acute respiratory distress syndrome.Chest radiography revealed diffuse opacities and consolidation.One of these patients died.Sequence results revealed the presence of a previously unknownβ-CoV strain in all five patients,with 99.8%to 99.9%nucleotide identities among the isolates.These isolates showed 79.0%nucleotide identity with the sequence of SARS-CoV(GenBank NC_004718)and 51.8%identity with the sequence of MERS-CoV(GenBank NC_019843).The virus is phylogenetically closest to a bat SARS-like CoV(SL-ZC45,GenBank MG772933)with 87.6%to 87.7%nucleotide identity,but is in a separate clade.Moreover,these viruses have a single intact open reading frame gene 8,as a further indicator of bat-origin CoVs.However,the amino acid sequence of the tentative receptor-binding domain resembles that of SARS-CoV,indicating that these viruses might use the same receptor.Conclusion:A novel bat-borne CoV was identified that is associated with severe and fatal respiratory disease in humans.
基金the National Natural Science Foundation of China (31470343, 31770256)the Science and Technology Project of Guangzhou City (201607020006).
文摘Over the past few years, three photorespiratory bypasses have been introduced into plants, two of which led to observable in creases in photos yn thesis and biomass yield. However, most of the experiments were carried out using Arabidopsis under controlled environmental conditions, and the increases were only observed under low-light and short-day conditions. In this study, we designed a new photorespiratory bypass (called GOC bypass), characterized by no reducing equivalents being produced during a complete oxidation of glycolate into CO2 catalyzed by three rice-self-originating enzymes, i.e., glycolate oxidase, oxalate oxidase, and catalase. We successfully established this bypass in rice chloroplasts using a multi-gene assembly and transformation system. Transgenic rice plants carrying GOC bypass (GOC plants) showed significant increases in photosynthesis efficiency, biomass yield, and nitrogen content, as well as several other CO2-enriched phe no types under both greenhouse and field conditions .Grain yield of GOC plants varied depending on seeding season and was increased significantly in the spring. We further demonstrated that GOC plants had significant advantages under high-light conditions and that the improvements in GOC plants resulted primarily from a photosynthetic CO2-concentrating effect rather than from improved energy balance. Taken together, our results reveal that engineering a newly designed chloroplastic photorespiratory bypass could increase photosynthetic efficiency and yield of rice plants grown in field conditions, particularly under high light.
基金This project was supported by National Key Research and Development Plan(2017YFB0902100).
文摘Based on decreasing the flexibility of the power grid through the integration of large-scale renewable energy,a multi-energy storage system architectural model and its coor-dination operational strategy with the same flexibility as in the pumped storage power station and battery energy storage system(BESS)are studied.According to the new energy fluctuation characteristics and the different peak valley parameters in the power grid,this paper proposes a electricity heat hydrogen multi-energy storage system(EHH-MESS)and its coordination and optimization operational model to reduce the curtailment of wind power and photovoltaic(PV)to the power grid and improve the flexibility of the power grid.Finally,this paper studied the simulation model of an energy storage optimization control strategy after the multi-energy storage system is connected to the distribution networks,and analyzed three operational modes of the multi-energy storage system.The simulation results show that the EHH-MESS proposed in this paper has a better power grid regulation flexibility and economy,and can be used to replace the battery energy storage system based on MATLAB.
文摘针对具有电、氢充能需求的高速公路服务区内的多能源负荷需求及服务区与周边生活垃圾处理需求,提出一种全可再生能源供能的"无废"电-氢充能服务区多源微网模型。首先,在电制氢、燃料电池、热解炉等多能源转换与存储设备的能量输入输出特性模型基础上,建立无废充能服务区多源微网(zero-waste charging service area multi-energy microgrid,ZWSA-MEMG)模型;其次,研究ZWSA-MEMG中多种能源转换、存储特性及多能流协调关系,建立基于高速公路充能服务区多源微网功率平衡、充能时间、多源负荷供能可靠性、可提供的电网调节性能等约束下的运行成本优化模型及其求解方法。最后,以我国西北某高速服务区实际多能源运行数据为基础,建立"无废"电-氢充能服务区多源微网优化运行仿真模型,算例仿真结果表明,该文提出的ZWSA-MEMG优化运行模型可有效提升具有垃圾处理能力的电-氢充能多能源系统的经济性,并可为电网提供较好的调节特性。
文摘Purpose： To investigate the usefulness of three-dimensional （3D） printing in complex spinal surgery. Methods： The study was conducted from October 2014 to March 2015 in Shenzhen Second Peoples＇ Hospital and 4 cases of complex severe spinal disorders were selected from our department. Among them one patient combined with congenital scoliosis, one with atlas neoplasm, one with atlantoaxial dislocation, and the rest one with atlantoaxial fracture-dislocation. The data of the diseased region was collected from computerized tomography scans for 3D digital reconstruction and rapid prototyping to prepare photosensitive resin models, which were applied in the treatment of these cases. Results： The use of 3D models reduced operating time and intraoperative blood loss as well as the risk of postoperative complications. Furthermore, no pedicle penetrations or screw misplacement occurred according to the postoperative planar radiographic images. Conclusion： The tactile models from 3D printing allow direct observation and measurement, helping the orthopedists to have accurate morphometric information to provide personalized surgical planning and better communication with the patient and coworkers. Moreover, the photosensitive resin models can also guide the actual surgery with the drilling of pedicle screws and safe resection of tumor.
基金jointly supported by the National Key Basic Research Program of China (973 Program: 2012CB214700)the Strategic Priority Research Program of the Chinese Academy of Sciences (XDB10040300)the National Natural Science Foundation of China (41321002)
文摘The Lower Paleozoic shale in south China has a very high maturity and experienced strong tectonic defor- mation. This character is quite different from the North America shale and has inhibited the shale gas evaluation and exploration in this area. The present paper reports a com- prehensive investigation of maturity, reservoir properties, fluid pressure, gas content, preservation conditions, and other relevant aspects of the Lower Paleozoic shale from the Sichuan Basin and its surrounding areas. It is found that within the main maturity range （2.5 % 〈 EqRo 〈 3.5 %） of the shale, its porosity develops well, having a positive cor- relation with the TOC content, and its gas content is con- trolled mainly by the preservation conditions related to the tectonic deformation, but shale with a super high maturity （EqRo 〉 3.5 %） is considered a high risk for shale gas exploration. Taking the southern area of the Sichuan Basin and the southeastern area of Chongqing as examples of uplifted/folded and faulted/folded areas, respectively, geo- logical models of shale gas content and loss were proposed. For the uplifted/folded area with a simple tectonic defor- mation, the shale system （with a depth 〉 2000 m） has lar- gely retained overpressure during uplifting without a great loss of gas, and an industrial shale gas potential is generally possible. However, for the faulted/folded area with a strong tectonic deformation, the sealing condition of the shale system was usually destroyed to a certain degree with a great loss of free gas, which decreased the pressure coefficient and resulted in a low production capacity. It is predicted that the deeply buried shale （〉3000 m） has a greater gas potential and will become the focus for further exploration and development in most of the south China region （outside the Sichuan Basin）.
基金This work was supported by the National Key Research and Development Program of China(No.2017YFB0902100).
文摘In view of the problem of low self-service capability of the microgrid due to the high operating cost and low capacity of the traditional battery energy storage system.In this paper,an electrothermal hybrid energy storage model based on electricity,hydrogen and thermal energy conversion and storage is introduced,and a microgrid autonomous operational strategy is proposed.First,the addition of the power to hydrogen transfer equipment in the traditional combined heat and power(TCHP)system without battery energy storage is studied,and a micro gas turbine,electric to hydrogen transfer equipment and electric boiler based electrothermal energy storage system(ETSS)model is established.Aiming at the lowest comprehen-sive operating cost of multiple energy sources in a microgrid and maximizing the consumption of curtailed wind,the multi-objective scheduling model of an electrothermal hybrid energy storage system is established,then the multi-energy autonomous operational strategy of a microgrid is proposed.Lastly,the simulation of a multi-energy microgrid in Northeast China is taken as an example.The results of the simulation showed that compared with a combined heat and power microgrid system considering conventiona battery energy storage,a multi-energy microgrid system using electrothermal hybrid energy storage has better flexibility and economy,and can improve wind power accommodation.
基金This work was financially and technically supported by National Key Basic Research Program(2015CB453000)of Ministry Science and TechnologyGeological Survey Projects(DD20160127 and DD20160128)from China Geological Surveythe International Geoscience Program(IGCP675)from UNESCO.
文摘The middle Jurassic Zhiluo Formation in the Dongsheng is comprised of a big set of green sandstone/mudstone with most of uranium orebodies occurring in close proximity to its footwall.By synthesizing field observations,region analysis,data collected from previous coal and uranium borehole,a regional north-south geological profile across the entire orefield is conducted.Experiments on sandstone/mudstone including rock mineral identification,clastic micromorphology and element geochemistry were carried out.Information from the geological profile indicates that green sandstone/mudstone is widely present in a stable horizon with clear boundaries to the country rock.Microscopic observations and geochemical data on sandstone/mudstone exhibit similar mineral composition with almost identical slightly flat,minor Eu enriched,Ce depleted chondrite-normalized REE patterns.Furthermore,the green clay membrane of the clasts has a complex composition containing chlorite/smectite,green smectite,chlorite,and green kaolinite,with elements including Fe,Mg,Si,and Al.These above results indicate that the green sandstone/mudstone underwent resemble sedimentary diagenetic processes as the country rock without transformation by large-scale regional fluid,while the existence of Fe2+-rich membrane is the main factor to the green sandstone/mudstone.Further concentration of the pre-enrichment uranium during diagenetic process led to the final formation for uranium deposits.The above studies are conducive to enrich the metallogenic mechanism of sandstone type uranium deposits and could provide certain reference for uranium exploration and deployment.
基金This study was supported by the grants from the National Key Research and Development Program of China(No.2016YFC0104801)National Natural Science Foundation of China(No.81730050)。
文摘Background:The current deep learning diagnosis of breast masses is mainly reflected by the diagnosis of benign and malignant lesions.In China,breast masses are divided into four categories according to the treatment method:inflammatory masses,adenosis,benign tumors,and malignant tumors.These categorizations are important for guiding clinical treatment.In this study,we aimed to develop a convolutional neural network(CNN)for classification of these four breast mass types using ultrasound(US)images.Methods:Taking breast biopsy or pathological examinations as the reference standard,CNNs were used to establish models for the four-way classification of 3623 breast cancer patients from 13 centers.The patients were randomly divided into training and test groups(n=1810 vs.n=1813).Separate models were created for two-dimensional(2D)images only,2D and color Doppler flow imaging(2D-CDFI),and 2D-CDFI and pulsed wave Doppler(2D-CDFI-PW)images.The performance of these three models was compared using sensitivity,specificity,area under receiver operating characteristic curve(AUC),positive(PPV)and negative predictive values(NPV),positive(LR+)and negative likelihood ratios(LR-),and the performance of the 2D model was further compared between masses of different sizes with above statistical indicators,between images from different hospitals with AUC,and with the performance of 37 radiologists.Results:The accuracies of the 2D,2D-CDFI,and 2D-CDFI-PW models on the test set were 87.9%,89.2%,and 88.7%,respectively.The AUCs for classification of benign tumors,malignant tumors,inflammatory masses,and adenosis were 0.90,0.91,0.90,and 0.89,respectively(95%confidence intervals[CIs],0.87-0.91,0.89-0.92,0.87-0.91,and 0.86-0.90).The 2D-CDFI model showed better accuracy(89.2%)on the test set than the 2D(87.9%)and 2D-CDFI-PW(88.7%)models.The 2D model showed accuracy of 81.7%on breast masses≤1 cm and 82.3%on breast masses>1 cm;there was a significant difference between the two groups(P<0.001).The accuracy of the CNN classifications for the test s
