Zhihui Guo
University of Iowa
22 Papers
21 Citations
Zhihui Guo is an academic researcher from University of Iowa. The author has contributed to research in topics: Medicine & Image segmentation. The author has an hindex of 6, co-authored 16 publications. Previous affiliations of Zhihui Guo include Tsinghua University & Microsoft.
Chat about Author
Papers
Choroidal Features of Acute Macular Neuroretinopathy via Optical Coherence Tomography Angiography and Correlation With Serial Multimodal Imaging.
Sun Young Lee,Justine L Cheng,Karen M. Gehrs,James C. Folk,Elliott H. Sohn,Elliott H. Sohn,Stephen R. Russell,Stephen R. Russell,Zhihui Guo,Michael D. Abràmoff,Ian C. Han,Ian C. Han +11 more
TL;DR: It is suggested that areas of inner choroidal vascular flow void on OCTA are seen in patients with AMN and these areas may persist weeks after the onset of symptoms and suggest that vascular compromise of theinner choroid may be involved in the pathogenesis of AMN.
DeepCenterline: A Multi-task Fully Convolutional Network for Centerline Extraction
Zhihui Guo,Junjie Bai,Lu Yi,Xin Wang,Kunlin Cao,Qi Song,Milan Sonka,Youbing Yin +7 more
- 02 Jun 2019
TL;DR: This is the first deep-learning based centerline extraction method that guarantees single-pixel-wide centerline for a complex tree-structured object.
Quantitative muscle MRI as a sensitive marker of early muscle pathology in myotonic dystrophy type 1.
Ellen van der Plas,Laurie Gutmann,Laurie Gutmann,Dan Thedens,Richard K. Shields,Kathleen E. Langbehn,Zhihui Guo,Milan Sonka,Peggy Nopoulos +8 more
TL;DR: In this paper, the authors evaluated the utility of muscle MRI as a marker of muscle pathology and disease progression in adult-onset myotonic dystrophy type 1 (DM1) was evaluated.
12
•Posted Content
DeepCenterline: a Multi-task Fully Convolutional Network for Centerline Extraction
TL;DR: In this article, an end-to-end trainable multi-task fully convolutional network (FCN) with a minimal path extractor was proposed for coronary artery centerline extraction.
9
•Posted Content
Deep LOGISMOS: Deep Learning Graph-based 3D Segmentation of Pancreatic Tumors on CT scans
TL;DR: DeepLOGISMOS approach to 3D tumor segmentation is reported by incorporating boundary information derived from deep contextual learning to LOGISMOS — layered optimal graph image segmentation of multiple objects and surfaces to find the globally optimal solution.
8