Zhang Xiong Chen

US Patent:

20130245961, Sep 19, 2013

Filed:

Mar 13, 2013

Appl. No.:

13/802268

Inventors:

- Shatin, CN
Wai Kwun Rossa Chiu - Shatin, CN
Kwan Chee Chan - Mei Foo Sun Chuen, CN
Wenli Zheng - Shatin, CN
Hao Sun - Shatin, CN
Zhang Chen - Philadelphia PA, US

Assignee:

The Chinese University of Hong Kong - Shatin

International Classification:

G06F 19/16

US Classification:

702 20

Abstract:

This invention provides several ways of managing GC bias that occurs during seequencing and analysis of genomic DNA. Maternal plasma can be used as a source of fetal DNA for analysis. DNA segments or tags obtained from the plasma can be aligned with a chromosomal region of interest and with an artificial reference chromosome assembled from regions of the genome having matching GC content. This technology can be used, for example, to detect and evaluate aneuploidy and other chromosomal abnormalities

US Patent:

20220366535, Nov 17, 2022

Filed:

Apr 28, 2021

Appl. No.:

17/242473

Inventors:

- Shanghai, CN
Zhang Chen - Cambridge MA, US
Xiao Chen - Cambridge MA, US
Shanhui Sun - Cambridge MA, US
Terrence Chen - Cambridge MA, US

Assignee:

Shanghai United Imaging Intelligence Co., LTD. - Shanghai

International Classification:

G06T 3/40
G06T 11/00
G16H 30/40
G06N 3/08

Abstract:

An unsupervised machine learning method with self-supervision losses improves a slice-wise spatial resolution of 3D medical images with thick slices, and does not require high resolution images as the ground truth for training. The method utilizes information from high-resolution dimensions to increase a resolution of another desired dimension.

US Patent:

20220277836, Sep 1, 2022

Filed:

May 5, 2022

Appl. No.:

17/737694

Inventors:

- Shanghai, CN
Srikrishna Karanam - Bangalore, IN
Arun Innanje - Lexington MA, US
Shanhui Sun - Lexington MA, US
Abhishek Sharma - Boston MA, US
Yimo Guo - Lexington MA, US
Zhang Chen - Brookline MA, US

Assignee:

SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD. - Shanghai

International Classification:

G16H 30/40
G06T 7/00
G06T 7/90
G06T 17/00
G06T 7/50
G06T 7/70
G06K 9/62
G06T 17/20
G16H 10/60
G16H 30/20
A61B 5/00
G06V 10/40
G06V 10/42
G06V 20/64
G06V 40/10
G06V 40/20
G06V 20/62

Abstract:

A medical system may utilize a modular and extensible sensing device to derive a two-dimensional (2D) or three-dimensional (3D) human model for a patient in real-time based on images of the patient captured by a sensor such as a digital camera. The 2D or 3D human model may be visually presented on one or more devices of the medical system and used to facilitate a healthcare service provided to the patient. In examples, the 2D or 3D human model may be used to improve the speed, accuracy and consistency of patient positioning for a medical procedure. In examples, the 2D or 3D human model may be used to enable unified analysis of the patient's medical conditions by linking different scan images of the patient through the 2D or 3D human model. In examples, the 2D or 3D human model may be used to facilitate surgical navigation, patient monitoring, process automation, and/or the like.

US Patent:

20230079164, Mar 16, 2023

Filed:

Sep 15, 2021

Appl. No.:

17/475534

Inventors:

- Shanghai, CN
Zhang Chen - Brookline MA, US
Xiao Chen - Lexington MA, US
Terrence Chen - Lexington MA, US
Junshen Xu - Cambridge MA, US

Assignee:

Shanghai United Imaging Intelligence Co., Ltd. - Shanghai

International Classification:

G06T 7/30
G06N 3/02

Abstract:

Deep learning based systems, methods, and instrumentalities are described herein for registering images from a same imaging modality and different imaging modalities. Transformation parameters associated with the image registration task are determined using a neural ordinary differential equation (ODE) network that comprises multiple layers, each configured to determine a respective gradient update for the transformation parameters based on a current state of the transformation parameters received by the layer. The gradient updates determined by the multiple ODE layers are then integrated and applied to initial values of the transformation parameters to obtain final parameters for completing the image registration task. The operations of the ODE network may be facilitated by a feature extraction network pre-trained to determine content features shared by the input images. The input images may be resampled into different scales, which are then processed by the ODE network iteratively to improve the efficiency of the ODE operations.

US Patent:

20210272332, Sep 2, 2021

Filed:

Feb 28, 2020

Appl. No.:

16/804985

Inventors:

- Shanghai, CN
Shanhui Sun - Cambridge MA, US
Abhishek Sharma - Cambridge MA, US
Zhang Chen - Cambridge MA, US
Ziyan Wu - Cambridge MA, US

Assignee:

Shanghai United Imaging Intelligence Co., LTD. - Shanghai

International Classification:

G06T 11/00
G06T 1/20
G06T 19/20

Abstract:

A standalone image reconstruction device is configured to reconstruct the raw signals received from a radiology scanner device into a reconstructed output signal. The image reconstruction device is a vendor neutral interface between the radiology scanner device and the post processing imaging device. The reconstructed output signal is a user readable domain that can be used to generate a medical image or a three-dimensional (3D) volume. The apparatus is configured to reconstruct signals from different types of radiology scanner devices using any suitable image reconstruction protocol.

US Patent:

20210161422, Jun 3, 2021

Filed:

Oct 1, 2020

Appl. No.:

17/060860

Inventors:

- Shanghai, CN
Shanhui Sun - Cambridge MA, US
Zhang Chen - Cambridge MA, US
Terrence Chen - Cambridge MA, US

International Classification:

A61B 5/055
A61B 5/00
G06N 3/08
G01R 33/561

Abstract:

A method includes acquiring initial scout images of a patient's heart, using a neural network to establish a patient specific heart model, and automatically plan imaging planes of the patient specific heart model, performing an accelerated scan of the patient's heart, using the neural network to determine a current location and pose of the patient's heart from the accelerated scan, and to reposition the imaging planes to correspond to the current location and pose of the patient's heart, and using the repositioned imaging planes to perform an acquisition scan and generate an image of the patient's heart from the acquisition scan according to a selected imaging protocol.

US Patent:

20210166445, Jun 3, 2021

Filed:

Nov 29, 2019

Appl. No.:

16/699540

Inventors:

- Shanghai, CN
Zhang Chen - Cambridge MA, US
Shanhui Sun - Cambridge MA, US
Terrence Chen - Cambridge MA, US

International Classification:

G06T 11/00
G06T 3/40
G06N 3/04
G06N 3/08
G06F 17/14

Abstract:

A system for reconstructing magnetic resonance images includes a processor that is configured to obtain, from a magnetic resonance scanner, sub-sampled k-space data; apply an inverse fast fourier transform to the sub-sampled k-space data to generate a preliminary image; and process the preliminary image via a trained cascaded recurrent neural network to reconstruct a magnetic resonance image.

US Patent:

20210158510, May 27, 2021

Filed:

Sep 8, 2020

Appl. No.:

17/014573

Inventors:

- Shanghai, CN
Shanhui Sun - Lexington MA, US
Zhang Chen - Brookline MA, US
Terrence Chen - Lexington MA, US

Assignee:

SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD. - Shanghai

International Classification:

G06T 7/00
G06T 7/55
G06T 7/11
G06N 3/04

Abstract:

Described herein are neural network-based systems, methods and instrumentalities associated with estimating a thickness of an anatomical structure based on a visual representation of the anatomical structure and a machine-learned thickness prediction model. The visual representation may include an image or a segmentation mask of the anatomical structure. The thickness prediction model may be learned based on ground truth information derived by applying a partial differential equation such as Laplace's equation to the visual representation and solving the partial differential equation. When the visual representation includes an image of the anatomical structure, the systems, methods and instrumentalities described herein may also be capable of generating a segmentation mask of the anatomical structure based on the image.