Invention Grant
- Patent Title: Method and system for machine learning based estimation of anisotropic vessel orientation tensor
-
Application No.: US15446409Application Date: 2017-03-01
-
Publication No.: US10210612B2Publication Date: 2019-02-19
- Inventor: Mehmet Akif Gulsun , Yefeng Zheng , Saikiran Rapaka , Gareth Funka-Lea
- Applicant: Siemens Healthcare GmbH
- Applicant Address: DE Erlangen
- Assignee: Siemens Healthcare GmbH
- Current Assignee: Siemens Healthcare GmbH
- Current Assignee Address: DE Erlangen
- Main IPC: G06K9/00
- IPC: G06K9/00 ; A61B5/05 ; G06T7/00 ; G06K9/62

Abstract:
A method and apparatus for machine learning based detection of vessel orientation tensors of a target vessel from a medical image is disclosed. For each of a plurality of voxels in a medical image, such as a computed tomography angiography (CTA), features are extracted from sampling patches oriented to each of a plurality of discrete orientations in the medical image. A classification score is calculated for each of the plurality of discrete orientations at each voxel based on the features extracted from the sampling patches oriented to each of the plurality of discrete orientations using a trained vessel orientation tensor classifier. A vessel orientation tensor at each voxel is calculated based on the classification scores of the plurality of discrete orientations at that voxel.
Public/Granted literature
- US20170262981A1 Method and System for Machine Learning Based Estimation of Anisotropic Vessel Orientation Tensor Public/Granted day:2017-09-14
Information query