Model-based segmentation of an anatomical structure

Patent metadata

Field	Value
Publication number	US-9824457-B2
Application number	US-201514832029-A
Country	US
Kind code	B2
Filing date	Aug 21, 2015
Priority date	Aug 28, 2014
Publication date	Nov 21, 2017
Grant date	Nov 21, 2017

Abstract

A system ( 100 ) and method is provided for performing a model-based segmentation of an anatomical structure in a medical image of a patient. The medical image ( 022 ) is accessed. Moreover, model data ( 162 ) is provided which defines a deformable model for segmenting the type of anatomical structure. The model-based segmentation of the anatomical structure is performed by adapting the deformable model to the anatomical structure in the medical image using an adaptation technique. In accordance with the present invention, performing the model based segmentation further comprises determining from patient data ( 042 ) medical information which is predictive of an appearance of the anatomical structure in the medical image, and adjusting or setting a segmentation parameter based on the medical information so as to adjust the model-based segmentation to said predicted appearance of the anatomical structure in the medical image, the segmentation parameter being a parameter of i) the deformable model or ii) the adaptation technique. Advantageously, the system and method are enabled to better cope with the inter-patient and inter-disease-stage variability in the appearance of anatomical structures.

First claim

The invention claimed is:

1. A system for performing a model-based segmentation of an anatomical structure in a medical image of a patient, the system comprising:
an image interface for accessing the medical image;
a patient data interface for accessing patient data of the patient;
a data storage comprising model data that defines a deformable model for segmenting the type of anatomical structure; and
a processor that:
determines, from the patient data, medical information that is separate and distinct from the medical image;
provides a predicted appearance of the anatomical structure of the patient in the medical image based on the medical information; and
adjusts or sets a segmentation parameter based on the medical information, and
performs a model-based segmentation of the anatomic structure in the medical image based on the deformable model and the segmentation parameter so as to adjust the model-based segmentation to be consistent with the predicted appearance of the anatomical structure in the medical image, the segmentation parameter being a parameter of at least one of the deformable model and the adaptation technique.

2. The system according to claim 1 , wherein the segmentation parameter has a pre-initialization value for use in adapting the deformable model to a reference appearance of the anatomical structure, and wherein the processor:
determines, based on the medical information, a deviation of the predicted appearance of the anatomical structure from the reference appearance; and
adjusts the segmentation parameter to accommodate the deviation.

3. The system according to claim 2 , wherein the reference appearance is an inter-patient mean appearance of the anatomical structure.

4. The system according to any one of claims 1 to 3 , wherein the segmentation parameter determines, at least in part, a geometric shape of the deformable model.

5. The system according to claim 1 , wherein the segmentation parameter determines a degree of allowable shape deformation of the deformable model during the adapting of the deformable model.

6. The system according to claim 5 , wherein the medical information is indicative of an anatomical part of the anatomical structure having an abnormal shape or size, and wherein the processor is configured for adjusting or setting the segmentation parameter to allow or restrict the shape deformation of a model part of the deformable model that corresponds to the anatomical part.

7. The system according to any one of claims 1 to 3 , wherein the medical information is predictive of an image contrast at a boundary of the anatomical structure in the medical image, wherein the segmentation parameter is for use in edge detection, and wherein the processor adjusts or sets the segmentation parameter to optimize the edge detection for the predicted image contrast.

8. The system according to claim 1 , wherein the medical information comprises at least one of: an age, a gender, a disease type, a disease progression state, of the patient.

9. The system according to claim 1 , wherein the adaptation technique is represented by data defining a plurality of operations, and wherein the segmentation parameter defines an order or a sub-selection of the plurality of operations to be performed by the processor.

10. The system according to claim 9 , wherein the deformable model comprises a plurality of model parts corresponding to respective anatomical parts of anatomical structure, and wherein at least part of the plurality of operations are for the adapting of respective ones of the plurality of model parts.

11. The system according to claim 10 , wherein the patient data is constituted by an electronic health record of the patient.

12. The system according to claim 1 , wherein the medical image is a DICOM (Digital Imaging and Communications in Medicine) formatted image, and wherein the patient data is constituted by DICOM metadata of the DICOM formatted image.

13. Workstation or imaging apparatus comprising the system according to claim 1 .

14. A method for performing a model-based segmentation of an anatomical structure in a medical image of a patient, the method comprising:
accessing the medical image;
accessing patient data of the patient;
providing model data defining a deformable model for segmenting a type of anatomical structure;
performing a model-based segmentation of the anatomical structure by adapting the deformable model to the anatomical structure in the medical image using an adaptation technique;
wherein the performing of the model-based segmentation comprises:
determining from the patient data medical information that is separate and distinct from the medical image,
determining a predicted appearance of the anatomical structure in the medical image based on the medical information; and
adjusting or setting a segmentation parameter based on the medical information so as to adjust the model-based segmentation to be consistent with the predicted appearance of the anatomical structure in the medical image, the segmentation parameter being a parameter of at least one of the deformable model and the adaptation technique.

15. A non-transitory computer-readable medium that includes a program that, when executed by a processor, causes the processor to:
access a medical image of a patient;
access patient data of the patient;
access model data defining a deformable model for segmenting a type of anatomical structure;
perform a model-based segmentation of the anatomical structure by adapting the deformable model to the anatomical structure in the medical image using an adaptation technique;
wherein the processor performs the model-based segmentation by a process that includes:
determining from the patient data medical information that is separate and distinct from the medical image of the patient;
determining a predicted appearance of the anatomical structure in the medical image based on the medical information; and
adjusting or setting a segmentation parameter based on the medical information so as to adjust the model-based segmentation to be consistent with the predicted appearance of the anatomical structure in the medical image, the segmentation parameter being a parameter of at least one of the deformable model and the adaptation technique.

16. The medium of claim 15 , wherein the segmentation parameter has a pre-initialization value for use in adapting the deformable model to a reference appearance of the anatomical structure, and wherein the program causes the processor to:
determine, based on the medical information, a deviation of the predicted appearance of the anatomical structure from the reference appearance; and
adjust or set the segmentation parameter to accommodate the deviation.

Assignees

• Koninklijke Philips Nv

Inventors

• Wenzel Fabian
• Meyer Carsten
• Stehle Thomas Heiko

Classifications

• G06T2207/20116

  Active contour; Active surface; Snakes · CPC title

• G06T7/12 Primary

  Edge-based segmentation · CPC title

• G06T7/13

  Edge detection · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06T7/149

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