- 专利标题: IMAGE SCORING USING ERROR PREDICTION
-
申请号: PCT/JP2021/026607申请日: 2021-07-15
-
公开(公告)号: WO2022014672A1公开(公告)日: 2022-01-20
- 发明人: GREENBLATT Elliot , SIEGELMAN Jenifer , YARDIBI Ozlem
- 申请人: TAKEDA PHARMACEUTICAL COMPANY LIMITED
- 申请人地址: 1-1, Doshomachi 4-chome, Chuo-ku, Osaka-shi, Osaka
- 专利权人: TAKEDA PHARMACEUTICAL COMPANY LIMITED
- 当前专利权人: TAKEDA PHARMACEUTICAL COMPANY LIMITED
- 当前专利权人地址: 1-1, Doshomachi 4-chome, Chuo-ku, Osaka-shi, Osaka
- 代理机构: OHNO Seiji et al.
- 优先权: US63/052,293 2020-07-15
- 主分类号: G06T7/00
- IPC分类号: G06T7/00 ; G06T7/11
摘要:
A method (600) for scoring image data using error prediction includes receiving a frame of image data (20) representative of an intensity of a condition. The method also includes processing, using a neural network (110), the frame of image data. The method also includes predicting, by the neural network, an intensity value (120) of the condition based on the frame of image data. The method also includes predicting, by the neural network, an error value (130) of the predicted intensity value. The error value is representative of a difference between the predicted intensity value and a ground truth intensity value (122) of the frame of image data.