Method, apparatus and computer program product for automatic segmenting of cardiac chambers

• US 7,864,997 B2
• Filed: 04/28/2006
• Issued: 01/04/2011
• Est. Priority Date: 04/28/2006
• Status: Active Grant

• Current Assignee: PIE Medical Imaging BV
• Original Assignee: Pie Medical Imaging B.V. (Esaote SpA)
• Inventors: Aben, Jean-Paul Maria Michel
• Primary Examiner(s): Bali; Vikkram
• Assistant Examiner(s): Bitar; Nancy
• Application Number:
  US11/380,681
• Publication Number:
  US 20070253609A1
• Time in Patent Office: 1,712 Days
• Field of Search: 382/128, 382/129, 382/130, 382/131, 382/132, 382/154, 434262-272, 378 1-210, 600/410, 600/372
• US Class Current: 382/128
• CPC Class Codes: G06T 2207/10076 4D tomography; Time-sequential 3D tomography
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models

Abstract

A method, apparatus and computer program product for machine-based segmentation of the cardiac chambers in a four-dimensional magnetic resonance image data that contains at least short-axis cine sequences. The segmenting is based on temporal variations in the data set and on features extracted from the image data. In particular, the method and apparatus process the image data to automatically segment an endocard based on fuzzy object extraction and to automatically segment an epicard through finding a radial minimum cost with dynamic sign definition and tissue classification. In addition, image data is preferably preprocessed to eliminate high local image variances and inhomogeneity. The image data is also preferably processed to identify positions of a base slice, an apex slice, an end-diastole, an end-systole and an LVRV connection.

Claims

1. A method for machine-based segmentation of a cardiac chamber in four-dimensional magnetic resonance image data that contains short-axis cine sequences and long-axis cine sequences, the segmentation based on temporal variations in the image, the method performed by a data processing system with access to the image data, the method comprising:

preprocessing the image data to eliminate high local image variances and inhomogeneity;

processing the image data to localize the cardiac chamber within the image data by identifying positions of a base slice, an apex slice, an end-diastole phase, and an end-systole phase;

machine-based segmentation of an endocard based on fuzzy object extraction;

machine-based segmentation of an epicard through finding a radial minimum cost with dynamic sign definition and tissue classification; and

determining a volume of the cardiac chamber based upon the segmentations of the endocard and epicard, the volume corrected on the basis of an apex position on a curve which is obtained from image data corresponding to long-axis cine sequences.

2. A method as claimed in claim 1, wherein:

said cine sequences furthermore comprise two-chamber cine sequences and four-chamber cine sequences.

3. A method as claimed in claim 1, further comprising:

correcting for data acquisition movements.

4. A method as claimed in claim 1, further comprising:

automatic segmentation of the papillary muscles of the heart.

5. A method as claimed in claim 4, further comprising:

automatic detection of a position of an LVRV connection, the LVRV connection being a posterior junction between a right ventricle and the interventricular septum.

6. A method as claimed in claim 1, further comprising:

allowing for operator inspection of a subject-caused movement in the acquired MR image dataset by using system coordinates from an MR scanner apparatus.

7. A method as claimed in claim 6, further comprising:

automatic correction for subject-caused movement in the acquired MR image dataset by using system coordinates from an MR scanner apparatus.

8. A method as claimed in claim 1, wherein:

the segmentation of the endocard based on fuzzy object extraction starts from a seed contour.

9. A method as claimed in claim 1, wherein:

said volume correction takes into account a mitral valve position obtained from data corresponding to long axis cine sequences.

19. A method as claimed in claim 1, wherein:

the curve is obtained from image data corresponding to two-chamber and 4-chamber long axis cine sequences.

10. An apparatus for machine-based segmentation of a cardiac chamber in a four-dimensional magnetic resonance image data that contains short-axis cine sequences and long-axis cine sequences, the segmentation based on temporal variations in the data set and on features extracted from the image, the apparatus comprising:

preprocessing means for preprocessing the image data to eliminate high local image variances and inhomogeneity;

means for processing the image data to localize the cardiac chamber within the image data by identifying positions of a base slice, an apex slice, an end-diastole phase, and an end-systole phase;

means for machine-based segmentation of an endocard based on fuzzy object extraction;

means for machine-based segmentation of an epicard through finding a radial minimum cost with dynamic sign definition and tissue classification; and

means for determining a volume of the cardiac chamber based upon the segmentations of the endocard and epicard, the volume corrected on the basis of an apex position on a curve which is obtained from image data corresponding to long-axis cine sequences.

11. An apparatus as claimed in claim 10, wherein:

said cine sequences furthermore comprise two-chamber cine sequences and four-chamber cine sequences.

12. An apparatus as claimed in claim 10, wherein:

the machine-based segmentation of the endocard is based on a seed contour.

20. An apparatus as claimed in claim 10, wherein:

the curve is obtained from image data corresponding to two-chamber and 4-chamber long axis cine sequences.

13. A non-transitory computer readable medium that is installable onto a computer processing platform, the computer readable medium readable by the computer processing platform, tangibly embodying a non-transitory program of instructions executable by the computer processing platform to perform methods steps for machine-based segmentation of the cardiac chambers in four-dimensional magnetic resonance image data that contains short-axis cine sequences and long- axis cine sequences, the segmentation based on temporal variations in the image and on features extracted from the image, the method steps comprising:

preprocessing the image data to eliminate high local image variances and inhomogeneity;

processing the image data to identify positions of a base slice, an apex slice, an end-diastole phase, and an end-systole phase

machine-based segmentation of an endocard based on fuzzy object extractions;

machine-based segmentation of an epicard through finding a radial minimum cost with dynamic sign definition and tissue classification; and

determining a volume of the cardiac chamber based upon the segmentations of the endocard and epicard, the volume corrected on the basis of an apex position on a curve which is obtained from image data corresponding to long-axis cine sequences.

15. A computer readable medium as claimed in claim 13, the method steps further comprising:

automatic segmentation of the papillary muscles of the heart.

16. A computer readable medium as claimed in claim 13, the method steps further comprising:

allowing for operator inspection of a subject-caused movement in the acquired MR image dataset by using system coordinates from an MR scanner apparatus.

17. A computer readable medium as claimed in claim 16, the method steps further comprising:

automatic correction for subject-caused movement in the acquired MR image dataset by using system coordinates from an MR scanner apparatus.

18. A computer readable medium as claimed in claim 13, wherein:

the curve is obtained from image data corresponding to two-chamber and 4-chamber long axis cine sequences.

14. A computer readable medium as claimed in claimed 13, the method steps further comprising:

correcting for data acquisition movements.