S. Kevin Zhou
Chinese Academy of Sciences
200 Papers
807 Citations
S. Kevin Zhou is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 30, co-authored 152 publications. Previous affiliations of S. Kevin Zhou include University of Illinois at Urbana–Champaign & Siemens.
Chat about Author
Papers
Lymph node detection in 3-D chest CT using a spatial prior probability
Johannes Feulner,S. Kevin Zhou,Martin Huber,Joachim Hornegger,Dorin Comaniciu,Alexander Cavallaro +5 more
- 13 Jun 2010
TL;DR: A learned prior of the spatial distribution is proposed to model this knowledge and it is shown that the prior based detector yields a true positive rate of 52.3% for seven false positives per volume image, which is about two times better than without a spatial prior.
DuDoTrans: Dual-Domain Transformer for Sparse-View CT Reconstruction
Ce Wang,Kun Shang,Haimiao Zhang,Qian Li,S. Kevin Zhou +4 more
- 01 Jan 2022
TL;DR: Dual-Domain Transformer (DuDoTrans) is proposed to simultaneously restore informative sinograms via the long-range dependency modeling capability of Transformer and reconstruct CT image with both the enhanced and raw sinograms.
31
Segmentation of multiple knee bones from CT for orthopedic knee surgery planning.
Dijia Wu,Michal Sofka,Neil Birkbeck,S. Kevin Zhou +3 more
- 14 Sep 2014
TL;DR: A fully automated, highly precise, and computationally efficient segmentation approach for multiple bones that achieves simultaneous segmentation of femur, tibia, patella, and fibula with an overall accuracy of less than 1mm surface-to-surface error.
Multiple object detection by sequential monte carlo and Hierarchical Detection Network
Michal Sofka,Jingdan Zhang,S. Kevin Zhou,Dorin Comaniciu +3 more
- 13 Jun 2010
TL;DR: This paper presents an algorithm that optimally selects the order based on probability of states (object poses) within the ground truth region, and shows on 2D ultrasound images of left atrium, that the automatically selected sequential order yields low mean detection error.
Miss the Point: Targeted Adversarial Attack on Multiple Landmark Detection.
Qingsong Yao,Zecheng He,Hu Han,S. Kevin Zhou +3 more
- 04 Oct 2020
TL;DR: This paper is the first to study how fragile a CNN-based model on multiple landmark detection to adversarial perturbations is, and proposes a novel Adaptive Targeted Iterative FGSM (ATI-FGSM) attack against the state-of-the-art models in multiple landmarks detection.
29