-
公开(公告)号：US20180374209A1
公开(公告)日：2018-12-27
申请号：US15634657
申请日：2017-06-27
Applicant: General Electric Company
Inventor： Bhushan Dayaram Patil , Peter Lamb , Roshni Rustom Bhagalia , Bipul Das
CPC classification number: G06T7/0012 , G06N3/0445 , G06N3/0454 , G06N3/082 , G06N3/084 , G06N3/088 , G06N7/005 , G06N20/10 , G06T7/11 , G06T2207/10081 , G06T2207/20081 , G06T2207/20084 , G06T2207/30008
Abstract: The present approach relates, in some aspects, to a multi-level and a multi-channel frame work for segmentation using model-based or “shallow” classification (i.e. learning processes such as linear regression, clustering, support vector machines, and so forth) followed by deep learning. This framework starts with a very low resolution version of the multi-channel data and constructs an shallow classifier with simple features to generate a coarser level tissue mask that in turn is used to crop patches from the high-resolution volume. The cropped volume is then processed using the trained convolution network to perform a deep learning based segmentation within the slices.
-
公开(公告)号：US10438350B2
公开(公告)日：2019-10-08
申请号：US15634657
申请日：2017-06-27
Applicant: General Electric Company
Inventor： Bhushan Dayaram Patil , Peter Lamb , Roshni Rustom Bhagalia , Bipul Das
Abstract: The present approach relates, in some aspects, to a multi-level and a multi-channel frame work for segmentation using model-based or “shallow” classification (i.e. learning processes such as linear regression, clustering, support vector machines, and so forth) followed by deep learning. This framework starts with a very low resolution version of the multi-channel data and constructs an shallow classifier with simple features to generate a coarser level tissue mask that in turn is used to crop patches from the high-resolution volume. The cropped volume is then processed using the trained convolution network to perform a deep learning based segmentation within the slices.
-
Search Results
2
records
(took 0.012 seconds)
