System and method for image-based object modeling using multiple image acquisitions or reconstructions
Systems and methods are disclosed for integrating imaging data from multiple sources to create a single, accurate model of a patient's anatomy. One method includes receiving a representation of a target object for modeling; determining one or more first anatomical parameters of the target anatomical object from at least one of one or more first images of the target anatomical object; determining one or more second anatomical parameters of the target anatomical object from at least one of one or more second images of the target anatomical object; updating the one or more first anatomical parameters based at least on the one or more second anatomical parameters; and generating a model of the target anatomical object based on the updated first anatomical parameters.
1. A computer-implemented method of processing images to produce an anatomical model, the method comprising:
determining a plurality of probabilities associated with a plurality of images of a portion of a patient's anatomy, wherein the plurality of images was obtained (i) using two or more different reconstruction methods, (ii) using two or more imaging modalities, and/or (iii) at two or more different points of time;
determining an average of the determined probabilities; and
determining an updated volumetric model of a target anatomy of the patient by updating a volumetric model based on the determined probabilities, wherein the determined probabilities indicate a probability that a voxel of the volumetric model belongs to vasculature of the patient.
2. The method of claim 1 , wherein the plurality of probabilities includes a plurality of voxel probabilities associated with each voxel of the volumetric model that the voxel belongs to a lumen.
3. The method of claim 1 , wherein determining the plurality of probabilities includes performing a segmentation of each of the plurality of images.
4. The method of claim 1 , further comprising:
selecting a reference image from a plurality of reference images; and
registering, using three-dimensional (3D) image registration, each image among the plurality of reference images to the reference image.
5. The method of claim 4 , wherein:
the plurality of probabilities includes a plurality of voxel probabilities associated with each voxel of the volumetric model that the voxel belongs to a lumen, and
registering each image includes registering each voxel probability to a probability of the reference image.
6. The method of claim 1 , wherein:
a first image among the plurality of images was obtained using a first imaging modality associated with first boundary information, and
a second image among the plurality of images was obtained using a second imaging modality associated with second boundary information.
7. The method of claim 6 , wherein the method further comprises combining the first boundary information and the second boundary information, wherein generating the updated volumetric model includes updating the volumetric model based on the combined first boundary information and second boundary information.
8. The method of claim 7 , wherein the first boundary information includes a first lumen boundary information, the second boundary information includes a second lumen boundary information, and generating the updated volumetric model includes updating a lumen boundary of the volumetric model based on a combined first lumen boundary information and second lumen boundary information.
9. The method of claim 6 , wherein the first imaging modality is a computerized tomography (CT) scan, and the second imaging modality is a magnetic resonance (MR) scan.
10. The method of claim 1 , wherein the plurality of images include:
a first image obtained at a first time point within a cardiac cycle, and
a second image obtained at a second time point within a cardiac cycle.
11. The method of claim 10 , wherein the plurality of images include:
a plurality of first images obtained during a first image acquisition, and
a plurality of second images obtained during a second image acquisition, wherein
the second image acquisition occurred after the first image acquisition.
12. The method of claim 1 , wherein the plurality of images include a plurality of three-dimensional (3-D) images from a cardiac scanner, wherein each of the 3-D images represents a different reconstruction of a computed tomography angiography (CTA) image for the patient.
13. The method of claim 1 , wherein the updated volumetric model further includes a parameterized representation of vasculature of the patient.
14. A system of processing images to produce an anatomical model, the system comprising:
a data storage device storing instructions for processing images to produce an anatomical model; and
a processor configured to execute the instructions to perform a method including:
determining a plurality of probabilities associated with a plurality of images of a portion of a patient's anatomy, wherein the plurality of images was obtained (i) using two or more different reconstruction methods, (ii) using two or more imaging modalities, and/or (iii) at two or more different points of time;
determining an average of the determined probabilities; and
determining an updated volumetric model of a target anatomy of the patient by updating a volumetric model based on the determined probabilities, wherein the determined probabilities indicate a probability that a voxel of the volumetric model belongs to vasculature of the patient.
15. The system of claim 14 , wherein determining the plurality of probabilities includes performing a segmentation of each of the plurality of images.
16. The system of claim 14 , wherein the processor is further configured for:
selecting a reference image from a plurality of reference images; and
registering, using three-dimensional (3D) image registration, each image among the plurality of reference images to the reference image, wherein:
the plurality of probabilities includes a plurality of voxel probabilities associated with each voxel of the volumetric model that the voxel belongs to a lumen, and
registering each image includes registering each voxel probability to a probability of the reference image.
17. The system of claim 14 , wherein:
the plurality of probabilities includes a plurality of voxel probabilities associated with each voxel of the volumetric model that the voxel belongs to a lumen.
18. A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for executing a method for processing images to produce an anatomical model, the method comprising:
determining a plurality of probabilities associated with a plurality of images of a portion of a patient's anatomy, wherein the plurality of images was obtained (i) using two or more different reconstruction methods, (ii) using two or more imaging modalities, and/or (iii) at two or more different points of time;
determining an average of the determined probabilities; and
determining an updated volumetric model of a target anatomy of the patient by updating a volumetric model based on the determined probabilities, wherein the determined probabilities indicate a probability that a voxel of the volumetric model belongs to vasculature of the patient.
19. The non-transitory computer readable medium of claim 18 , wherein:
the plurality of probabilities includes a plurality of voxel probabilities associated with each voxel of the volumetric model that the voxel belongs to a lumen; and
determining the plurality of probabilities includes performing a segmentation of each of the plurality of images.
20. The system of claim 14 ,
a first image among the plurality of images was obtained using a first imaging modality associated with first boundary information, and
a second image among the plurality of images was obtained using a second imaging modality associated with second boundary information;
wherein the method further comprises combining the first boundary information and the second boundary information, wherein generating the updated volumetric model includes updating the volumetric model based on the combined first boundary information and second boundary information.