GSTDTAP

浏览/检索结果: 共5条,第1-5条 帮助

已选(0)清除 条数/页:   排序方式:
Video-based AI for beat-to-beat assessment of cardiac function 期刊论文
NATURE, 2020, 580 (7802) : 252-+
作者:  Pleguezuelos-Manzano, Cayetano;  Puschhof, Jens;  Huber, Axel Rosendahl;  van Hoeck, Arne;  Wood, Henry M.;  Nomburg, Jason;  Gurjao, Carino;  Manders, Freek;  Dalmasso, Guillaume;  Stege, Paul B.;  Paganelli, Fernanda L.;  Geurts, Maarten H.;  Beumer, Joep;  Mizutani, Tomohiro;  Miao, Yi;  van der Linden, Reinier;  van der Elst, Stefan;  Garcia, K. Christopher;  Top, Janetta;  Willems, Rob J. L.;  Giannakis, Marios;  Bonnet, Richard;  Quirke, Phil;  Meyerson, Matthew;  Cuppen, Edwin;  van Boxtel, Ruben;  Clevers, Hans
收藏  |  浏览/下载:137/0  |  提交时间:2020/07/03

A video-based deep learning algorithm-EchoNet-Dynamic-accurately identifies subtle changes in ejection fraction and classifies heart failure with reduced ejection fraction using information from multiple cardiac cycles.


Accurate assessment of cardiac function is crucial for the diagnosis of cardiovascular disease(1), screening for cardiotoxicity(2) and decisions regarding the clinical management of patients with a critical illness(3). However, human assessment of cardiac function focuses on a limited sampling of cardiac cycles and has considerable inter-observer variability despite years of training(4,5). Here, to overcome this challenge, we present a video-based deep learning algorithm-EchoNet-Dynamic-that surpasses the performance of human experts in the critical tasks of segmenting the left ventricle, estimating ejection fraction and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice similarity coefficient of 0.92, predicts ejection fraction with a mean absolute error of 4.1% and reliably classifies heart failure with reduced ejection fraction (area under the curve of 0.97). In an external dataset from another healthcare system, EchoNet-Dynamic predicts the ejection fraction with a mean absolute error of 6.0% and classifies heart failure with reduced ejection fraction with an area under the curve of 0.96. Prospective evaluation with repeated human measurements confirms that the model has variance that is comparable to or less than that of human experts. By leveraging information across multiple cardiac cycles, our model can rapidly identify subtle changes in ejection fraction, is more reproducible than human evaluation and lays the foundation for precise diagnosis of cardiovascular disease in real time. As a resource to promote further innovation, we also make publicly available a large dataset of 10,030 annotated echocardiogram videos.


  
Global-scale human impact on delta morphology has led to net land area gain 期刊论文
NATURE, 2020, 577 (7791) : 514-+
作者:  Nienhuis, J. H.;  Ashton, A. D.;  Edmonds, D. A.;  Hoitink, A. J. F.;  Kettner, A. J.;  Rowland, J. C.;  Tornqvist, T. E.
收藏  |  浏览/下载:40/0  |  提交时间:2020/05/13

River deltas rank among the most economically and ecologically valuable environments on Earth. Even in the absence of sea-level rise, deltas are increasingly vulnerable to coastal hazards as declining sediment supply and climate change alter their sediment budget, affecting delta morphology and possibly leading to erosion(1-3). However, the relationship between deltaic sediment budgets, oceanographic forces of waves and tides, and delta morphology has remained poorly quantified. Here we show how the morphology of about 11,000 coastal deltas worldwide, ranging from small bayhead deltas to mega-deltas, has been affected by river damming and deforestation. We introduce a model that shows that present-day delta morphology varies across a continuum between wave (about 80 per cent), tide (around 10 per cent) and river (about 10 per cent) dominance, but that most large deltas are tide- and river-dominated. Over the past 30 years, despite sea-level rise, deltas globally have experienced a net land gain of 54 +/- 12 square kilometres per year (2 standard deviations), with the largest 1 per cent of deltas being responsible for 30 per cent of all net land area gains. Humans are a considerable driver of these net land gains-25 per cent of delta growth can be attributed to deforestation-induced increases in fluvial sediment supply. Yet for nearly 1,000 deltas, river damming(4) has resulted in a severe (more than 50 per cent) reduction in anthropogenic sediment flux, forcing a collective loss of 12 +/- 3.5 square kilometres per year (2 standard deviations) of deltaic land. Not all deltas lose land in response to river damming: deltas transitioning towards tide dominance are currently gaining land, probably through channel infilling. With expected accelerated sea-level rise(5), however, recent land gains are unlikely to be sustained throughout the twenty-first century. Understanding the redistribution of sediments by waves and tides will be critical for successfully predicting human-driven change to deltas, both locally and globally.


A global study of river deltas shows a net increase in delta area by about 54 km(2) yr(-1) over the past 30 years, in part due to deforestation-induced sediment delivery increase.


  
Impacts of future climate change on species richness of land vertebrates and critical areas in South Korea 期刊论文
CLIMATE RESEARCH, 2019, 77 (3) : 241-248
作者:  Lee, Ju-Hyun;  Kang, Hee-Jin;  Sung, Ha-Cheol
收藏  |  浏览/下载:15/0  |  提交时间:2019/11/26
Climate Change Severity Index  Species richness  Critical area  RCP scenarios  
Unexpected spatial stability of water chemistry in headwater stream networks 期刊论文
ECOLOGY LETTERS, 2018, 21 (2) : 296-308
作者:  Abbott, Benjamin W.;  Gruau, Gerard;  Zarnetske, Jay P.;  Moatar, Florentina;  Barbe, Lou;  Thomas, Zahra;  Fovet, Ophelie;  Kolbe, Tamara;  Gu, Sen;  Pierson-Wickmann, Anne-Catherine;  Davy, Philippe;  Pinay, Gilles
收藏  |  浏览/下载:13/0  |  提交时间:2019/04/09
Critical source area  dissolved organic carbon  hydrologically sensitive area  network analysis  nutrients  representative elementary area  stream network  subcatchment leverage  subcatchment synchrony  synoptic sampling  
Development of RWHet to Simulate Contaminant Transport in Fractured Porous Media 科技报告
来源:US Department of Energy (DOE). 出版年: 2012
作者:  Zhang, Yong;  LaBolle, Eric;  Reeves, Donald M;  Russell, Charles
收藏  |  浏览/下载:14/0  |  提交时间:2019/04/05
Accurate simulation of matrix diffusion in regional-scale dual-porosity and dual-permeability media is a critical issue for the DOE Underground Test Area (UGTA) program  given the prevalence of fractured geologic media on the Nevada National Security Site