-
公开(公告)号:US11756658B2
公开(公告)日:2023-09-12
申请号:US16327992
申请日:2018-05-16
Applicant: BOE TECHNOLOGY GROUP CO., LTD
Inventor: Lvwei Wang
IPC: G16H10/60 , G16H50/30 , G16H10/40 , G16H50/20 , G06F16/50 , G16H20/60 , G16H50/50 , G16H20/40 , G06F16/53 , G16H20/10 , G16H20/30
CPC classification number: G16H10/60 , G06F16/50 , G16H10/40 , G16H20/40 , G16H20/60 , G16H50/20 , G16H50/30 , G16H50/50 , G06F16/53 , G16H20/10 , G16H20/30
Abstract: A medical information query system is provided. The medical information query system includes: a processor and a memory, wherein the memory is configured to store computer instructions: and the processor is configured to load the computer instructions and execute: receiving clinical data and acquiring query rules matched with the clinical data; and inquiring medical information corresponding to the query rules in a graphic database.
-
公开(公告)号:US11636664B2
公开(公告)日:2023-04-25
申请号:US16053574
申请日:2018-08-02
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor: Yingying Li , Lvwei Wang
Abstract: The present disclosure provides a training method and device of a neural network for medical image processing, a medical image processing method and device, and an electronic apparatus for medical image processing based on a neural network. The training method includes performing a pre-processing process on an original image to obtain a pre-processed image, performing a data-augmenting process on the pre-processed image to obtain an augmented image retaining a pathological feature, the augmented image including at least one image with first resolution and at least one image with second resolution being higher than the first resolution, and training the neural network by selecting the image with first resolution and a part-cropping image from the image with second resolution as training samples.
-
公开(公告)号:US11170482B2
公开(公告)日:2021-11-09
申请号:US16619771
申请日:2018-08-20
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor: Lvwei Wang , Zhenglong Li , Yingying Li
Abstract: The present disclosure relates to an image processing method and a device, wherein the image processing method includes: acquiring a first image, the first image including an image formed with respect to a skin part of a patient to be diagnosed which needs diagnosis; inputting the first image into a neural network, to acquire position information of a pathologic change area in the first image; acquiring a boundary of the pathologic change area in the first image, acquiring an original image and a mask image which include the pathologic change area from the first image; fusing the mask image and the original image, obtaining a target image corresponding to the pathologic change area; wherein the target image is an image for diagnosing the pathologic change area, pixel points in the target image correspond to those in the original image and the mask image one by one.
-
公开(公告)号:US10772501B2
公开(公告)日:2020-09-15
申请号:US16013898
申请日:2018-06-20
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor: Lvwei Wang , Zhenglong Li , Hui Li
Abstract: A method and an electronic device for positioning an eyeball in a retinopathy image are disclosed. The method includes: using retinopathy image data with corresponding labeled data to train a deep learning network based on a loss function, so as to obtain a trained deep learning network; and processing retinopathy image data to be tested by using the trained deep learning network to obtain corresponding eyeball center coordinates and/or an eyeball diameter.
-
公开(公告)号:US20200167929A1
公开(公告)日:2020-05-28
申请号:US16613066
申请日:2018-11-23
Applicant: BOE Technology Group Co., Ltd.
Inventor: Lvwei Wang
Abstract: An image processing method. The method includes extracting features of an input image using a feature extraction network to generate and output a target feature map of the input image; and constructing and outputting a target mask map of the input image using a mask construction network based on the target feature map. The feature extraction network includes a feature input layer, a feature intermediate layer, and a feature output layer sequentially connected together. The mask construction network includes a mask input layer, a mask intermediate layer, and a mask output layer sequentially connected together. The feature output layer is connected to the mask input layer. The feature intermediate layer is connected to the mask intermediate layer. The feature input layer is connected to the mask output layer.
-
公开(公告)号:US20190059719A1
公开(公告)日:2019-02-28
申请号:US16013898
申请日:2018-06-20
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor: Lvwei Wang , Zhenglong Li , Hui Li
Abstract: A method and an electronic device for positioning an eyeball in a retinopathy image are disclosed. The method includes: using retinopathy image data with corresponding labeled data to train a deep learning network based on a loss function, so as to obtain a trained deep learning network; and processing retinopathy image data to be tested by using the trained deep learning network to obtain corresponding eyeball center coordinates and/or an eyeball diameter.
-
公开(公告)号:US11024066B2
公开(公告)日:2021-06-01
申请号:US16301594
申请日:2018-02-28
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor: Lvwei Wang
Abstract: A presentation generating system of medical images includes: a memory and a processor. The memory stores computer program instructions. The processor executes the following operations while loading the program instructions: acquiring 2D medical image; extracting image features of the medical images and transforming the image features into image feature vectors and outputting them to a first vector space established in advance; determining and outputting semantic feature vectors corresponding to the image feature vectors according to a correspondence between image feature vectors contained in the pre-established first vector space and the matching semantic feature vectors contained in the second vector space; and transforming and outputting semantic feature vectors that match the image feature vectors into corresponding natural language. Further provided are a training method for the presentation generating system and a presentation generating method.
-
公开(公告)号:US10997725B2
公开(公告)日:2021-05-04
申请号:US16613066
申请日:2018-11-23
Applicant: BOE Technology Group Co., Ltd.
Inventor: Lvwei Wang
Abstract: An image processing method. The method includes extracting features of an input image using a feature extraction network to generate and output a target feature map of the input image; and constructing and outputting a target mask map of the input image using a mask construction network based on the target feature map. The feature extraction network includes a feature input layer, a feature intermediate layer, and a feature output layer sequentially connected together. The mask construction network includes a mask input layer, a mask intermediate layer, and a mask output layer sequentially connected together. The feature output layer is connected to the mask input layer. The feature intermediate layer is connected to the mask intermediate layer. The feature input layer is connected to the mask output layer.
-
公开(公告)号:US20190065994A1
公开(公告)日:2019-02-28
申请号:US16006740
申请日:2018-06-12
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor: Lvwei Wang , Zhenglong Li
Abstract: A deep learning-based image recognition method and apparatus are disclosed. The deep learning-based image recognition method comprises: training deep learning models based on deep learning frameworks, by using training image data, to obtain at least two deep learning models; selecting a predetermined number of deep learning models from the obtained deep learning models in a descending order of their recognition accuracies for verification image data, wherein the predetermined number is less than or equal to the number of the obtained deep learning models; and recognizing image data to be recognized using at least one of the selected deep learning models.
-
10.
公开(公告)号:US20190065884A1
公开(公告)日:2019-02-28
申请号:US16053574
申请日:2018-08-02
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor: Yingying Li , Lvwei Wang
Abstract: The present disclosure provides a training method and device of a neural network for medical image processing, a medical image processing method and device, and an electronic apparatus for medical image processing based on a neural network. The training method includes performing a pre-processing process on an original image to obtain a pre-processed image, performing a data-augmenting process on the pre-processed image to obtain an augmented image retaining a pathological feature, the augmented image including at least one image with first resolution and at least one image with second resolution being higher than the first resolution, and training the neural network by selecting the image with first resolution and a part-cropping image from the image with second resolution as training samples.
-
-
-
-
-
-
-
-
-