Methods and systems for extracting blood vessel
Methods and systems for determining a region of interest (ROI) in an image associated with a subject are provided. Slice information of multiple slices of an image are identified and multiple slice ranges are determined based on the slice information. Based on the slice ranges, multiple sub-images of the image are then determined. For each sub-image, a template and a corresponding probability graph are acquired, a registration result is determined by registering the sub-image with the template, and a ROI in the sub-image is identified based on the registration result. A ROI of the image can be determined by combining the ROIs of the sub-images.
1. A method for determining a region of interest (ROI) in an image associated with a subject implemented on at least one machine each of which has at least one processor and at least one storage, the method comprising:
identifying slice information relating to multiple slices included in the image;
determining a plurality of slice ranges in the multiple slices based on the slice information;
determining a plurality of sub-images based on the plurality of slice ranges;
for each of the plurality of sub-images,
acquiring a template corresponding to the sub-image, wherein the template has a corresponding probability graph, the template is determined by registering, filtering, or averaging a plurality of reference images, and the probability graph is determined by:
for each of the plurality of reference images,
determining an ROI in the reference image;
determining an ROI mask based on the ROI in the reference image;
mapping a plurality of ROI masks corresponding to the plurality of reference images to a same coordinate space; and
determining probabilities that pixels in the template are within an ROI in the template based on pixels in the mapped ROI masks in the same coordinate space, the ROI in the template corresponding to the plurality of ROI masks;
determining a registration result by registering the sub-image with the template; and
identifying an ROI in the sub-image based on the registration result; and
determining an ROI in the image by combining a plurality of ROIs corresponding to the plurality of sub-images.
2. The method of claim 1 , wherein
the sub-image includes at least one of a head sub-image or a neck sub-image;
the template includes at least one of a head image template or a neck image template; and
the ROI includes at least one of a head ROI or a neck ROI.
3. The method of claim 1 , wherein the ROI is a region where a blood vessel is located in the image.
4. The method of claim 1 , wherein a shape of the ROI is a tubule, a ring, a circle, an oval, a triangle, a rectangle, or an irregular shape.
5. The method of claim 1 , wherein the slice information relating to the multiple slices includes at least one of a size of each of the multiple slices, a shape of each of the multiple slices, or a position of each of the multiple slices.
6. The method of claim 1 , wherein the template is determined based on the plurality of reference images according to a statistical approach.
7. The method of claim 1 , wherein the plurality of reference images are images of a group sharing at least one characteristic with the subject.
8. The method of claim 1 , wherein the determining the registration result by registering the sub-image with the template includes:
determining the registration result by registering the sub-image with the template according to an affine registration.
9. The method of claim 1 , wherein the determining the registration result by registering the sub-image with the template includes:
determining one or more anatomical structural features in the sub-image and the template;
performing an initial alignment on the sub-image and the template based on the one or more anatomical structural features; and
registering the sub-image with the template based on an initial alignment result.
10. The method of claim 1 , wherein the image includes a computed tomography angiography (CTA) image.
11. A system for determining a region of interest (ROI) in an image associated with a subject, comprising:
at least one storage device including a set of instructions; and
at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is directed to cause the system to:
identify slice information relating to multiple slices included in the image;
determine a plurality of slice ranges in the multiple slices based on the slice information;
determine a plurality of sub-images based on the plurality of slice ranges;
for each of the plurality of sub-images,
acquiring a template corresponding to the sub-image, wherein the template has a corresponding probability graph, the template is determined by registering, filtering, or averaging a plurality of reference images, and the probability graph is determined by:
for each of the plurality of reference images,
determining an ROI in the reference image;
determining an ROI mask based on the ROI in the reference image;
mapping a plurality of ROI masks corresponding to the plurality of reference images to a same coordinate space; and
determining probabilities that pixels in the template are within an ROI in the template based on pixels in the mapped ROI masks in the same coordinate space, the ROI in the template corresponding to the plurality of ROI masks;
determining a registration result by registering the sub-image with the template; and
identifying an ROI in the sub-image based on the registration result and the probability graph; and
determining an ROI in the image by combining a plurality of ROIs corresponding to the plurality of sub-images.
12. The system of claim 11 , wherein
the sub-image includes at least one of a head sub-image or a neck sub-image;
the template includes at least one of a head image template or a neck image template; and
the ROI includes at least one of a head ROI or a neck ROI.
13. The system of claim 11 , wherein the ROI is a region where a blood vessel is located in the image.
14. The system of claim 11 , wherein a shape of the ROI is a tubule, a ring, a circle, an oval, a triangle, a rectangle, or an irregular shape.
15. The system of claim 11 , wherein the slice information relating to the multiple slices includes at least one of a size of each of the multiple slices, a shape of each of the multiple slices, or a position of each of the multiple slices.
16. The system of claim 11 , wherein the template is determined based on the plurality of reference images according to a statistical approach.
17. The system of claim 11 , wherein the plurality of reference images are images of a group sharing at least one characteristic with the subject.
18. The system of claim 11 , wherein to determine the registration result by registering the sub-image with the template, the at least one processor is directed to cause the system to:
determine the registration result by registering the sub-image with the template according to an affine registration.
19. The system of claim 11 , wherein to determine the registration result by registering the sub-image with the template, the at least one processor is directed to cause the system to:
determine one or more anatomical structural features in the sub-image and the template;
perform an initial alignment on the sub-image and the template based on the one or more anatomical structural features; and
register the sub-image with the template based on an initial alignment result.
20. The method of claim 11 , wherein the image includes a computed tomography angiography (CTA) image.