Regular health screening plays a crucial role in the early detection of common chronic diseases and prevention of their progression. An AI system capable of recapitulating early disease detection, staging and incidence prediction would help to improve healthcare access and delivery, particularly in resource-poor or remote settings. Using a total of 115,344 retinal fundus photographs from 57,672 patients (with data split into mutually exclusive training, internal testing, and external validation sets), we first developed AI models capable of identifying chronic kidney disease (CKD) and type 2 diabetes mellitus (T2DM) based on fundus images. The AI system was shown to be capable of predicting the clinical indicators of CKD and T2DM (including eGFR and blood glucose levels), which indicates its potential for extracting quantitative clinical metrics embedded subtly within retinal fundus images. We further developed an AI system to predict the risk of disease progression using baseline images of 10,269 patients for whom longitudinal clinical data were available for up to 6 years, which demonstrated potential utility in optimizing health screening intervals and clinical management. The generalizability of the AI system in identifying and predicting the progression of CKD and T2DM was evaluated using population-based external validation cohorts. Moreover, a prospective pilot study with 3,081 patients was also conducted to demonstrate the broader applicability of the AI system at the 'point-of-care' using fundus images captured with smartphones. The results provide proof-of-concept for a reliable and non-invasive AI-based clinical screening tool based on fundus photographs for the early detection and incidence prediction of two common systemic diseases.
Changes on lakes and rivers are of great significance for the study of global climate change. Accurate segmentation of lakes and rivers is critical to the study of their changes. However, traditional water area segmentation methods almost all share the following deficiencies: high computational requirements, poor generalization performance, and low extraction accuracy. In recent years, semantic segmentation algorithms based on deep learning have been emerging. Addressing problems associated to a very large number of parameters, low accuracy, and network degradation during training process, this paper proposes a separable residual SegNet (SR-SegNet) to perform the water area segmentation using remote sensing images. On the one hand, without compromising the ability of feature extraction, the problem of network degradation is alleviated by adding modified residual blocks into the encoder, the number of parameters is limited by introducing depthwise separable convolutions, and the ability of feature extraction is improved by using dilated convolutions to expand the receptive field. On the other hand, SR-SegNet removes the convolution layers with relatively more convolution kernels in the encoding stage, and uses the cascading method to fuse the low-level and high-level features of the image. As a result, the whole network can obtain more spatial information. Experimental results show that the proposed method exhibits significant improvements over several traditional methods, including FCN, DeconvNet, and SegNet.
Intensive agricultural development can change land use, which can further affect regional ecosystem services and functions. With the rapid growth of the population and the national demand for food, the northeast of China, which is located in the high latitudes, has experienced four agricultural developments since the 1950s. The original wetlands of this area were developed for farmland. The evaluation of ecosystem services is conducted to reveal the ecosystem status and variable trends caused by land reclamation. The aim of this study is to provide scientific basis for environmental management and for the sustainable development of agriculture in Northeast China. With GIS-RS technology, a typical farm was chosen to analyze variations in the ecosystem service value in response to land use changes during the study period. The total ecosystem service value of the farm decreased from 7523.10 million Yuan in 1979 to 4023.59 million Yuan in 2009 with an annual rate of -1.6 % due to the decreasing areas of woodland and wetland. The increased areas of cropland, water area and grassland partly offset the loss of the total value, but the loss was still greater than the compensation. Waste treatment and climate regulation were the top two service functions with high service values, contributing to approximately 50 % of the total service value. The spatial difference of the ecosystem service value also was analyzed. The wetlands located in the central and northeastern sections of the farm changed significantly. From the aspect of ecosystem service value, the wetland and water area should be conserved, as they have the highest value coefficients. The accuracy of the value coefficient, however, needs to be studied further in future research.
Mapping soil nutrients can help smallholder farmers identify soil nutrient status and implement site-specific soil management schemes. In the past, Digital Soil Mapping has seldom been utilized to guide soil nutrient management in smallholder farm settings in South India. The objective of this research was to analyze the spatial resolution effects of different remote sensing images on soil Total Nitrogen (TN) prediction models in two smallholder villages, Kothapally and Masuti in South India. Regression kriging (RK) was used to characterize the spatial pattern
A B S T R A C TImage fusion is in its infancy in the application of Digital Soil Mapping, and the incorporation of the image pansharpened spectral indices into the soil prediction models has seldom been analyzed. This research performed image pansharpening of Landsat 8, WorldView-2, and Pleiades-1A in a smallholder village called Masuti in South India using three pansharpening techniques: Brovey, Gram-Schmit (GS), and Intensity-Hue-Saturation (IHS) methods. The research analyzed the relationships between multispectral (MS) and pansharpened (PAN) spectral indices and soil total nitrogen (TN), developed the soil TN prediction models using Random Forest methods, and explored the effects of different PAN spectral indices on soil TN prediction models. The results showed the spectral behavior of PAN spectral indices and MS spectral indices were similar. The results also demonstrated that soil TN models based on MS/PAN spectral indices have slightly higher model performance and more detailed characterization of TN spatial pattern compared with soil TN models based on MS spectral indices. Soil TN models based on the GS PAN and MS spectral indices attained slightly higher prediction accuracy compared with those based on other PAN and MS spectral indices. This research advocates the promotion of image pansharpening techniques in digital soil mapping and soil nutrient management research. (S. Grunwald), aamr@ufl.edu (A. Abd-Elrahman), s.wani@cgiar.org (S.P. Wani).Geoderma 320 (2018) 52-66 0016-7061/
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.