-
1.
公开(公告)号:US20240331868A1
公开(公告)日:2024-10-03
申请号:US18573998
申请日:2022-06-22
发明人: Chukang ZHANG , Zhiwei HUANG , Hao ZHANG , Fanhua MING
CPC分类号: G16H50/30 , G06T7/0012 , G06V10/74 , G16H50/70 , G06T2207/20081 , G06T2207/20084 , G06T2207/30092 , G06V2201/032
摘要: The present invention provides a deep learning-based cancer prognosis survival prediction method and a device, and a storage medium. The method includes: data acquisition: acquiring sample data, where the sample data comprising pathological image data and clinical data of a sample; data preprocessing; prediction model training: training and evaluating a prediction model to obtain an optimal prediction model; and risk prediction: performing risk prediction on a new sample on the basis of an optimal classifier model and the optimal prediction model. In the method, data features of the pathological image data and clinical data are unified, the prediction model is trained and evaluated to obtain the optimal prediction model, and prognosis risk evaluation is performed on the new sample to enhance the efficiency of diagnosis and treatment in the clinical field and improve the accuracy of risk evaluation results.
-
2.
公开(公告)号:US20240070858A1
公开(公告)日:2024-02-29
申请号:US18260528
申请日:2021-12-14
发明人: Hang ZHANG , Hao ZHANG , Wenjin YUAN , Chukang ZHANG , Hui LIU , Zhiwei HUANG
IPC分类号: G06T7/00 , G06T5/20 , G06T7/11 , G06T7/20 , G06V10/764 , G06V10/771
CPC分类号: G06T7/0012 , G06T5/20 , G06T7/11 , G06T7/20 , G06V10/764 , G06V10/771 , G06T2207/10068 , G06T2207/20084
摘要: A capsule endoscope image recognition method based on deep learning, and a device and a medium is provided. After a plurality of frames of continuously captured images are processed to form an image sequence of a specific format, multi-channel recognition is performed on the plurality of frames of images by means of a 3D convolutional neural network model, and a recognition result is then output in combination with a recognition probability of each channel, such that the image recognition precision is improved.
-