Invention Grant
- Patent Title: Image segmentation via multi-atlas fusion with context learning
-
Application No.: US15540487Application Date: 2016-02-18
-
Publication No.: US10402981B2Publication Date: 2019-09-03
- Inventor: Mayur Patel , Patrick Kelly , Miya Smith , Andrew Plassard , Bennett Landman , Richard G. Abramsom , Zhoubing Xu , Benjamin K. Poulose , Rebeccah B. Baucom , Andrew Joseph Asman
- Applicant: Vanderbilt University
- Applicant Address: US TN Nashville
- Assignee: VANDERBILT UNIVERSITY
- Current Assignee: VANDERBILT UNIVERSITY
- Current Assignee Address: US TN Nashville
- Agency: Tarolli, Sundheim, Covell & Tummino LLP
- International Application: PCT/US2016/018433 WO 20160218
- International Announcement: WO2016/134125 WO 20160825
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06T7/162 ; G06T7/00 ; G16H50/20 ; G16H50/50 ; G06F19/00

Abstract:
Systems and methods are provided for segmenting tissue within a computed tomography (CT) scan of a region of interest into one of a plurality of tissue classes. A plurality of atlases are registered to the CT scan to produce a plurality of registered atlases. A context model representing respective likelihoods that each voxel of the CT scan is a member of each of the plurality of tissue classes is determined from the CT scan and a set of associated training data. A proper subset of the plurality of registered atlases is selected according to the context model and the registered atlases. The selected proper subset of registered atlases are fused to produce a combined segmentation.
Public/Granted literature
- US20180005381A1 IMAGE SEGMENTATION VIA MULTI-ATLAS FUSION WITH CONTEXT LEARNING Public/Granted day:2018-01-04
Information query