Uncertainty maps for segmentation in the presence of metal artifacts

Patent metadata

Field	Value
Publication number	US-9730663-B2
Application number	US-67377908-A
Country	US
Kind code	B2
Filing date	Aug 12, 2008
Priority date	Aug 31, 2007
Publication date	Aug 15, 2017
Grant date	Aug 15, 2017

Abstract

When performing model-based segmentation on a 3D patient image ( 80 ), metal artifacts in the patient image ( 80 ), caused by metal in the patient's body, are detected, and a metal artifact reduction technique is performed to reduce the artifact(s) by interpolation projection data in the region of the artifact(s). The interpolated data is used to generate an uncertainty map for artifact-affected voxels in the image, and a mesh model ( 78 ) is conformed to the image to facilitate segmentation thereof. Internal and external energies applied to push and pull the model ( 78 ) are weighted as a function of the uncertainty associated with one or more voxels in the image ( 80 ). Iteratively, mathematical representations of the energies and respective weights are solved to describe an updated model shape that more closely aligns to the image ( 80 ).

First claim

Having thus described the preferred embodiments, the invention is now claimed to be:

1. A system for image segmentation in the presence of metal artifacts, including:
a model generator that receives patient image data and stores trained models of anatomical structures;
a voxel analyzer that determines whether metal artifacts are present in one or more voxels in the patient image data;
a processor that executes a metal artifact reduction algorithm and generates an uncertainty map with corrected voxel data incorporated therein for a patient image generated from the patient image data, wherein the uncertainty map indicates a likelihood of metal contamination for corrected voxels representing boundary surfaces of one or more remote organs in other parts of the patient image; and
a segmentation tool that:
conforms a trained model of an anatomical structure corresponding to the patient image;
segments the patient image using a model-based segmentation technique; and
evaluates the uncertainty map derived by the processor;
wherein the segmentation tool applies an internal force along a surface normal vector in a surface region in which the feature is located; and
wherein the segmentation tool applies an external force along the vector; and
wherein the internal force increases and the external force decreases as a function of an increase in the likelihood of metal contamination associated with each corrected voxel.

2. The system according to claim 1 , wherein the model has a triangulated mesh surface.

3. The system of claim 1 , wherein a feature on the surface of the model is selected at least one of automatically or in response to user input.

4. The system according to claim 1 , wherein the segmentation tool balances the internal force and the external force to align the surface region to a surface of the patient image.

5. The system according to claim 1 , wherein the total energy applied to the feature through the internal and external forces is expressed as E total =w int ×E int +w ext ×E ext , wherein E total is total energy, E int is internal energy, E ext is external energy, w int is an internal energy weight, and w ext is an external energy weight, and wherein

E
ext

=

∑

t
=
1

t
=

N
Δ

⁢

r
⁡

(

x
^

t

)

⁢

w
t

⁡

(

x
~

t

-

x
^

t

)

2

,

where r({circumflex over (x)} t ) represents the reliability of the external energy and is spatially variant, N Δ is the number of triangles in the mesh surface, w t is the feature strength of a triangle t, {tilde over (x)} t is the coordinates of the best feature for triangle t, and {circumflex over (x)} t is the coordinates of the center of triangle t.

6. The system according to claim 5 , wherein w ext is 1, and wherein the segmentation tool applies increased internal force to compensate for a detected metal artifact.

7. The system according to claim 1 , wherein the model generator includes:
a routine for determining whether a voxel is affected by a metal artifact;
a routine for quantitatively predicting a level to which the voxel is affected by the metal artifact;
a routine for interpolating projection data and updating the voxel with the interpolated projection data; and
a routine for deforming the model to the patient image.

8. A method of performing model-based segmentation in the system of claim 1 , including:
determining whether a voxel is affected by a metal artifact;
quantitatively predicting a level to which the voxel is affected by the metal artifact;
interpolating projection data and updating the voxel with the interpolated projection data; and
deforming the model to the patient image.

9. A processor for performing model-based segmentation, the processor being configured to:
receive a patient image of a region of a patient that includes a metal object;
generate an uncertainty map for the patient image indicative of a likelihood of metal contamination of corrected voxels in the patient image due to metal object reconstruction artifacts;
segment the patient image;
employ the uncertainty map when segmenting a portion of the patient image displaced from the metal object using model-based segmenting;
compute external and internal energies to be applied to each triangle of a model surface using respective best features and weights, wherein the internal energy increases and the external energy decreases as a function of an increase in the likelihood of metal contamination associated with each corrected voxel; and
model the internal energy as:

E
int

=

∑

e
=
1

e
=

N
edges

⁢

(

x
→

e

-

sR
⁢

x
→

e
0

Assignees

• Koehler Thomas
• Schmitt Holger
• Schulz Heinrich
• Koninklijke Philips Nv

Inventors

• Koehler Thomas
• Schmitt Holger
• Schulz Heinrich

Classifications

• A61B6/5258 Primary

  involving detection or reduction of artifacts or noise · CPC title

• G06T2207/30052

  Implant; Prosthesis · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• G06T2207/20012

  Locally adaptive · CPC title