Simultaneous partial volume corection and segmentation refinement

Patent metadata

Field	Value
Publication number	US-11935245-B2
Application number	US-201917282008-A
Country	US
Kind code	B2
Filing date	Sep 27, 2019
Priority date	Oct 2, 2018
Publication date	Mar 19, 2024
Grant date	Mar 19, 2024

Abstract

The invention provides for a medical apparatus (100, 400, 600) comprising a memory (110) for storing machine executable instructions (120) and a processor (104) for controlling the medical apparatus. Execution of the machine executable instructions causes the processor to: receive (200) a medical image (122) descriptive of a three-dimensional anatomy of a subject (418); and provide (202) an image segmentation (124) by segmenting the medical image into multiple tissue regions (300, 302) using a model-based segmentation. The model-based segmentation assigns a tissue type to each of the multiple regions. The model-based segmentation has a surface mesh (304). The segmentation is corrected by using the tissue type assigned to each of the multiple regions to correct for partial volume effects at boundaries formed by the surface mesh between at least some of the multiple tissue regions.

First claim

The invention claimed is:

1. A medical apparatus comprising:
a memory configured to store machine executable instructions;
a processor configured to control the medical apparatus, wherein execution of the machine executable instructions causes the processor to:
receive a medical image descriptive of a three-dimensional anatomy of a subject ( 418 ); and
provide an image segmentation by segmenting the medical image into multiple tissue regions using a model-based segmentation, wherein the model-based segmentation assigns a tissue type to each of the multiple regions, wherein the model-based segmentation has a surface mesh, wherein the model-based segmentation comprises a cortical bone model and wherein the segmentation is corrected by using the tissue type assigned to each of the multiple regions to correct for partial volume effects at boundaries formed by the surface mesh between at least some of the multiple tissue regions; and
reconstruct a pseudo radiographic image using the image segmentation and the tissue type assigned to each of the multiple regions, wherein execution of the machine executable instructions causes the processor to correct the pseudo radiographic image using the cortical bone model by forward simulating the partial volume effect correction of the image segmentation in the pseudo radiographic image.

2. The medical apparatus of claim 1 , wherein the surface mesh is formed from faces, wherein each of the faces has an outward facing vector, wherein the correction of the segmentation is performed by adjusting the position of each of the faces in the direction of the outward facing vector to correct the partial volume effect at the boundaries between at least some of the multiple tissue regions.

3. The medical apparatus of claim 2 , wherein the medical image comprises voxels, wherein the model-based segmentation assigns a voxel intensity range to each tissue type, wherein boundary voxels exhibiting the partial volume effect have a voxel intensity intermediate to the voxel intensity range on either side of the surface mesh, wherein the adjusting of the position of each of the faces in the direction of the outward facing vector is performed by adjusting the position of each of the faces such that the voxel intensity of the boundary voxels is consistent with the contribution to the voxel intensity from the tissue types on both sides of the surface mesh.

4. The medical apparatus of claim 2 , wherein the correction of the segmentation is performed after segmentation by the model-based segmentation.

5. The medical apparatus of claim 2 , wherein the model-based segmentation is a shape constrained deformable model that is configured for segmenting the medical image by balancing an external energy term which defines an attraction to boundaries in the magnetic resonance image with an internal energy term which defines the shape constraint of the shape constrained deformable model, and wherein the correction of the segmentation is incorporated into the external energy term.

6. The medical apparatus of claim 1 , wherein the cortical bone model corrects the pseudo radiographic image by segmenting the cortical bone into layers.

7. The medical apparatus of claim 1 , wherein the cortical bone model is configured for segmenting cortical bone into multiple cortical bone layers, wherein execution of the machine executable instructions further causes the processor to correct the pseudo radiographic image using the multiple cortical bone layers.

8. The medical apparatus of claim 1 , wherein execution of the machine executable instructions further causes the processor to reconstruct an electron density map using the pseudo radiographic image.

9. The medical apparatus of claim 8 , wherein execution of the machine executable instructions further causes the processor to:
receive radiation therapy planning data; and
calculate radiotherapy system control commands configured for controlling a radiotherapy system using the electron density map and the radiation therapy planning data.

10. The medical apparatus of claim 8 , wherein the pseudo radiographic image has a predefined resolution, wherein the medical apparatus further comprises the radiotherapy system, wherein the medical apparatus further comprises a radiographic imaging system, wherein execution of the machine executable instructions further causes the processor to:
forward simulate partial volume effects in the pseudo radiographic image;
control the radiographic imaging system to acquire an acquired radiographic image of a subject, wherein the acquired radiographic image has the predefined resolution; and
align the subject in the radiotherapy system by registering the acquired radiographic image and the pseudo radiographic image.

11. The medical apparatus of claim 1 , wherein the medical image is a magnetic resonance image, wherein the medical apparatus comprises a magnetic resonance imaging system, wherein the memory further contains pulse sequence commands configured for controlling the magnetic resonance imaging system to acquire the magnetic resonance imaging data, and wherein execution of the machine executable instructions further causes the processor to:
control the magnetic resonance imaging system with the pulse sequence commands to acquire the magnetic resonance imaging data,
reconstruct the magnetic resonance image using the magnetic resonance imaging data.

12. A medical imaging method, wherein the method comprises:
receiving a medical image;
providing an image segmentation by segmenting the medical image into multiple tissue regions using a model-based segmentation, wherein the model-based segmentation assigns a tissue type to each of the multiple regions, wherein the model-based segmentation has a surface mesh, wherein the model-based segmentation comprises a cortical bone model, and wherein the segmentation is corrected by using the tissue type assigned to each of the multiple regions to correct for partial volume effects at boundaries formed by the surface mesh between at least some of the multiple tissue regions; and
reconstruct a pseudo radiographic image using the image segmentation and the tissue type assigned to each of the multiple regions, wherein execution of the machine executable instructions causes the processor to correct the pseudo radiographic image using the cortical bone model by forward simulating the partial volume effect correction of the image segmentation in the pseudo radiographic image.

13. A computer program product comprising machine executable instructions stored on a non-transitory computer readable medium for execution by a processor controlling a medical imaging system, wherein execution of the machine executable instructions causes the processor to:
receive a medical image;
provide an image segmentation by segmenting the medical image into multiple tissue regions using a model-based segmentation, wherein the model-based segmentation assigns a tissue type to each of the multiple regions, wherein the model-based segmentation has a surface mesh, wherein the model-based segmentation comprises a cortical bone model, and wherein the segmentation is corrected by using the tissue type assigned to each of the multiple regions to correct for partial volume effects at boundaries formed by the surface mesh between at least some of the multiple tissue regions; and reconstruct a pseudo radiographic image using the image segmentation and the tissue type assigned to each of the multiple regions, wherein execution of the machine executable instructions causes the processor to correct the pseudo radiographic image using the cortical bone model by forward simulating the partial

Assignees

• Koninklijke Philips Nv

Inventors

• Renisch Steffen
• Buerger Christian

Classifications

• G06T7/149 Primary

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

• G06T7/0012

  Biomedical image inspection · CPC title

• G06T2207/10088

  Magnetic resonance imaging [MRI] · CPC title

• G06T2207/30008

  Bone · CPC title

• G06T2207/30016

  Brain · CPC title