System and method for image composition
A system and method for obtaining a composite image by combining multiple sub-images are provided. In some embodiments, the method may include retrieving overlapping images corresponding to sub-images including 3D volume data, generating two-dimensional (2D) projection images and pixel maps based on the overlapping images, performing one or more registrations based on the 2D projection images and the pixel maps, calibrating the sub-images based on the results of the registration(s), and fusing the sub-images to produce a composite image. In some embodiments, the method may include setting a plurality of parameters relating to an X-radiation source or a radiation detector based on a preliminary number of exposures and a preliminary exposure region, controlling, based on at least one of the plurality of parameters, a motion of the X-radiation source or a motion of the radiation detector to capture a plurality of sub-images, and combining the plurality of sub-images.
1. An image composition system comprising:
an acquisition engine configured to retrieve a first sub-image and a second sub-image; the first sub-image corresponding to a first set of 3D volume data, and the second sub-image corresponding to a second set of 3D volume data;
an image processing engine configured to perform operations comprising
retrieving a first overlapping image from the first sub-image;
retrieving a second overlapping image from the second sub-image;
generating a first 2D projection image and a first pixel map based on maximum intensity projection of the first overlapping image onto a plane;
generating a second 2D projection image and a second pixel map based on maximum intensity projection of the second overlapping image onto the plane;
performing 2D registration based on the first 2D projection image, the first pixel map, the second 2D projection image, and the second pixel map;
performing 3D registration based on the 2D registration, the first pixel map, or the second pixel map;
identifying a correlation between of the first sub-image including the first overlapping image and the second sub-image including the second overlapping image based on the 2D registration or the 3D registration; and
fusing the first overlapping image and the second overlapping image based on the correlation to provide a composite image.
2. The image composition system of claim 1 , the first sub-image or the second sub-image comprising a coronal image, a sagittal image, or a transverse image.
3. The image composition system of claim 1 , the plane comprising a coronal plane, a sagittal plane, or a transverse plane.
4. The image composition system of claim 1 , retrieving the first sub-image or retrieving the second sub-image comprising using DSA (digital subtraction angiography), CT (computed tomography), CTA (computed tomography angiography), PET (positron emission tomography), X-ray, MM (magnetic resonance imaging), MRA (magnetic resonance angiography), SPECT (single-photon emission computerized tomography), or US (ultrasound scanning).
5. The image composition system of claim 1 , retrieving the first overlapping image or retrieving the second overlapping image comprising using Digital Imaging and Communication in Medicine.
6. The image composition system of claim 1 , performing 2D registration comprising calculating an offset in a direction within the plane, and
the offset comprising an X offset, a Y offset, a Z offset, a coronal offset, a sagittal offset, or a transverse offset.
7. The image composition system of claim 1 , the performing 3D registration comprising calculating an offset in a direction perpendicular to the plane, and
the offset comprising an X offset, a Y offset, a Z offset, a coronal, a sagittal offset, or a transverse offset.
8. The image composition system of claim 1 further comprising
performing a fine registration based on recursion, a bisection method, an exhaustive method, a greedy algorithm, a divide and conquer algorithm, dynamic programming method, an iterative method, a branch-and-bound algorithm, or a backtracking algorithm.
9. The image composition system of claim 1 ,
the first pixel map comprising information identifying first locations of maximum intensity of the first overlapping image, the first locations being in a direction perpendicular to the plane; and
the second pixel map comprising information identifying second locations of maximum intensity of the second overlapping image, the second locations being in a direction perpendicular to the plane.
10. The image composition system of claim 9 , the performing 3D registration comprising
calculating a plurality of differences between the first locations and the second locations, each one of the plurality of differences corresponding to a pixel within the plane;
comparing the plurality of differences to obtain a probability of the differences; and
designating an offset in the direction perpendicular to the plane based on the probability.
11. The image composition system of claim 10 , the second pixel map comprising a calibrated pixel map based on the 2D registration.