Harvard University
Doctorates, Doctor of Philosophy, Philosophy
Harvard University
Doctor of Medicine, Doctorates, Medicine
Stanford University
Bachelors, Bachelor of Science, Engineering
Skills:
Medical Imaging Clinical Research Medical Education Science Neuroscience Research Cancer Clinical Trials Medicine Mri Machine Learning Deep Learning
Harvard Medical School 1998 - 2000
Doctor of Medicine, Doctorates, Medicine
Harvard University 1992 - 2000
Doctorates, Doctor of Philosophy, Engineering, Applied Physics, Physics, Philosophy
Us Patents
Method For Generating T1-Weighted Magnetic Resonance Images And Quantitative T1 Maps
Reed Busse - San Mateo CA, US John Pauly - Redwood City CA, US Greg Zaharchuk - San Francisco CA, US
International Classification:
G01V 3/00
US Classification:
324309000
Abstract:
Methods and systems for generating T-weighted images are provided. The method includes acquiring a pair of single-shot fast-spin-echo (SSFSE) images Sand S. The method further includes generating a T-weighted image Sbased on Sand S.
Arterial Spin Labeling Mri-Based Correction Factor For Improving Quantitative Accuracy Of Blood Flow And Volume Images
Roland Bammer - Palo Alto CA, US Greg Zaharchuk - Stanford CA, US
International Classification:
A61B 5/055
US Classification:
600411, 600419
Abstract:
Arterial spin labeling MRI is used to provide a patient specific correction factor to correct a image provided by a non-ASL imaging modality (e.g., DSC MRI). More specifically, a first blood flow image is taken using the non-ASL imaging modality, and a corresponding second blood flow image is taken with ASL. Some or all of the voxels in the first image are selected according to a predetermined selection method. A correction factor (CF) is computed to be the ratio of second image BF to first image BF averaged over the selected voxels. Thus, CF is the average of ASL/non-ASL blood flow over the selected voxels. This correction factor is applied to all voxels of an image equally, but can differ from patient to patient. This correction can be applied to one or more non-ASL blood flow images.
Systems And Methods For Improved Prognostics In Medical Imaging
- Stanford CA, US Greg Zaharchuk - Stanford CA, US
Assignee:
The Board of Trustees of the Leland Stanford Junior University - Stanford CA
International Classification:
G16B 40/20 G16B 5/20 G06N 20/00 G06N 3/02
Abstract:
Methods and systems for predicting biomarker progression in medical imaging is provided. A predictive model can be utilized to predict progression of a medical disorder as determined by progression of the predicted biomarker. Further, the predicted biomarker progression can be utilized to identify individuals that are fast progressors, moderate progressors, slow progressors. In some instances, the enrollment within clinical trials or treatment regimens are determined based on biomarker progression.
System And Method For Synthesizing Magnetic Resonance Images
- Schenetady NY, US - Stanford CA, US Greg ZAHARCHUK - Palo Alto CA, US John M. PAULY - Palo Alto CA, US
International Classification:
G06T 5/00 G06T 5/50 A61B 5/055 G06T 7/00
Abstract:
Methods and systems for synthesizing contrast images from a quantitative acquisition are disclosed. An exemplary method includes performing a quantification scan, using a trained deep neural network to synthesize a contrast image from the quantification scan, and outputting the contrast image synthesized by the trained deep neural network. In another exemplary method, an operator can identify a target contrast type for the synthesized contrast image. A trained discriminator and classifier module determines whether the synthesized contrast image is of realistic image quality and whether the synthesized contrast image matches the target contrast type.
Methods Of Predicting Disorder Progression For Control Arms Within An Experimental Trial
Methods of performing experimental treatments on a cohort of subjects are provided. A predictive model can be utilized to predict progression of a medical disorder or relevant imaging biomarker. The predicted medical disorder progression can be utilized as a control to determine whether an experimental treatment has an effect on the progression of the medical disorder. In some instances, the enrollment of subjects within a control group for clinical experiment is eliminated or reduced.
Mri Reconstruction Using Deep Learning, Generative Adversarial Network And Acquisition Signal Model
A method for diagnostic imaging includes measuring undersampled data y with a diagnostic imaging apparatus; linearly transforming the undersampled data y to obtain an initial image estimate {tilde over (x)}; applying the initial image estimate {tilde over (x)} as input to a generator network to obtain an aliasing artifact-reduced image x as output of the generator network, where the aliasing artifact-reduced image x is a projection onto a manifold of realistic images of the initial image estimate {tilde over (x)}; and performing an acquisition signal model projection of the aliasing artifact-reduced x onto a space of consistent images to obtain a reconstructed image {circumflex over (x)} having suppressed image artifacts.
System And Method For Magnetic Resonance Imaging An Object Via A Stochastic Optimization Of A Sampling Function
- SCHENECTADY NY, US - PALO ALTO CA, US GREG ZAHARCHUK - STANFORD CA, US JOHN PAULY - STANFORD CA, US
Assignee:
GENERAL ELECTRIC COMPANY - SCHENECTADY NY THE BOARD OF TRUSTEES OF THE LELAND STANFORD JUNIOR UNIVERSITY - PALO ALTO CA
International Classification:
G01R 33/561 G01R 33/54
Abstract:
A system for magnetic resonance imaging an object via a stochastic optimization of a sampling function is provided. The system includes a magnet assembly and a controller. The magnet assembly is operative to acquire MR data from the object. The controller is operative to: acquire a first MR data set using the magnet assembly; select the sampling function from a plurality of sampling function candidates based at least in part on the stochastic optimization; and acquire a second MR data set from the object using the magnet assembly based at least in part on the sampling function.
Quality Of Medical Images Using Multi-Contrast And Deep Learning
Greg Zaharchuk - Stanford CA, US Enhao Gong - Stanford CA, US John M. Pauly - Stanford CA, US
International Classification:
G06T 7/00 G06T 3/60
Abstract:
A method of improving diagnostic and functional imaging is provided by obtaining at least two input images of a subject, using a medical imager, where each input image includes a different contrast, generating a plurality of copies of the input images using non-local mean (NLM) filtering, using an appropriately programmed computer, where each input image copy of the subject includes different spatial characteristics, obtaining at least one reference image of the subject, using the medical imager, where the reference image includes imaging characteristics that are different form the input images of the subject, training a deep network model, using data augmentation on the appropriately programmed computer, to adaptively tune model parameters to approximate the reference image from an initial set of the input and reference images, with the goal of outputting an improved quality image of other sets of low SNR low resolution images, for analysis by a physician.
News
Stanford-led clinical trial shows broader benefits of acute-stroke therapy
clinical research manager Stephanie Kemp; senior research scientists Soren Christensen, PhD, and Michael Mlynash, MD; former postdoctoral scholar Jenny Tsai, MD, now at the Cleveland Clinic; clinical assistant professor of neurology Jeremy Heit, MD, PhD; associate professor of radiology Greg Zaharchuk
Date: Jan 24, 2018
Category: Health
Source: Google
Youtube
Lightning Talk: Deep Learning Revolution in M...
Greg Zaharchuk Professor, Radiology/Neuroi... and Neurointerventio......
Duration:
19m 29s
AI in Pediatric Imaging
In this webinar with Aimed, we're excited to have Stanford Neuroradiol...
Duration:
1h 1m 47s
The Imaging Wire Show - Subtle Medical's Effi...
The Imaging Wire's interview with Subtle Medical's Josh Gurewitz and G...
Duration:
30m
Greg Zaharchuk Deep Learning
Greg Zaharchuk Deep Learning.
Duration:
2m 46s
Greg Zaharchuk
Greg Zaharchuk Stroke Ukraine.
Duration:
5m 26s
Subtle Insights: "How Deep Learning and AI a...
Presented by Stanford Radiologist and Professor, Greg Zaharchuk, MD.
Duration:
28m 49s
Upstream AI: Strategies for Image Reconstruct...
Dr. Greg Zaharchuk, Stanford University Upstream AI: Strategies for Im...
Duration:
55m 3s
Imaging Elevated 2020 - Day 3, Oct 9th
Faculty host Dr. Donna Cross, keynote speaker Dr. Greg Zaharchuk (Stan...