K
Kevin Chen
Researcher at Stanford University
Publications - 44
Citations - 2235
Kevin Chen is an academic researcher from Stanford University. The author has contributed to research in topics: Iterative reconstruction & Standardized uptake value. The author has an hindex of 13, co-authored 39 publications receiving 1905 citations. Previous affiliations of Kevin Chen include Harvard University & National Taiwan University.
Papers
More filters
Proceedings ArticleDOI
CarTel: a distributed mobile sensor computing system
Bret Hull,Vladimir Bychkovsky,Yang Zhang,Kevin Chen,Michel Goraczko,Allen Miu,Eugene Shih,Hari Balakrishnan,Samuel Madden +8 more
TL;DR: CarTel has been deployed on six cars, running on a small scale in Boston and Seattle for over a year, and has been used to analyze commute times, analyze metropolitan Wi-Fi deployments, and for automotive diagnostics.
Journal ArticleDOI
An SPM8-Based Approach for Attenuation Correction Combining Segmentation and Nonrigid Template Formation: Application to Simultaneous PET/MR Brain Imaging
David Izquierdo-Garcia,Adam E. Hansen,Stefan Förster,Didier Benoit,Sylvia Schachoff,Sebastian Fürst,Kevin Chen,Kevin Chen,Daniel B. Chonde,Daniel B. Chonde,Ciprian Catana +10 more
TL;DR: An SPM8-based approach for deriving the head μ map from MR data to be used for PET AC in integrated PET/MR scanners is accurate and robust, combining the strengths of both segmentation- and atlas-based approaches while minimizing their drawbacks.
Journal ArticleDOI
Ultra–Low-Dose 18F-Florbetaben Amyloid PET Imaging Using Deep Learning with Multi-Contrast MRI Inputs
Kevin Chen,Enhao Gong,Fabiola Macruz,Junshen Xu,Athanasia Boumis,Mehdi Khalighi,Kathleen L. Poston,Sharon J. Sha,Michael D. Greicius,Elizabeth C. Mormino,John M. Pauly,S. Srinivas,Greg Zaharchuk +12 more
TL;DR: Simultaneously acquired MRI and ultra-low-dose PET data can be used to synthesize full-dose-like amyloid PET images, which showed marked improvement on all quality metrics compared with the low-dose image.
Journal ArticleDOI
Ultra‐low‐dose PET Reconstruction using Generative Adversarial Network with Feature Matching and Task‐Specific Perceptual Loss
TL;DR: Standard-dose amyloid PET images can be synthesized from ultra-low-dose images using GAN by applying adversarial learning, feature matching, and task-specific perceptual loss to ensure image quality and the preservation of pathological features.
Journal ArticleDOI
Anatomically-aided PET reconstruction using the kernel method.
TL;DR: The kernel method is extended, to incorporate anatomical side information into the PET reconstruction model and results in reduced noise at a matched contrast level compared with the conventional ML expectation maximization algorithm.