-
公开(公告)号：US20230114934A1
公开(公告)日：2023-04-13
申请号：US18064366
申请日：2022-12-12
发明人： Rui Liao , Shun Miao , Pierre de Tournemire , Julian Krebs , Li Zhang , Bogdan Georgescu , Sasa Grbic , Florin Cristian Ghesu , Vivek Kumar Singh , Daguang Xu , Tommaso Mansi , Ali Kamen , Dorin Comaniciu
摘要： Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.
-
2.发明授权公开(公告)号：US10032281B1
公开(公告)日：2018-07-24
申请号：US15661675
申请日：2017-07-27
摘要： Multi-scale deep reinforcement learning generates a multi-scale deep reinforcement model for multi-dimensional (e.g., 3D) segmentation of an object. In this context, segmentation is formulated as learning an image-driven policy for shape evolution that converges to the object boundary. The segmentation is treated as a reinforcement learning problem, and scale-space theory is used to enable robust and efficient multi-scale shape estimation. By learning an iterative strategy to find the segmentation, the learning challenges of end-to-end regression systems may be addressed.
-
公开(公告)号：US11741605B2
公开(公告)日：2023-08-29
申请号：US18064366
申请日：2022-12-12
发明人： Rui Liao , Shun Miao , Pierre de Tournemire , Julian Krebs , Li Zhang , Bogdan Georgescu , Sasa Grbic , Florin Cristian Ghesu , Vivek Kumar Singh , Daguang Xu , Tommaso Mansi , Ali Kamen , Dorin Comaniciu
CPC分类号： G06T7/0012 , A61B5/7267 , G06T7/30 , G06T2207/20081
摘要： Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.
-
4.发明申请公开(公告)号：US20180322637A1
公开(公告)日：2018-11-08
申请号：US16015231
申请日：2018-06-22
CPC分类号： G06T7/12 , G06F19/321 , G06N3/0472 , G06N3/08 , G06T7/13 , G06T7/187 , G06T2207/10028 , G06T2207/20081 , G06T2207/20116 , G06T2207/20124 , G06T2207/30004
摘要： Multi-scale deep reinforcement learning generates a multi-scale deep reinforcement model for multi-dimensional (e.g., 3D) segmentation of an object. In this context, segmentation is formulated as learning an image-driven policy for shape evolution that converges to the object boundary. The segmentation is treated as a reinforcement learning problem, and scale-space theory is used to enable robust and efficient multi-scale shape estimation. By learning an iterative strategy to find the segmentation, the learning challenges of end-to-end regression systems may be addressed.
-
公开(公告)号：US20230368383A1
公开(公告)日：2023-11-16
申请号：US18351548
申请日：2023-07-13
发明人： Rui Liao , Shun Miao , Pierre de Tournemire , Julian Krebs , Li Zhang , Bogdan Georgescu , Sasa Grbic , Florin Cristian Ghesu , Vivek Kumar Singh , Daguang Xu , Tommaso Mansi , Ali Kamen , Dorin Comaniciu
CPC分类号： G06T7/0012 , G06T7/30 , A61B5/7267 , G06T2207/20081
摘要： Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.
-
公开(公告)号：US20200258227A1
公开(公告)日：2020-08-13
申请号：US16861353
申请日：2020-04-29
发明人： Rui Liao , Shun Miao , Pierre de Tournemire , Julian Krebs , Li Zhang , Bogdan Georgescu , Sasa Grbic , Florin Cristian Ghesu , Vivek Kumar Singh , Daguang Xu , Tommaso Mansi , Ali Kamen , Dorin Comaniciu
摘要： Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.
-
公开(公告)号：US09792531B2
公开(公告)日：2017-10-17
申请号：US15397638
申请日：2017-01-03
发明人： Bogdan Georgescu , Florin Cristian Ghesu , Yefeng Zheng , Dominik Neumann , Tommaso Mansi , Dorin Comaniciu , Wen Liu , Shaohua Kevin Zhou
IPC分类号： G06K9/62 , G06N3/08 , G06T7/00 , G06K9/20 , G06K9/66 , G06T7/70 , A61B8/08 , A61B5/055 , A61B5/00 , A61B8/00 , G06F19/00
CPC分类号： G06K9/6256 , A61B5/0044 , A61B5/055 , A61B6/032 , A61B6/5217 , A61B8/0883 , A61B8/4416 , A61B8/483 , A61B8/5223 , G06F19/00 , G06F19/321 , G06K9/2063 , G06K9/2081 , G06K9/4628 , G06K9/6267 , G06K9/627 , G06K9/66 , G06K2209/051 , G06N3/08 , G06N99/005 , G06T7/0012 , G06T7/70 , G06T7/73 , G06T2207/10016 , G06T2207/10088 , G06T2207/20016 , G06T2207/20081 , G06T2207/30048 , G06T2207/30204 , G16H50/20
摘要： Intelligent multi-scale image parsing determines the optimal size of each observation by an artificial agent at a given point in time while searching for the anatomical landmark. The artificial agent begins searching image data with a coarse field-of-view and iteratively decreases the field-of-view to locate the anatomical landmark. After searching at a coarse field-of view, the artificial agent increases resolution to a finer field-of-view to analyze context and appearance factors to converge on the anatomical landmark. The artificial agent determines applicable context and appearance factors at each effective scale.
-
公开(公告)号：US11185231B2
公开(公告)日：2021-11-30
申请号：US16829368
申请日：2020-03-25
发明人： Bogdan Georgescu , Florin Cristian Ghesu , Yefeng Zheng , Dominik Neumann , Tommaso Mansi , Dorin Comaniciu , Wen Liu , Shaohua Kevin Zhou
IPC分类号： A61B5/00 , G06K9/62 , G06N3/08 , G06T7/00 , G06K9/20 , G06K9/66 , G06T7/70 , A61B8/08 , A61B5/055 , A61B8/00 , A61B6/00 , G06K9/46 , G16H50/20 , A61B6/03 , G06T7/73 , G16H50/70 , G06N3/00 , G06N7/00 , G16H30/40 , G16H30/20
摘要： Intelligent multi-scale image parsing determines the optimal size of each observation by an artificial agent at a given point in time while searching for the anatomical landmark. The artificial agent begins searching image data with a coarse field-of-view and iteratively decreases the field-of-view to locate the anatomical landmark. After searching at a coarse field-of view, the artificial agent increases resolution to a finer field-of-view to analyze context and appearance factors to converge on the anatomical landmark. The artificial agent determines applicable context and appearance factors at each effective scale.
-
公开(公告)号：US20200242405A1
公开(公告)日：2020-07-30
申请号：US16829368
申请日：2020-03-25
发明人： Bogdan Georgescu , Florin Cristian Ghesu , Yefeng Zheng , Dominik Neumann , Tommaso Mansi , Dorin Comaniciu , Wen Liu , Shaohua Kevin Zhou
IPC分类号： G06K9/62 , A61B8/00 , A61B5/00 , A61B5/055 , A61B8/08 , G06T7/70 , G06K9/20 , G06K9/66 , G06T7/00 , G06N3/08 , G06N7/00 , G06N3/00 , G16H30/40 , G16H50/70 , G06T7/73 , A61B6/03 , G16H50/20 , G06K9/46 , A61B6/00
摘要： Intelligent multi-scale image parsing determines the optimal size of each observation by an artificial agent at a given point in time while searching for the anatomical landmark. The artificial agent begins searching image data with a coarse field-of-view and iteratively decreases the field-of-view to locate the anatomical landmark. After searching at a coarse field-of view, the artificial agent increases resolution to a finer field-of-view to analyze context and appearance factors to converge on the anatomical landmark. The artificial agent determines applicable context and appearance factors at each effective scale.
-
公开(公告)号：US10096107B2
公开(公告)日：2018-10-09
申请号：US15386856
申请日：2016-12-21
发明人： Florin Cristian Ghesu , Bogdan Georgescu , Dominik Neumann , Tommaso Mansi , Dorin Comaniciu , Wen Liu , Shaohua Kevin Zhou
IPC分类号： G06T7/00 , G06N99/00 , A61B8/08 , A61B8/00 , G16H50/20 , G06T7/11 , G06T7/70 , A61B5/055 , A61B5/00 , A61B6/03 , G06F19/00 , G06K9/62
摘要： Intelligent image parsing for anatomical landmarks and/or organs detection and/or segmentation is provided. A state space of an artificial agent is specified for discrete portions of a test image. A set of actions is determined, each specifying a possible change in a parametric space with respect to the test image. A reward system is established based on applying each action of the set of actions and based on at least one target state. The artificial agent learns an optimal action-value function approximator specifying the behavior of the artificial agent to maximize a cumulative future reward value of the reward system. The behavior of the artificial agent is a sequence of actions moving the agent towards at least one target state. The learned artificial agent is applied on a test image to automatically parse image content.
-
-
-
-
-
-
-
-
-
搜索结果
18 条记录 (耗时 0.019 秒)
