Segmentation of magnetic resonance imaging data

• US 9,514,539 B2
• Filed: 05/09/2013
• Issued: 12/06/2016
• Est. Priority Date: 05/09/2012
• Status: Active Grant

• Current Assignee: Laboratoires Bodycad Inc
• Original Assignee: Laboratoires Bodycad Inc
• Inventors: Rivet-Sabourin, Geoffroy
• Primary Examiner(s): Bali, Vikkram
• Assistant Examiner(s): Mangialaschi, Tracy
• Application Number:
  US14/399,796
• Publication Number:
  US 20150302601A1
• Time in Patent Office: 1,307 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G01R 33/5608 Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels image data processing or generation, in general G06T
• CPC Class Codes: G06T 17/20 Finite element generation, e.g. wire-frame surface description, tesselation
• CPC Class Codes: G06T 19/20 Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/20116 Active contour; Active surface; Snakes
• CPC Class Codes: G06T 2207/30008 Bone
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models
• CPC Class Codes: G06T 7/155 involving morphological operators
• CPC Class Codes: G06T 7/77 using statistical methods

Abstract

There is described herein an image segmentation technique using an iterative process. A contour, which begins with a single point that expands into a hollow shape, is iteratively deformed into a defined structure. As the contour is deformed, various constraints are applied to points along the contour to dictate its rate of change and direction of change are modified dynamically. The constraints may be modified after one or more iterations, at each point along the contour, in accordance with newly measured or determined data.

Claims

1. A computer-implemented method for segmenting magnetic resonance imaging (MRI) data, the method comprising:

detecting one or more edges in an image for a given bone structure;

determining an initial position on the image;

converting the initial position into an initial contour within the given bone structure; and

iteratively deforming the initial contour to expand into a shape matching the given bone structure by dynamically applying a set of constraints locally to each point along the initial contour for causing each point to evolve towards at least a selected one of the one or more edges, and updating the set of constraints after one or more iterations, wherein the set of constraints includes curvature and continuity constraints, and wherein iteratively deforming the initial contour comprises computing a distance from each point along the initial contour to a nearest one of the one or more edges present in the image and dynamically determining from the computed distance the curvature and continuity constraints to be applied at the point.

2. The method of claim 1, wherein determining the initial position, converting the initial position into the initial contour, and iteratively deforming the initial contour are performed for a plurality of images for the given bone structure, the plurality of images processed at least one of sequentially and in parallel.

3. The method of claim 1, wherein iteratively deforming the initial contour comprises performing a first contour definition of the given bone structure along a first direction followed by a second contour definition of the given bone structure along a second direction, and merging the first and second contour definitions such that data from the second contour definition complements data from the first contour definition.

4. The method of claim 3, further comprising obtaining a points cloud representative of the first contour definition, converting the points cloud into a mesh model, obtaining a plurality of slices of the mesh model along the second direction, and performing the second contour definition on the basis of the mesh slices.

5. The method of claim 4, wherein the first contour definition is performed along a sagittal plane and the second contour definition is performed along a coronal plane.

6. The method of claim 4, wherein converting the points cloud into a mesh model comprises performing a grid decimation on the points cloud for reducing a number of points to be processed from the points cloud.

7. The method of claim 1, further comprising computing a mean distance between a current contour and a previous contour and comparing the mean distance to a threshold distance, wherein the initial contour is iteratively deformed until the mean distance is below the threshold distance.

8. The method of claim 1, wherein iteratively deforming the initial contour comprises evaluating a magnitude of a vector field at each point along the initial contour and dynamically determining from the magnitude one or more viscosity constraints to be applied at the point for preventing the expanding initial contour from entering into holes defined between the one or more edges in the image.

9. The method of claim 1, wherein iteratively deforming the initial contour comprises defining one or more form constraint zones in the image and dynamically modifying a displacement vector at each point along the initial contour in accordance with at least one of a form constraint zone the point belongs to and a position of the point within the given bone structure.

10. The method of claim 1, wherein iteratively deforming the initial contour comprises predicting a displacement direction at each point along the initial contour relative to a normal to the initial contour, identifying ones of the one or more edges present in the predicted displacement direction, and dynamically modifying a normal force applied to each point along the initial contour in accordance with the ones of the one or more edges identified in the predicted displacement direction.

11. A system for generating segmented data from magnetic resonance imaging (MRI) data, the system comprising:

at least one computer server communicable with at least one computing device over a network, the at least one computer server having a processor and a memory;

an initial position module stored on the memory and executable by the processor, the initial position module having program code that when executed, determines an initial position on an image for a given bone structure and converting the initial position into an initial contour; and

a contour definition module stored on the memory and executable by the processor, the contour definition module having program code that when executed, iteratively deforms the initial contour to expand into a shape matching the given bone structure by dynamically applying a set of constraints locally to each point along the initial contour for causing each point to evolve towards at least a selected one of one or more edges present in the image, and updating the set of constraints after one or more iterations, wherein the set of constraints includes curvature and continuity constraints, and wherein iteratively deforming the initial contour comprises computing a distance from each point along the initial contour to a nearest one of the one or more edges present in the image and dynamically determining from the computed distance the curvature and continuity constraints to be applied at the point.

12. The system of claim 11, wherein the contour definition module has program code that when executed performs a first contour definition of the given bone structure along a first direction followed by a second contour definition of the given bone structure along a second direction.

13. The system of claim 12, further comprising a meshing module stored on the memory and executable by the processor, wherein the contour definition module has program code that when executed obtains a points cloud representative of the first contour definition and further wherein the meshing module has program code that when executed converts the points cloud into a mesh model.

14. The system of claim 13, further comprising a segmentation merging module stored on the memory and executable by the processor, wherein the contour definition module has program code that when executed performs the second contour definition on the basis of the mesh model and the segmentation merging module has program code that when executed merges the first and second contour definitions such that data from the second contour definition complements data from the first contour definition.

15. The system of claim 14, wherein the meshing module has program code that when executed performs a grid decimation on the points cloud to reduce a number of points to be processed when converting the points cloud into the mesh model.

16. The system of claim 11, wherein the contour definition module comprises a viscosity constraints module having program code that when executed evaluates a magnitude of a vector field at each point along the initial contour and dynamically determines from the magnitude one or more viscosity constraints to be applied at the point for preventing the expanding initial contour from entering into holes defined between the one or more edges in the image.

17. The system of claim 11, wherein the contour definition module comprises a form constraints module having program code that when executed defines one or more form constraint zones in the image and dynamically modifies a displacement vector at each point along the initial contour in accordance with at least one of a form constraint zone the point belongs to and a position of the point within the given bone structure.

18. The system of claim 11, wherein the contour definition module has program code that when executed predicts a displacement direction at each point along the initial contour relative to a normal to the initial contour, identifies ones of the one or more edges present in the predicted displacement direction, and dynamically modifies a normal force applied to each point along the initial contour in accordance with the ones of the one or more edges identified in the predicted displacement direction.

19. A non-transitory computer readable medium having stored thereon program code executable by a processor for generating segmented data from magnetic resonance imaging (MRI) data, the program code executable for:

determining an initial position on an image for a given bone structure;

converting the initial position into an initial contour within the given bone structure; and

iteratively deforming the initial contour to expand into a shape matching the given bone structure by dynamically applying a set of constraints locally to each point along the initial contour for causing each point to evolve towards at least a selected one of one or more edges present in the image, and updating the set of constraints after one or more iterations,

wherein the set of constraints includes curvature and continuity constraints, and wherein iteratively deforming the initial contour comprises computing a distance from each point along the initial contour to a nearest one of the one or more edges present in the image and dynamically determining from the computed distance the curvature and continuity constraints to be applied at the point.