-
公开(公告)号：US20240394846A1
公开(公告)日：2024-11-28
申请号：US18787991
申请日：2024-07-29
Inventor： Yawen HUANG , Yefeng ZHENG , LE ZHANG
Abstract: A training method includes: obtaining a first sample image and at least two types of second sample images; respectively adding at least two damage feature corresponding to the second sample images to the first sample image, to generate at least two types of single degradation images; fusing the single degradation images, to obtain a multiple degradation image corresponding to the first sample image; performing image reconstruction processing on the multiple degradation image, to generate a predicted reconstruction image corresponding to the multiple degradation image; calculating a loss function value based on the second sample images, the single degradation images, the first sample image, and the predicted reconstruction image; and updating a model parameter of the model based on the loss function value.
-
2.发明申请公开(公告)号：US20220036550A1
公开(公告)日：2022-02-03
申请号：US17503160
申请日：2021-10-15
Inventor： Fubo ZHANG , Dong WEI , Kai MA , Yefeng ZHENG
Abstract: The present disclosure provides an artificial intelligence-based (AI-based) medical image processing method performed by a computing device, and a non-transitory computer-readable storage medium. The AI-based medical image processing method includes: processing a medical image to generate an encoded intermediate image; processing the encoded intermediate image, to segment a first feature and generate a segmented intermediate image; processing the encoded intermediate image and the segmented intermediate image based on an attention mechanism, to generate a detected intermediate input image; and performing second feature detection on the detected intermediate input image, to determine whether an image region of the detected intermediate input image in which the first feature is located comprises a second feature.
-
公开(公告)号：US20210233247A1
公开(公告)日：2021-07-29
申请号：US17229707
申请日：2021-04-13
Inventor： Shilei CAO , Kai MA , Yefeng ZHENG
Abstract: This application relates to a medical image segmentation method, a computer device, and a storage medium. The method includes: obtaining medical image data; obtaining a target object and weakly supervised annotation information of the target object in the medical image data; determining a pseudo segmentation mask for the target object in the medical image data according to the weakly supervised annotation information; and performing mapping on the medical image data by using a preset mapping model based on the pseudo segmentation mask, to obtain a target segmentation result for the target object. Because the medical image data is segmented based on the weakly supervised annotation information, there is no need to annotate information by using much labor during training of the preset mapping model, thereby saving labor costs. The preset mapping model is a model used for mapping the medical image data based on the pseudo segmentation mask.
-
4.发明公开公开(公告)号：US20240078756A1
公开(公告)日：2024-03-07
申请号：US18386940
申请日：2023-11-03
Inventor： Yawen HUANG , Yefeng ZHENG
CPC classification number: G06T19/00 , G06T7/12 , G06T7/174 , G06T7/40 , G06T15/04 , G06T2200/04 , G06T2207/20021 , G06T2207/20076 , G06T2207/20081 , G06T2207/20084 , G06T2210/32 , G06T2210/41
Abstract: An image generation method includes obtaining a modality image corresponding to a first modality, and performing modality conversion on the modality image through a first candidate network to obtain a generated image corresponding to a second modality different from the first modality. The generated image is a three-dimensional image. The method further includes performing modality restoration on the generated image through a second candidate network to obtain a restored image corresponding to the first modality and obtaining a constraint loss value based on a modality conversion effect of the generated image and a modality restoration effect of the restored image. The constraint loss value indicates a mapping loss in mapping the modality image to a three-dimensional image space by the first candidate network. The method also includes training the first candidate network based on the constraint loss value to obtain an image conversion network.
-
公开(公告)号：US20220036187A1
公开(公告)日：2022-02-03
申请号：US17502847
申请日：2021-10-15
Inventor： Dong WEI , Kai MA , Yefeng ZHENG
Abstract: A sample generation method outputs a dummy sample set generated by a trained sample generation network that operates on spliced vectors formed by combining real category feature vectors extracted from real samples with real category label vectors corresponding to the real samples. The trained sample generation network is trained using real samples and dummy samples that are generated by an intermediate sample generation network operating on the spliced vectors. The training includes inputting the real samples and the dummy samples to an intermediate sample discrimination network, performing iterative adversarial training of the intermediate sample generation network and the intermediate sample discrimination network until an iteration stop condition is met. As a result, the dummy sample set output by the trained sample generation network includes dummy samples that are not easily differentiated from real samples and that are already labeled with category information, for accurate use in training classifiers.
-
Patent Agency Ranking
公开(公告)号：US20220028087A1
公开(公告)日：2022-01-27
申请号：US17499993
申请日：2021-10-13
Inventor： Yifan HU , Yefeng ZHENG
Abstract: The present disclosure provides methods, devices, apparatus, and storage medium for determining a target image region of a target object in a target image. The method includes: obtaining a target image comprising a target object; obtaining an original mask and an image segmentation model, the image segmentation model comprising a first unit model and a second unit model; downsampling the original mask based on a pooling layer in the first unit model to obtain a downsampled mask; extracting region convolution feature information of the target image based on a convolution pooling layer in the second unit model and the downsampled mask; updating the original mask according to the region convolution feature information; and in response to the updated original mask satisfying an error convergence condition, determining a target image region of the target object in the target image according to the updated original mask.
-
7.发明申请公开(公告)号：US20210251590A1
公开(公告)日：2021-08-19
申请号：US17246339
申请日：2021-04-30
Inventor： Heng GUO , Xingde YING , Kai MA , Yefeng ZHENG
Abstract: This disclosure discloses a CT image generation method and apparatus, a computer device, and a computer-readable storage medium. The method includes: obtaining a first X-ray image and a second X-ray image, the first X-ray image and the second X-ray image being X-ray images acquired for a target object from two orthogonal viewing angles; calling a generator to perform three-dimensional reconstruction on the first X-ray image and the second X-ray image, to obtain a three-dimensional model of the target object; and obtaining a CT image of the target object according to the three-dimensional model of the target object.
-
8.发明公开公开(公告)号：US20230376120A1
公开(公告)日：2023-11-23
申请号：US18227857
申请日：2023-07-28
Inventor： Xiaolin HONG , Qingqing ZHENG , Xinmin Wang , Kai MA , Yefeng ZHENG
CPC classification number: G06F3/017 , G06T5/002 , G06N3/045 , G06T2207/20081 , G06T2207/20084
Abstract: This application provides a gesture information processing method and apparatus, an electronic device, and a storage medium. The method includes: acquiring an electromyography signal sample generated by an electromyography signal collection target object in connection with performing multiple gestures; dividing the electromyography signal sample through a sliding window having a fixed window value and a fixed stride into different electromyography signals of the target object; and applying the different electromyography signals to a first neural network model to determine gesture information matching the multiple gestures performed by the target object.
-
公开(公告)号：US20230097391A1
公开(公告)日：2023-03-30
申请号：US18071106
申请日：2022-11-29
Inventor： Luyan LIU , Kai MA , Yefeng ZHENG
IPC: G06V10/776 , G06V10/764 , G06V20/70 , G06V10/762
Abstract: An image processing method can reduce costs related to manual labeling, improve training efficiency, and increase a quantity of training samples, thereby improving the accuracy of an image classification model. First images and second images are processed using an image classification model to obtain predicted classification results. The first images include a classification label and the second images include a pseudo classification label. A first loss value indicating accuracy is acquired based on the predicted classification results, the corresponding classification labels, and the corresponding pseudo classification labels. A second loss value indicating accuracy is acquired based on the predicted classification results and the corresponding pseudo classification labels. A model parameter of the image classification model is updated based on the first loss value and the second loss value. Classification processing and acquisition is performed until a target image classification model is obtained.
-
10.发明申请公开(公告)号：US20230080533A1
公开(公告)日：2023-03-16
申请号：US17992759
申请日：2022-11-22
Inventor： Luyan LIU , Kai MA , Yefeng ZHENG
Abstract: An electroencephalogram signal classification method includes: obtaining a first electroencephalogram signal; processing the first electroencephalogram signal using at least two electroencephalogram signal classification models to obtain respective motor imagery probability distributions from the at least two electroencephalogram signal classification models; and determining a motor imagery type of the first electroencephalogram signal based on the motor imagery probability distributions. A plurality of electroencephalogram signal classification models is respectively trained using an augmented data set obtained through augmentation. During prediction, by combining the plurality of electroencephalogram signal classification models, the accuracy of classifying an electroencephalogram signal to determine a motor imagery type may be improved, when using a model trained with a relatively small number of training samples.
-
-
-
-
-
-
-
-
-
Search Results
34
records
(took 0.022 seconds)
