-
公开(公告)号：US20210142475A1
公开(公告)日：2021-05-13
申请号：US17122788
申请日：2020-12-15
发明人： Junning Li , Pechin Chien Pau Lo , Ahmed Taha , Tao Zhao
摘要： A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.
-
2.发明公开公开(公告)号：US20230252634A1
公开(公告)日：2023-08-10
申请号：US18299612
申请日：2023-04-12
发明人： Junning Li , Pechin Chien Pau Lo , Ahmed Taha , Tao Zhao
CPC分类号： G06T7/0012 , A61B34/10 , G06T7/12 , A61B34/20 , G06T2207/30101 , A61B2034/2065
摘要： A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.
-
公开(公告)号：US12033325B2
公开(公告)日：2024-07-09
申请号：US18299612
申请日：2023-04-12
发明人： Junning Li , Pechin Chien Pau Lo , Ahmed Taha , Tao Zhao
CPC分类号： G06T7/0012 , A61B34/10 , A61B34/20 , G06T7/12 , A61B2034/2065 , G06T2207/30101
摘要： A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting at least one of a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The weighting that at least one of the plurality of volumetric units includes applying a weight based on a foreground structure classification. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.
-
公开(公告)号：US11657502B2
公开(公告)日：2023-05-23
申请号：US17122788
申请日：2020-12-15
发明人： Junning Li , Pechin Chien Pau Lo , Ahmed Taha , Tao Zhao
CPC分类号： G06T7/0012 , A61B34/10 , A61B34/20 , G06T7/12 , A61B2034/2065 , G06T2207/30101
摘要： A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.
-
公开(公告)号：US20220254104A1
公开(公告)日：2022-08-11
申请号：US17617869
申请日：2020-06-09
发明人： Hui Zhang , Junning Li , Bai Wang , Tao Zhao
摘要： An exemplary processing system accesses a three-dimensional (3D) model of an anatomical structure of a patient and applies a detection process to the 3D model to detect a single-layer anatomical feature in the anatomical structure. The detection process includes generating, from the 3D model, a probability map of candidate points for the single-layer anatomical feature, and generating, based on the probability map of candidate points, a single-layer mesh representing the single-layer anatomical feature.
-
6.发明公开公开(公告)号：US20240312012A1
公开(公告)日：2024-09-19
申请号：US18674438
申请日：2024-05-24
发明人： Junning Li , Pechin Chien Pau Lo , Ahmed Taha , Tao Zhao
CPC分类号： G06T7/0012 , A61B34/10 , A61B34/20 , G06T7/12 , A61B2034/2065 , G06T2207/30101
摘要： A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.
-
公开(公告)号：US12067678B2
公开(公告)日：2024-08-20
申请号：US17617869
申请日：2020-06-09
发明人： Hui Zhang , Junning Li , Bai Wang , Tao Zhao
CPC分类号： G06T17/20 , A61B34/10 , G06T7/0012 , A61B2034/105 , A61B2034/107 , G06T2207/30064 , G06T2207/30101 , G06T2210/41
摘要： An exemplary processing system accesses a three-dimensional (3D) model of an anatomical structure of a patient and applies a detection process to the 3D model to detect a single-layer anatomical feature in the anatomical structure. The detection process includes generating, from the 3D model, a probability map of candidate points for the single-layer anatomical feature, and generating, based on the probability map of candidate points, a single-layer mesh representing the single-layer anatomical feature.
-
公开(公告)号：US10885630B2
公开(公告)日：2021-01-05
申请号：US16289103
申请日：2019-02-28
发明人： Junning Li , Pechin Chien Pau Lo , Ahmed Taha , Tao Zhao
摘要： A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.
-
9.发明申请公开(公告)号：US20190272634A1
公开(公告)日：2019-09-05
申请号：US16289103
申请日：2019-02-28
发明人： Junning Li , Pechin Chien Pau Lo , Ahmed Taha , Tao Zhao
摘要： A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.
-
-
-
-
-
-
-
-
搜索结果
9 条记录 (耗时 0.015 秒)
