id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-103533-k1lg8c7q	Jin, C.	Development and Evaluation of an AI System for COVID-19	2020-03-23		.txt	text/plain	6431	370	53	We developed and evaluated a deep learning based COVID-19 diagnosis system, using multi-center data, which includes 756 subjects (496 COVID-19 positives and 260 negatives) collected in Wuhan Union Hospital, Western Campus of Wuhan Union Hospital, and Jianghan Mobile Cabin Hospital in Wuhan, the major epidemic area in China (detailed information is in Table 1 ). https://doi.org/10.1101/2020.03.20.20039834 doi: medRxiv preprint sists of five key components (Figure 1 a) , (1) a 2D convolutional neural network (CNN) model for segmenting the lung, (2) a COVID-19 diagnosis model, (3) an abnormal slices locating block to locate abnormal slices in positive cases, (4) a network visualization module for interpreting the attentional region of deep networks, and (5) an image phenotype analysis module for explaining the features of the attentional region.	./cache/cord-103533-k1lg8c7q.txt	./txt/cord-103533-k1lg8c7q.txt