G
Gengyan Zhao
Researcher at University of Wisconsin-Madison
Publications - 16
Citations - 693
Gengyan Zhao is an academic researcher from University of Wisconsin-Madison. The author has contributed to research in topics: Deep learning & Convolutional neural network. The author has an hindex of 8, co-authored 14 publications receiving 467 citations. Previous affiliations of Gengyan Zhao include Tianjin University.
Papers
More filters
Journal ArticleDOI
Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging.
TL;DR: A new fully automated musculoskeletal tissue segmentation method using deep convolutional neural network (CNN) and three‐dimensional (3D) simplex deformable modeling to improve the accuracy and efficiency of cartilage and bone segmentation within the knee joint.
Journal ArticleDOI
Deep convolutional neural network for segmentation of knee joint anatomy.
TL;DR: A new segmentation method using deep convolutional neural network, 3D fully connected conditional random field, and 3D simplex deformable modeling to improve the efficiency and accuracy of knee joint tissue segmentation is described and evaluated.
Journal ArticleDOI
A deep learning approach for 18 F-FDG PET attenuation correction
TL;DR: An automated approach is developed that allows generation of a continuously valued pseudo-CT from a single 18F-FDG non-attenuation-corrected (NAC) PET image and evaluated it in PET/CT brain imaging and provides quantitatively accurate 18F -FDG PET results with average errors of less than 1% in most brain regions.
Journal ArticleDOI
Bayesian convolutional neural network based MRI brain extraction on nonhuman primates.
TL;DR: A novel deep learning based brain extraction method that takes the complete 3D context into consideration and can generate model uncertainty maps for each prediction is proposed and outperforms 6 state‐of‐the art software packages and 3 deep learning methods on a 100‐subject nonhuman primate dataset.
Journal ArticleDOI
Technical Note: Deep learning based MRAC using rapid ultrashort echo time imaging.
TL;DR: The proposed MRAC method utilizing deep learning with transfer learning and an efficient dRHE acquisition enables reliable PET quantitation with accurate and rapid pseudo CT generation and produced relative PET errors less than 1% within most brain regions.