专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2022207443A1 REINFORCED ATTENTION 审中-公开
公开(公告)号：WO2022207443A1
公开(公告)日：2022-10-06
申请号：PCT/EP2022/057746
申请日：2022-03-24
申请人： BAYER AKTIENGESELLSCHAFT
发明人： LENGA, Matthias , PURTORAB, Marvin , RAMOS DOS SANTOS, Thiago , HOOGE, Jens , CORONA, Veronica
IPC分类号： G06N3/00 , G06N3/04 , G06N3/08 , G06N7/00 , G06N3/006 , G06N3/0454 , G06N7/005
摘要： The present invention relates to the technical field of machine learning. Subject matter of the present invention is a novel approach for training a neural network and the use of this approach for the processing of (medical) images.

2. 发明申请

WO2022179896A2 ACTOR-CRITIC APPROACH FOR GENERATING SYNTHETIC IMAGES 审中-公开
公开(公告)号：WO2022179896A2
公开(公告)日：2022-09-01
申请号：PCT/EP2022/053756
申请日：2022-02-16
申请人： BAYER AKTIENGESELLSCHAFT
发明人： RAMOS DOS SANTOS, Thiago , CORONA, Verona , PURTORAB, Marvin , LORIO, Sara
IPC分类号： G06T1/00 , G06T5/00 , G06T7/10 , G06T2207/10072 , G06T2207/10116 , G06T2207/10132 , G06T2207/20081 , G06T2207/20084 , G06T2207/30004
摘要： The present invention provides a technique for model improvement in supervised learning with potential applications to a variety of imaging tasks, such as segmentation, registration, detection. In particular, it has shown potential in medical imaging enhancement.

3. 发明申请

WO2022223383A1 IMPLICIT REGISTRATION FOR IMPROVING SYNTHESIZED FULL-CONTRAST IMAGE PREDICTION TOOL 审中-公开
公开(公告)号：WO2022223383A1
公开(公告)日：2022-10-27
申请号：PCT/EP2022/059836
申请日：2022-04-13
申请人： BAYER AKTIENGESELLSCHAFT
发明人： CORONA, Veronica , PURTORAB, Marvin , LORIO, Sara , RAMOS DOS SANTOS, Thiago
IPC分类号： G06T5/50
摘要： The invention provides a method of training a prediction tool to generate at least one synthetic full-contrast image from zero-contrast and low-contrast images of a subject, the method comprising the steps of: receiving a training set, the training set comprising a set of images of a set of subjects, for each subject of the set of subjects: i) a full-contrast image acquired with a full-contrast agent dose administered to the subject; ii) a low-contrast image acquired with a low-contrast agent dose administered to the subject, where the low-contrast agent dose is less than the full-contrast agent dose; iii) a first zero-contrast image acquired with no contrast agent dose administered to the subject wherein the first zero-contrast image is acquired prior to the acquisition of the full-contrast image; and iv) a second zero-contrast image acquired with no contrast agent dose administered to the subject wherein the second zero-contrast image is acquired prior to the acquisition of the low-contrast image; and training an artificial neural network with the received training set, by applying the first and second zero-contrast images from the set of images and the low-contrast images from the set of images as input to the artificial neural network and using a cost function to compare the output of the artificial neural network with the full-contrast images from the set of images to train parameters of the artificial neural network using backpropagation.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式