发明授权
- 专利标题: Multi-level contextual learning of data
- 专利标题(中): 数据的多层次上下文学习
-
申请号: US12962901申请日: 2010-12-08
-
公开(公告)号: US08724866B2公开(公告)日: 2014-05-13
- 发明人: Dijia Wu , Le Lu , Jinbo Bi , Yoshihisa Shinagawa , Marcos Salganicoff
- 申请人: Dijia Wu , Le Lu , Jinbo Bi , Yoshihisa Shinagawa , Marcos Salganicoff
- 申请人地址: US PA Malvern
- 专利权人: Siemens Medical Solutions USA, Inc.
- 当前专利权人: Siemens Medical Solutions USA, Inc.
- 当前专利权人地址: US PA Malvern
- 代理商 Peter R. Withstandley
- 主分类号: G06K9/00
- IPC分类号: G06K9/00
摘要:
Described herein is a framework for automatically classifying a structure in digital image data are described herein. In one implementation, a first set of features is extracted from digital image data, and used to learn a discriminative model. The discriminative model may be associated with at least one conditional probability of a class label given an image data observation Based on the conditional probability, at least one likelihood measure of the structure co-occurring with another structure in the same sub-volume of the digital image data is determined. A second set of features may then be extracted from the likelihood measure.
公开/授权文献
- US20110075920A1 Multi-Level Contextual Learning of Data 公开/授权日:2011-03-31