公开(公告)号：US20240273720A1

公开(公告)日：2024-08-15

申请号：US18641184

申请日：2024-04-19

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Zhongyi Yang ,  Sen Yang ,  Jinxi Xiang ,  Jun Zhang ,  Xiao Han

IPC分类号： G06T7/00 ,  G06T3/40 ,  G06T7/11 ,  G06T7/194 ,  G06V10/42 ,  G06V10/44 ,  G06V10/764

CPC分类号： G06T7/0012 ,  G06T3/40 ,  G06T7/11 ,  G06T7/194 ,  G06V10/42 ,  G06V10/44 ,  G06V10/764 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30096 ,  G06V2201/03

摘要： This application discloses a method for determining a lesion region, and a model training method and apparatus, and relates to the field of computer vision technologies. The method includes the following steps: sampling a pathological image by a first sampling way to obtain at least two first instance images (310); determining a candidate lesion region in the pathological image, based on feature information extracted from the at least two first instance images (320); sampling the candidate lesion region by a second sampling way to obtain at least two second instance images, where an overlap degree between the second instance images is greater than that between the first instance images (330); and determining lesion indication information of the pathological image, based on feature information extracted from the at least two second instance images, where the lesion indication information is used for indicating the lesion region in the pathological image (340). In this application, the consumption of human resources is reduced, and costs required to determine the lesion region are saved.

公开(公告)号：US20230237771A1

公开(公告)日：2023-07-27

申请号：US18127657

申请日：2023-03-29

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Qingfu Wen ,  Yuexi Du ,  Sen Yang ,  Peng Yang ,  Jun Zhang ,  Xiao Han

IPC分类号： G06V10/77 ,  G06T7/00

CPC分类号： G06V10/7715 ,  G06T7/0012 ,  G06T2207/20081 ,  G06V2201/031

摘要： The present application provides a self-supervised learning method performed by a computer device. The method includes: performing a data enhancement on an original medical image to obtain a first enhanced image and a second enhanced image, the first enhanced image and the second enhanced image being positive samples of each other; performing feature extractions on the first enhanced image and the second enhanced image by a feature extraction model to obtain a first image feature of the first enhanced image and a second image feature of the second enhanced image; determining a model loss of the feature extraction model based on the first image feature, the second image feature, and a negative sample image feature, the negative sample image feature being an image feature corresponding to other original medical images; and training the feature extraction model based on the model loss.