Integrated registration of dynamic renal perfusion magnetic resonance images
View Patent ↗A system and method are provided for integrated registration of images, the system including a processor, a first registration portion for performing rough registration of an image, a first segmentation portion for performing segmentation of an object of interest in the image, a second registration portion for performing fine registration of the image, and a second segmentation portion for performing segmentation of structures of the object of interest in the image; and the method including receiving a sequence of images, selecting an image from the sequence, cropping a region of interest (ROI) from the selected image, performing rough registration of the cropped ROI, performing segmentation of an object of interest from the rough registered ROI, performing fine registration of the ROI, and performing segmentation of structures of the object of interest from the fine registered ROI.
1. A method for integrated registration of images, the method comprising:
receiving a sequence of images;
selecting an image from the sequence;
cropping a region of interest (ROI) from the selected image;
performing rough registration of the cropped ROI;
performing segmentation of an object of interest from the rough registered ROI;
performing fine registration of the ROI; and
performing segmentation of structures of the object of interest from the fine registered ROI.
2. A method as defined in claim 1 wherein the images are dynamic renal perfusion magnetic resonance (MR) images.
3. A method as defined in claim 1 wherein the object of interest is a kidney.
4. A method as defined in claim 1 wherein the segmentation of an object is responsive to the rough registration.
5. A method as defined in claim 1 wherein the fine registration is responsive to at least one of the rough registration and the segmentation of an object.
6. A method as defined in claim 1 wherein each of the rough registration and the fine registration are temporal.
7. A method as defined in claim 1 wherein performing rough registration includes detecting large-scale motion.
8. A method as defined in claim 1 wherein performing fine registration includes integrating region information and local gradient information with auxiliary image segmentation results.
9. A method as defined in claim 1 wherein cropping the ROI containing the object of interest is user-controlled.
10. A method as defined in claim 1 wherein the ROI is rectangular.
11. A method as defined in claim 7 wherein large-scale motion is identified by maximizing an edge-based consistency metric that is invariant to rapidly changing contrast.
12. A method as defined in claim 1 wherein registration results are refined by integrating region information and edge information with auxiliary image segmentation results.
13. A method as defined in claim 11 , further comprising identifying the translational motion of the object of interest across the image sequence by exploiting the invariance of the consistency metric.
14. A system for integrated registration of images, the system comprising:
a processor;
a first registration portion in signal communication with the processor for performing rough registration of at least one image;
a first segmentation portion in signal communication with the processor for performing segmentation of an object of interest in the at least one image;
a second registration portion in signal communication with the processor for performing fine registration of the at least one image; and
a second segmentation portion in signal communication with the processor for performing segmentation of structures of the object of interest in the at least one image.
15. A system as defined in claim 14 wherein the second registration portion is in further signal communication with the first segmentation portion.
16. A system as defined in claim 14 wherein the second segmentation portion is in further signal communication with the second registration portion.
17. A system as defined in claim 14 , further comprising a user interface adapter for cropping a region of interest (ROI) from the at least one image.
18. A computer-readable medium, tangibly embodying a program of instructions executable by a computer to perform program steps for integrated registration of images, the program steps comprising:
receiving a sequence of images;
selecting an image from the sequence;
cropping a region of interest (ROI) from the selected image;
performing rough registration of the cropped ROI;
performing segmentation of an object of interest from the rough registered ROI;
performing fine registration of the ROI; and
performing segmentation of structures of the object of interest from the fine registered ROI.
19. A computer-readable medium as defined in claim 18 wherein the program step of performing rough registration includes detecting large-scale motion.
20. A computer-readable medium as defined in claim 19 wherein large-scale motion is identified by maximizing an edge-based consistency metric that is invariant to rapidly changing contrast.
21. A computer-readable medium as defined in claim 20 , further comprising the program step of identifying the translational motion of the object of interest across the image sequence by exploiting the invariance of the consistency metric.