Method and apparatus for fitting a smooth boundary to segmentation masks

• US 6,771,803 B1
• Filed: 11/22/2000
• Issued: 08/03/2004
• Est. Priority Date: 11/22/2000
• Status: Expired due to Term

• Current Assignee: GE Medical Systems Global Technology Company LLC (GE Healthcare Technologies, Inc.)
• Original Assignee: GE Medical Systems Global Technology Company LLC (GE Healthcare Technologies, Inc.)
• Inventors: Avinash, Gopal B., Turek, Matthew W.
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): Miller, Ryan J.
• Application Number:
  US09/718,708
• Time in Patent Office: 1,350 Days
• Field of Search: 382/128, 382/131, 382/132, 382/133, 382/173, 382/174, 382/197, 382/199, 382/268, 382/269
• US Class Current: 382/131
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/155 involving morphological operators

Abstract

A method and apparatus is provided for producing a smooth closed curve from a binary mask such as the type produced when segmenting various parts of a human body. Points defining the segmentation boundary are transformed into a set of polar coordinates. The set of coordinates is thresholded and averaged, and then smoothed using a window smoothing technique. The resulting boundary points are curve fit to produce the smooth closed curve.

Claims

1. A method for smoothing an image produced with a magnetic resonance imaging system, wherein the image is defined by an initial plurality of boundary points, each said initial boundary point having a corresponding radius, the method comprising:

removing each said radius having a length that falls outside a first predetermined interval so as to produce a second plurality of radii emanating from a common central location whose corresponding lengths fall within said first predetermined interval, wherein said second plurality of radii define a plurality of remaining boundary points;

encapsulating a portion of said second plurality of radii with a moving window;

examining each of the portion of said second plurality of radii to determine those radii within said portion of second radii having lengths outside a second interval, and adjusting the lengths of those radii such that said adjusted length falls within said second predetermined interval;

iteratively rotating said moving window about said central location so as to examine each radius within said second plurality of radii; and

curve fitting said remaining boundary points so as to produce a smooth, closed curve representing said image.

2. The method as recited in claim 1, wherein said second plurality of radii is defined by the equation $\hat{R}\equiv$

{r

;



{(1-γ

)*rave≤

r≤

(1+γ

)*raverave2

 



otherwise}}

wherein {circumflex over (R)} defines a set of said second plurality of radii;

r defines a range of said lengths defining said second plurality of radii;

r_ave is an average value of all radii defining said initial boundary points;

r_ave2 is an average value of all radii within said second plurality of radii; and

γ

is a threshold coefficient.

3. The method of claim 1, further comprising calculating an average of the lengths of said second plurality of radii, wherein said second predetermined interval defines a range about said calculated average.

4. The method of claim 1, wherein said image is a binary mask having a plurality of pixels representing a magnetic resonance image of a left ventricular epicardial boundary.

5. A boundary smoothing system for smoothing an image produced with a magnetic resonance imaging system, wherein the image is defined by a plurality of boundary points defined by a corresponding first plurality of radii, the system comprising:

means for removing a portion of said first plurality of radii having corresponding length that are outside a first predetermined interval so as to produce a second plurality of radii emanating from a common central location;

means for encapsulating a portion of said second plurality of radii and for rotating a window about said central location so as to examine each radius within said second plurality of radii;

means for determining whether the length of a radius within said portion of said second plurality of radii is outside a second interval; and

means for adjusting adjusting said length such that said adjusted length is within said second predetermined interval.

6. The system as recited in claim 5, wherein said length of said radius is adjusted if said length is outside said second interval.

7. The system of claim 6, further comprising means for calculating an average of the lengths of said second plurality of radii, wherein said second predetermined interval defines a range about said calculated average.

8. The system as recited in claim 5, wherein said second plurality of radii is defined by the equation $\hat{R}\equiv$

{r

;



{(1-γ

)*rave≤

r≤

(1+γ

)*raverave2

 



otherwise}}

wherein {circumflex over (R)} defines a set of said second plurality of radii;

r defines a range of said lengths defining said second plurality of radii;

r_ave is an average value of all radii defining said initial boundary points;

r_ave2 is an average value of all radii within said second plurality of radii; and

γ

is a threshold coefficient.

9. The system of claim 5, further comprising means for curve-fitting said plurality of boundary points so as to produce a closed curve.

10. The system of claim 5, wherein said image is a binary mask, and said boundary points are defined by a corresponding plurality of pixels.

11. The system of claim 10, wherein said binary mask represents a magnetic resonance image of a left ventricular epicardial boundary.