Chen K.T.Gong E.De Carvalho Macruz F.B.Xu J.Boumis A.Khalighi M.Poston K.L.Sha S.J.Greicius M.D.Mormino E.Pauly J.M.Srinivas S.Zaharchuk G.TZE-HSIANG CHEN2022-05-242022-05-242020https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089556248&doi=10.1148%2fradiol.2020202527&partnerID=40&md5=56c5c06f02265758d1d95ef632c683bdhttps://scholars.lib.ntu.edu.tw/handle/123456789/611662This erratum corrects the network schematic in Figure 1. The network structure in Figure 1 should be as follows: The encoder portion consists of three sets of three 3 3 3 convolution (conv)-batch normalization (BN)-rectified linear unit activation (ReLU) operations, with 32, 32, and 64 tensors for the convolutions in each set respectively; 2 3 2 max-pooling is performed on the output of each set and fed into the next set. The center connection consists of one set of three 3 3 3 conv (64 tensors)-BN-ReLU operations; the result is added with the input of the center connection (residual connection) and passed on to the decoder portion. The decoder portion consists of three sets of three 3 3 3 conv-BN-ReLU operations, with 64, 32, and 32 tensors for the convolutions in each set respectively. The inputs of each set are a concatenation of the output of the previous set after 2 3 2 up-sampling and the output of its corresponding encoder set. A 1 31 convolution with hyperbolic tangent activation is performed on the output of the final decoder set and added to the original low-dose PET input to obtain the output image. ? 2020 Radiological Society of North America Inc.. All rights reserved.erratumcorrigendum10.1148/radiol.20202025272-s2.0-85089556248