Beijing Tiantan Hospital, Capital Medical University

Beihang University

Microsoft Technology Licensing, LLC

Jing Jing

Tao Liu

Yongjun Wang

Ziyang Liu

Zixiao Li

Hao Liu

Shuo Zhang

Zhe Zhang

Yong Jiang

Yanhui Li

Pan Liu

Yu Zhou

Sandhya Vankamamidi

Ali Alam

Gerardo Bodegas Martinez

Lingling Ding

Ayyappan Balasubramanian

Can Zheng

Hong Xu

Alka Garg

Amanda Holcomb

James Paul Gyarmathy

Carrie Ann Culley

Hardeep Kohli

Zhuang Gao

John Kingsly Masilamani

Rohan Kamath

Michael Todd

Jack Pullikottil

Xuewei Xie

Mansi Singhal

Xia Meng

This application relates to the technical field of image recognition, and provides a method for evaluating a diffusion weighted imaging (DWI)-fluid attenuated inversion recovery (FLAIR) mismatch, an apparatus, a medium, and a product. The method includes: obtaining a DWI image and a FLAIR image of a target object; applying a first image segmentation model to segment the DWI image to obtain a first image segmentation result; applying a second image segmentation model to segment the FLAIR image to obtain a second image segmentation result; registering the second image segmentation result onto the first image segmentation result to obtain a registered second image segmentation result; and applying a Dice metric to evaluate a degree of mismatch between the first image segmentation result and the registered second image segmentation result. This application can improve efficiency of determining whether DWI and FLAIR are matched.

Method for evaluating DWI-flair mismatch, apparatus, medium, and product

A method and system for processing an intracranial large vessel image, an electronic device, and a medium are provided. The method includes: acquiring original intracranial large vessel images of a target to be identified and a sample subject; applying a cerebrovascular segmentation model to obtain cerebrovascular mask images; computing regions of interest of the cerebrovascular mask images and bounding boxes; selecting corresponding regions of interest from the original intracranial large vessel images; separately preprocessing the mask image regions of interest and the original image regions of interest to obtain images to be processed; annotating a target region in the image to be processed of the sample subject; training a convolutional neural network model with a training set to obtain a cerebrovascular occlusion classification model; and inputting the image to be processed of the target to be identified to the cerebrovascular occlusion classification model to obtain a target region identification result.

Method and system for processing intracranial large vessel image, electronic device, and medium

A regionally integrated emergency stroke unit includes an information interaction area, an imaging examination area, and a thrombolytic therapy area. A doctor workstation, a comprehensive information surveillance monitor, and a process support artificial intelligence (AI) assistant are set in the information interaction area. A test device, a first television display, a movable low-field magnetic resonance imager, and an AI-assisted decision-making system are set in the imaging examination area. The process support AI assistant performs, via voice interaction or touchscreen keying interaction, automatic inquiry and auxiliary nervous system scale scoring, and further provides real-time retrieval support for a knowledge base and a clinical guideline. The AI-assisted decision-making system is configured to assist in decision-making based on an automatic inquiry result, a scale score result, the test result, and magnetic resonance imaging results of the head and neck, to generate and display a therapy regimen.

Regionally integrated emergency stroke unit

Methods, systems, and computer programs are presented for managing access to resources using scenarios. One method includes an operation for storing first scenario data received for a first control scenario. The first scenario data comprises a control scenario identifier, a first resource, an authorization control, and a scenario trigger that defines an event that causes an activation of the first control scenario for providing access to the first resource. Further, the method includes operations for monitoring for an occurrence of the scenario trigger and detecting an occurrence of the event associated with the scenario trigger. Further, the method determines, in response to the occurrence of the event, a set of users authorized to access the first resource, including accessing the first scenario data to determine the set of users associated with the authorization control. Furthermore, access is provided to the set of users based on the determining.

Scenario-based access control

Growing community of inventors

Beijing, China

Jing Jing