Method and system for mesh segmentation and mesh registration

Patent metadata

Field	Value
Publication number	US-9761005-B2
Application number	US-201414785438-A
Country	US
Kind code	B2
Filing date	May 8, 2014
Priority date	May 9, 2013
Publication date	Sep 12, 2017
Grant date	Sep 12, 2017

Abstract

A system, apparatus and method for mesh registration including an extraction of a preoperative anatomical mesh from a preoperative anatomical image based on a base topology of an anatomical mesh template, an extraction of an intraoperative anatomical mesh from an intraoperative anatomical image based on a preoperative topology of the preoperative anatomical mesh derived from the base topology of an anatomical mesh template, and a registration of the preoperative anatomical image and the intraoperative anatomical image based on a mapping correspondence between the preoperative anatomical mesh and the intraoperative anatomical mesh established by an intraoperative topology of the intraoperative anatomical mesh derived from the preoperative topology of the preoperative anatomical mesh.

First claim

The invention claimed is:

1. A system for mesh registration, the system comprising:
a processor and a processor storage medium having instructions stored thereon, the processor configured by the instructions stored on the processor storage medium to:
extract a preoperative anatomical mesh from a preoperative anatomical image based on a base topology of an anatomical mesh template;
extract an intraoperative anatomical mesh from an intraoperative anatomical image based on a preoperative topology of the preoperative anatomical mesh derived from the base topology of the anatomical mesh template; and
register the preoperative anatomical image and the intraoperative anatomical image based on a mapping correspondence between the preoperative anatomical mesh and the intraoperative anatomical mesh established by an intraoperative topology of the intraoperative anatomical mesh derived from the preoperative topology of the preoperative anatomical mesh.

2. The system of claim 1 , wherein the processor is further configured by the instructions stored on the processor storage medium to generate both the preoperative anatomical image and the intraoperative anatomical image from an identical image modality.

3. The system of claim 1 , wherein the processor is further configured by the instructions stored on the processor storage medium to generate the preoperative anatomical image and the intraoperative anatomical image from different image modalities.

4. The system of claim 1 , wherein the processor is further configured by the instructions stored on the processor storage medium to:
construct a preoperative segmentation model from an extraction of a preoperative training mesh dataset from a preoperative anatomical image dataset based on the base topology of the anatomical mesh template; and
extract the preoperative anatomical mesh from the preoperative anatomical image based on the base topology of the anatomical mesh template.

5. The system of claim 1 , wherein the processor is further configured by the instructions stored on the processor storage medium to:
construct an intraoperative segmentation model from an extraction of an intraoperative training mesh dataset from an intraoperative anatomical image dataset based on the preoperative topology of a preoperative baseline mesh dataset; and
utilize the intraoperative segmentation model to extract the intraoperative anatomical mesh from the intraoperative anatomical image based on the preoperative topology of the preoperative anatomical mesh.

6. The system of claim 5 , wherein the processor is further configured by the instructions stored on the processor storage medium to extract the preoperative baseline mesh dataset from a preoperative anatomical image dataset based on the base topology of the anatomical mesh template.

7. The system of claim 1 , wherein the processor is further configured by the instructions stored on the processor storage medium to register the preoperative anatomical image and the intraoperative anatomical image using a spatial transformation of the preoperative anatomical mesh to the intraoperative anatomical mesh.

8. A modular network for mesh segmentation and registration, the modular network comprising:
a processor and a processor storage medium having instructions stored thereon, the processor configured by the instructions stored on the processor storage medium to:
extract a preoperative anatomical mesh from a preoperative anatomical image based on a base topology of an anatomical mesh template;
extract an intraoperative anatomical mesh from an intraoperative anatomical image based on a preoperative topology of the preoperative anatomical mesh derived from the base topology of the anatomical mesh template; and
register the preoperative anatomical image and the intraoperative anatomical image based on a mapping correspondence between the preoperative anatomical mesh and the intraoperative anatomical mesh established by an intraoperative topology of the intraoperative anatomical mesh derived from the preoperative topology of the preoperative anatomical mesh.

9. The modular network of claim 8 , wherein the processor is further configured by the instructions stored on the processor storage medium to generate both the preoperative anatomical image and the intraoperative anatomical image from an identical image modality.

10. The modular network of claim 8 , wherein the processor is further configured by the instructions stored on the processor storage medium to generate the preoperative anatomical image and the intraoperative anatomical image from different image modalities.

11. The modular network of claim 8 , wherein the processor is further configured by the instructions stored on the processor storage medium to:
construct a preoperative segmentation model from an extraction of a preoperative training mesh dataset from a preoperative anatomical image dataset based on the base topology of the anatomical mesh template; and
extract the preoperative anatomical mesh from the preoperative anatomical image based on the base topology of the anatomical mesh template.

12. The modular network of claim 8 , wherein the processor is further configured by the instructions stored on the processor storage medium to:
construct an intraoperative segmentation model from an extraction of an intraoperative training mesh dataset from an intraoperative anatomical image dataset based on the preoperative topology of the preoperative baseline mesh dataset; and
extract the intraoperative anatomical mesh from the intraoperative anatomical image based on the preoperative topology of the preoperative anatomical mesh.

13. The modular network of claim 12 , wherein the processor is further configured by the instructions stored on the processor storage medium to extract the preoperative baseline mesh dataset from a preoperative anatomical image dataset based on the base topology of the anatomical mesh template.

14. The modular network of claim 8 , wherein the processor comprises a plurality of processors,
wherein a first of the plurality of processors is configured to extract the preoperative anatomical mesh and comprises a portion of a preoperative workstation;
wherein a second of the plurality of processors is configured to extract the intraoperative anatomical mesh and is configured to register the preoperative anatomical image and the intraoperative anatomical image; and
wherein the second of the plurality of processors comprises a portion of an intraoperative workstation.

15. The modular network of claim 8 , wherein the processor is further configured by the instructions stored on the processor storage medium to register the preoperative anatomical image and the intraoperative anatomical image using a spatial transformation of the preoperative anatomical mesh to the intraoperative anatomical mesh.

16. A system for mesh registration, the system comprising:
a processor and a processor storage medium having instructions stored thereon, the processor configured by the instructions stored on the processor storage medium to perform acts:
extracting a preoperative anatomical mesh from a preoperative anatomical image based on a base topology of an anatomical mesh template;
extracting an intraoperative anatomical mesh from an intraoperative anatomical image based on a preoperative topology of the preoperative anatomical mesh derived from the base topology of the anatomical mesh template; and
registering the preoperative anatomical image and the intraoperative anatomical image based on a mapping correspondence between the preoperative anatomical mesh and

Assignees

• Koninklijke Philips Nv

Inventors

• Tahmasebi Maraghoosh Amir Mohammad
• Kruecker Jochen
• Zagorchev Lyubomir Georgiev

Classifications

• G06T7/344 Primary

  involving models · CPC title

• G06T7/174 Primary

  involving the use of two or more images · CPC title

• G06T3/0068

  Physics · mapped topic

• G06T2207/10088

  Magnetic resonance imaging [MRI] · CPC title

• G06T7/149

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