Beihang University

Beijing Tiantan Hospital, Capital Medical University

Zixiao Li

Tao Liu

Yongjun Wang

Hao Liu

Ziyang Liu

Jing Jing

Lingling Ding

Shuo Zhang

Zhe Zhang

Yong Jiang

Yanhui Li

Pan Liu

Yu Zhou

Hong Xu

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 extracting a multi-dimensional disconnection network region of symptom mapping: registering a lesion image to a brain standard space; obtaining diffusion magnetic resonance images and resting-state functional magnetic resonance images of healthy control groups; constructing a structural disconnection weighting network corresponding to lesions using a fiber tracking method according to the lesion image in the brain standard space and the diffusion magnetic resonance images; constructing a functional significant disconnection network corresponding to the lesions using a cross-correlation verification method according to the lesion image in the brain standard space and the resting-state functional magnetic resonance images; and determining the multi-dimensional disconnection network region of the lesions of symptom mapping according to the structural disconnection weighting network and the functional significant disconnection network, where the multi-dimensional disconnection network region of the lesions is configured to locate network mapping of a brain lesion in the brain.

Method and system for extracting multi-dimensional disconnection network region of symptom mapping

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

Growing community of inventors

Beijing, China

Zixiao Li