Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional ...Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional attention schemes have not considered the impact of lesion type differences on grading,resulting in unreasonable extraction of important lesion features.Therefore,this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator(MPAG)and a lesion localization module(LLM).Firstly,MPAGis used to predict patches of different sizes and generate a weighted attention map based on the prediction score and the types of lesions contained in the patches,fully considering the impact of lesion type differences on grading,solving the problem that the attention maps of lesions cannot be further refined and then adapted to the final DR diagnosis task.Secondly,the LLM generates a global attention map based on localization.Finally,the weighted attention map and global attention map are weighted with the fundus map to fully explore effective DR lesion information and increase the attention of the classification network to lesion details.This paper demonstrates the effectiveness of the proposed method through extensive experiments on the public DDR dataset,obtaining an accuracy of 0.8064.展开更多
To overcome the shortcomings of 1 D and 2 D Otsu’s thresholding techniques, the 3 D Otsu method has been developed.Among all Otsu’s methods, 3 D Otsu technique provides the best threshold values for the multi-level ...To overcome the shortcomings of 1 D and 2 D Otsu’s thresholding techniques, the 3 D Otsu method has been developed.Among all Otsu’s methods, 3 D Otsu technique provides the best threshold values for the multi-level thresholding processes. In this paper, to improve the quality of segmented images, a simple and effective multilevel thresholding method is introduced. The proposed approach focuses on preserving edge detail by computing the 3 D Otsu along the fusion phenomena. The advantages of the presented scheme include higher quality outcomes, better preservation of tiny details and boundaries and reduced execution time with rising threshold levels. The fusion approach depends upon the differences between pixel intensity values within a small local space of an image;it aims to improve localized information after the thresholding process. The fusion of images based on local contrast can improve image segmentation performance by minimizing the loss of local contrast, loss of details and gray-level distributions. Results show that the proposed method yields more promising segmentation results when compared to conventional1 D Otsu, 2 D Otsu and 3 D Otsu methods, as evident from the objective and subjective evaluations.展开更多
In recent years, intensifying waterlogging, salt water intrusion, wetland loss, and ecosystem degradation in Chinese delta cities and adjacent regions have generated the pressing need to create an urban form that is s...In recent years, intensifying waterlogging, salt water intrusion, wetland loss, and ecosystem degradation in Chinese delta cities and adjacent regions have generated the pressing need to create an urban form that is suited to both current and future climates incorporating sea level rise. However, adaptation planning uptake is slow. This is particularly unfortunate because patterns of urban form interact with mean sea level rise （MSLR） in ways that reduce or intensify its impact. There are currently two main barriers that are significant in arresting the implementation of adaptation planning with reference to the MSLR projections composed of geomorphologic MSLR projections and eustatic MSLR projections from global climate warming, and making a comprehensive risk assessment of MSLR projections. The present review shows recent progresses in mapping MSLR projections and their risk assessment approaches on Chinese delta cities, and then a perspective of adapting these cities to MSLR projections as following six aspects. 1） The geomorphologic MSLR projections are contributed by the natural tectonic subsidence projections and the MSLR projections by anthropogenic geomorphologic change. The former needs to be updated in a global framework. The latter is accumulated by land subsidence from underground water depletion, water level fall caused by the erosion of riverbeds from a sediment supply decline attributed to the construction of watershed dams, artificial sand excavation, water level raise by engineering projects including land reclamation, deep waterway regulation, and fresh water reservoirs. 2） Controlling MSLR projections by anthropogenic geomorphologic changes. 3） The IPCC AR5 RCPs MSLRs scenarios are expected to be projected to the local eustatic MSLR projections on the Chinese deltas. 4） The MSLR projections need to be matched to a local elevation datum. 5） Modeling approaches of regional river-sea numerical with semi- analytical hydrodynamics, estuarine channel network, system dynamics and adaptation points are perspective. 6） Adaptation planning to MSLR projections requires a comprehensive risk assessment of the risk of flood, fresh water supply shortage, coastal erosion, wetland loss, siltation of ports and waterway in Chinese delta cities and adjacent regions.展开更多
Sea level rise （SLR） is a major projected threat of climate change that is expected to affect developing coastal cities located in estuarine delta regions, Shanghai is one such city, being located in the Yangtze Riv...Sea level rise （SLR） is a major projected threat of climate change that is expected to affect developing coastal cities located in estuarine delta regions, Shanghai is one such city, being located in the Yangtze River Delta （YRD）, It is difficult, however, for decision-makers to implement adaptation due to the uncer- tain causes, magnitudes, and timings of SLR behaviors, This paper attempts to map the causes and mag- nitudes of SLR behaviors on a decadal scale, We analyze the tidal level records from 11 tidal gauge stations and the corresponding bathymetry measurements around these stations since 1921, We identify three new SLR behaviors along the Shanghai coast due to anthropogenic geomorphologic changes （AGCs）, besides the well-known eustatic sea level rise （ESLR）, tectonic subsidence （TS）, and urban land subsidence （ULS）, The first new behavior is regional sea level rise （RSLR）, which occurs as a result of land reclamation and deep waterway regulation, The second is regional sea level fall （RSLF）, which occurs because the channel bed is eroded due to sediment supply decline in the river catchment, The last SLR behavior is local tidal datum rise （LTDR）. Thus, we project that the magnitude of SLR for the Shanghai coast ranges from 10 cm to 16 cm from 2011 to 2030, Clarifying SLR behaviors is important to aid local decision- makers in planning structural and non-structural measures to combat escalating flood damage costs in an estuarine delta system; this field is full of future challenges,展开更多
Estimation of the zero-height geopotential value W_0^（LVD） for the CVD（China Vertical Datum） plays a fundamental role in the connection of traditional height reference systems into a global height system.Estimatio...Estimation of the zero-height geopotential value W_0^（LVD） for the CVD（China Vertical Datum） plays a fundamental role in the connection of traditional height reference systems into a global height system.Estimation the W_0^（LVD） of China is based on the computation of the mean geopotential offset between the value W_0= 62636856.0 m^2 s^（-2）, selected as reference in this study, and the unknown geopotential value W_0^（LVD）. This estimation is based on the combination of ellipsoidal heights, levelled heights（referring to the CVD）, and some physical parameters, such as geopotential values, gravity values, and geoid undulations.The geoid undulations derived from the GGM（Global Geopotential Models）. This combination is performed through three approaches： The first one is based on the theory of Molodensky, and the second one compares levelled heights and geopotential values derived from the GGMs, while the third one analyses the differences between GPS/Levelling and GGMs geoid undulations. The approaches are evaluated at 65 benchmarks（BMs） covered around Qingdao where the tide gauge is used to observe the local mean sea level of China. The results from three approaches are very similar. Furthermore, the W_0^（LVD）determined for the China local vertical datum was 62636852.9462 m^2 s^（-2）, indicates a bias of about3.0538 m^2/s^（-2） compared to the conventional value of 62636856.0 m^2 s^（-2）.展开更多
基金supported in part by the Research on the Application of Multimodal Artificial Intelligence in Diagnosis and Treatment of Type 2 Diabetes under Grant No.2020SK50910in part by the Hunan Provincial Natural Science Foundation of China under Grant 2023JJ60020.
文摘Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional attention schemes have not considered the impact of lesion type differences on grading,resulting in unreasonable extraction of important lesion features.Therefore,this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator(MPAG)and a lesion localization module(LLM).Firstly,MPAGis used to predict patches of different sizes and generate a weighted attention map based on the prediction score and the types of lesions contained in the patches,fully considering the impact of lesion type differences on grading,solving the problem that the attention maps of lesions cannot be further refined and then adapted to the final DR diagnosis task.Secondly,the LLM generates a global attention map based on localization.Finally,the weighted attention map and global attention map are weighted with the fundus map to fully explore effective DR lesion information and increase the attention of the classification network to lesion details.This paper demonstrates the effectiveness of the proposed method through extensive experiments on the public DDR dataset,obtaining an accuracy of 0.8064.
文摘To overcome the shortcomings of 1 D and 2 D Otsu’s thresholding techniques, the 3 D Otsu method has been developed.Among all Otsu’s methods, 3 D Otsu technique provides the best threshold values for the multi-level thresholding processes. In this paper, to improve the quality of segmented images, a simple and effective multilevel thresholding method is introduced. The proposed approach focuses on preserving edge detail by computing the 3 D Otsu along the fusion phenomena. The advantages of the presented scheme include higher quality outcomes, better preservation of tiny details and boundaries and reduced execution time with rising threshold levels. The fusion approach depends upon the differences between pixel intensity values within a small local space of an image;it aims to improve localized information after the thresholding process. The fusion of images based on local contrast can improve image segmentation performance by minimizing the loss of local contrast, loss of details and gray-level distributions. Results show that the proposed method yields more promising segmentation results when compared to conventional1 D Otsu, 2 D Otsu and 3 D Otsu methods, as evident from the objective and subjective evaluations.
基金Acknowledgments This study was financially supported by the Shanghai Science and Technology Committee （10dz1210600）, the National Sea Welfare Project （201005019-09）, the Natural Science Foundation of China （41476075, 41340044）, and the China Geological Survey （12120115043101 ）.
文摘In recent years, intensifying waterlogging, salt water intrusion, wetland loss, and ecosystem degradation in Chinese delta cities and adjacent regions have generated the pressing need to create an urban form that is suited to both current and future climates incorporating sea level rise. However, adaptation planning uptake is slow. This is particularly unfortunate because patterns of urban form interact with mean sea level rise （MSLR） in ways that reduce or intensify its impact. There are currently two main barriers that are significant in arresting the implementation of adaptation planning with reference to the MSLR projections composed of geomorphologic MSLR projections and eustatic MSLR projections from global climate warming, and making a comprehensive risk assessment of MSLR projections. The present review shows recent progresses in mapping MSLR projections and their risk assessment approaches on Chinese delta cities, and then a perspective of adapting these cities to MSLR projections as following six aspects. 1） The geomorphologic MSLR projections are contributed by the natural tectonic subsidence projections and the MSLR projections by anthropogenic geomorphologic change. The former needs to be updated in a global framework. The latter is accumulated by land subsidence from underground water depletion, water level fall caused by the erosion of riverbeds from a sediment supply decline attributed to the construction of watershed dams, artificial sand excavation, water level raise by engineering projects including land reclamation, deep waterway regulation, and fresh water reservoirs. 2） Controlling MSLR projections by anthropogenic geomorphologic changes. 3） The IPCC AR5 RCPs MSLRs scenarios are expected to be projected to the local eustatic MSLR projections on the Chinese deltas. 4） The MSLR projections need to be matched to a local elevation datum. 5） Modeling approaches of regional river-sea numerical with semi- analytical hydrodynamics, estuarine channel network, system dynamics and adaptation points are perspective. 6） Adaptation planning to MSLR projections requires a comprehensive risk assessment of the risk of flood, fresh water supply shortage, coastal erosion, wetland loss, siltation of ports and waterway in Chinese delta cities and adjacent regions.
基金This study was financially supported by the National Natural Science Foundation of China-the Netherlands Organization for Scientific Research-Research Councils UK （NSFC-NWO-RCUK） （51761135023）, the Shanghai Science and Technology Committee （10dz1210600）, the National Sea Welfare Project （201005019- 09）, the National Natural Science Foundation of China （41476075）, and the China Geological Survey （DD20160246）. We would like to give a special acknowledgement to the second author, ProfessorJi-Yu Chen, who was a great scientist of estuarine and coastal research, for the excellent suggestions and guidelines he provided over a considerable period of time before he passed away.
文摘Sea level rise （SLR） is a major projected threat of climate change that is expected to affect developing coastal cities located in estuarine delta regions, Shanghai is one such city, being located in the Yangtze River Delta （YRD）, It is difficult, however, for decision-makers to implement adaptation due to the uncer- tain causes, magnitudes, and timings of SLR behaviors, This paper attempts to map the causes and mag- nitudes of SLR behaviors on a decadal scale, We analyze the tidal level records from 11 tidal gauge stations and the corresponding bathymetry measurements around these stations since 1921, We identify three new SLR behaviors along the Shanghai coast due to anthropogenic geomorphologic changes （AGCs）, besides the well-known eustatic sea level rise （ESLR）, tectonic subsidence （TS）, and urban land subsidence （ULS）, The first new behavior is regional sea level rise （RSLR）, which occurs as a result of land reclamation and deep waterway regulation, The second is regional sea level fall （RSLF）, which occurs because the channel bed is eroded due to sediment supply decline in the river catchment, The last SLR behavior is local tidal datum rise （LTDR）. Thus, we project that the magnitude of SLR for the Shanghai coast ranges from 10 cm to 16 cm from 2011 to 2030, Clarifying SLR behaviors is important to aid local decision- makers in planning structural and non-structural measures to combat escalating flood damage costs in an estuarine delta system; this field is full of future challenges,
文摘Estimation of the zero-height geopotential value W_0^（LVD） for the CVD（China Vertical Datum） plays a fundamental role in the connection of traditional height reference systems into a global height system.Estimation the W_0^（LVD） of China is based on the computation of the mean geopotential offset between the value W_0= 62636856.0 m^2 s^（-2）, selected as reference in this study, and the unknown geopotential value W_0^（LVD）. This estimation is based on the combination of ellipsoidal heights, levelled heights（referring to the CVD）, and some physical parameters, such as geopotential values, gravity values, and geoid undulations.The geoid undulations derived from the GGM（Global Geopotential Models）. This combination is performed through three approaches： The first one is based on the theory of Molodensky, and the second one compares levelled heights and geopotential values derived from the GGMs, while the third one analyses the differences between GPS/Levelling and GGMs geoid undulations. The approaches are evaluated at 65 benchmarks（BMs） covered around Qingdao where the tide gauge is used to observe the local mean sea level of China. The results from three approaches are very similar. Furthermore, the W_0^（LVD）determined for the China local vertical datum was 62636852.9462 m^2 s^（-2）, indicates a bias of about3.0538 m^2/s^（-2） compared to the conventional value of 62636856.0 m^2 s^（-2）.
