Choosing anatomical variant model for image segmentation

Patent metadata

Field	Value
Publication number	US-9367913-B2
Application number	US-201113823472-A
Country	US
Kind code	B2
Filing date	Sep 13, 2011
Priority date	Sep 17, 2010
Publication date	Jun 14, 2016
Grant date	Jun 14, 2016

Abstract

A system ( 100 ) for segmenting an object in an image adapts a first model for segmenting the object to the image. A feature is extracted from the image based on the adapted first model. A second model is selected for segmenting the object from a plurality of models for segmenting the object, based on the feature extracted from the image. The second model includes additional detail of the object. The second model is utilized based on the adapted first model and/or the feature extracted from the image; the initialized second model is adapted to the image. The features extracted from the image based on the adapted first model help the system ( 100 ) to select the second model for segmenting the object from a plurality of models for segmenting the object. The adapted first model and/or the extracted features are also used for initializing the second model. Because the second model includes the additional detail of the object, the segmentation result using the second model is more complete than the segmentation result Obtained using the first model. Moreover, the initialization of the second model based on the adapted first model and/or the detected features Improves the accuracy of the second model adaptation.

First claim

The invention claimed is:

1. A system for segmenting an object in a medical diagnostic image comprising;
a processor programmed to;
adapt is first deformable model for segmenting the object in the image;
perform a steered region growing which is steered based on the adapted first deformable model;
extract a feature from the image based on a result of the region growing;
select a second deformable model for segmenting the object based on the feature extracted from the image wherein the second deformable model comprises additional detail of the object;
initialize the second deformable model based on the adapted first deformable model and/or the feature extracted from the image; and
adapt the initialized second deformable model to the image.

2. The system as claimed in claim 1 , wherein the first deformable model includes a mesh and in the steered region growing growth space is limited based on the mesh and a landmark of the adapted first deformable model.

3. The system as claimed in claim 2 , wherein the region growing detects blood vessels.

4. The system as claimed in claim 3 , wherein the extracted feature is indicative of the detected blood vessels such that the second deformable model is selected based on the detected blood vessels.

5. The system as claimed in claim 4 , wherein the first and second deformable models are left atrium models.

6. The system as claimed in claim 4 , wherein the first and second deformable models are kidney models.

Assignees

• Lorenz Cristian
• Barschdorf Hans
• Klinder Tobias
• Hanna Raghed
• Koninkl Philips Nv

Inventors

• Lorenz Cristian
• Barschdorf Hans
• Klinder Tobias
• Hanna Raghed

Classifications

• G06T17/00

  Three-dimensional [3D] modelling for computer graphics · CPC title

• G06T2207/30004

  Biomedical image processing · CPC title

• G06T7/149

  involving deformable models, e.g. active contour models · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06T15/08

  Volume rendering · CPC title