id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-154091-uuupn82y	Xu, Zhanwei	GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation	2020-10-19		.txt	text/plain	6364	397	56	The proposed framework is designed to mine the potential knowledge contained in many COVID-19 positive and negative CT volumes by embedding Generative Adversarial training in a standard Segmentation Network, referred to as GASNet, and hence its demand for voxel-level annotations is very small. When using only one voxel-level labeled sample in training, GASNet obtains a 70% Dice score on a public COVID-19 lesion segmentation dataset [5] , comparable to representative fully-supervised algorithms (U-Net [21] , V-Net [22] , and UNet ++ [23] ) requiring a large number of voxel-level annotated samples. We will also detail a simple but effective method of generating COVID-19 positive CT volumes with voxel-level pseudo-label to improve the segmentation performance of GASNet. Finally, we provide the implementation details, including the specific structure, data preprocessing, and the training hyperparameters.	./cache/cord-154091-uuupn82y.txt	./txt/cord-154091-uuupn82y.txt