Method for segmentation of the head-neck arteries, brain and skull in medical images
A method for automated segmentation of a blood vessel of a head and neck of a subject in a medical image, the method comprising: identifying the location of anatomical landmarks in the medical image; identifying regions of interest in the medical image based on the landmarks; segmenting segments of blood vessels in the medical image; classifying at least one of the segments as defining the blood vessel based on its position relative to the landmarks within the regions of interest to create a classified blood vessel; identifying a starting seed for the blood vessel from the classified blood vessel; identifying an ending seed for the blood vessel from the classified blood vessel; segmenting the blood vessel between the starting seed and the ending seed; and defining a path between the starting seed and the ending seed.
1. A system for segmentation of a blood vessel of a subject in a medical image wherein the medical image comprises a plurality of slices, the system comprising a processor for executing the steps of:
automatically identifying a plurality of landmark slices in the plurality of slices, the plurality of landmark slices containing each anatomical landmark of one or more anatomical landmarks in the medical image;
automatically identifying relevant landmark slices for finding the blood vessel based on positional relationships of the landmarks and the blood vessel;
automatically prompting for manual identification of a seed for the blood vessel in response to being unable to automatically identify a blood vessel component;
receiving an input indicative of manual identification of the seed for the blood vessel from within a set of slices that is constrained to the relevant landmark slices; and
automatically segmenting the blood vessel based on the input indicative of manual identification of the seed for the blood vessel from within a set of slices that is constrained to the relevant landmark slices.
2. The system according to claim 1 , wherein the landmarks comprise at least one of the lungs, trachea, brain, skull, or segmented blood vessels.
3. The system according to claim 1 , wherein the seed includes a first seed in a first blood vessel at a first position and a second seed in a blood vessel at a second position.
4. The system according to claim 3 , further comprising:
ballooning the first and second seeds using a fast marching tool that has a predetermined local cost in a Hounsfield unit range between one hundred and fifty and five hundred and twenty-five.
5. The system according to claim 4 , wherein the fast marching tool has an exponential cost outside the one hundred and fifty to five hundred and twenty-five as at a scale of twenty.
6. The system according to claim 5 , wherein the balloon runs repeatedly for multiple iterations.
7. The system according to claim 6 , wherein the first and second seeds for each iteration are a result of a previous iteration and a stopping criteria is a path cost of five.
8. The system according to claim 1 , further comprising:
automatically identifying a first seed in a first blood vessel, wherein the prompt for the seed is for a second seed in a second blood vessel at a same slice where the first seed in the first blood vessel is identified.
9. The system according to claim 1 , wherein the prompt for the seed is a prompt for a seed on a lowest slice of a region of interest.
10. The system according to claim 1 , wherein the prompt for the seed is a prompt for a seed in a slice which is located two centimeters above a top lung slice.
11. The system according to claim 1 , wherein the prompt for the seed is part of user aided recovery of the segmentation of the blood vessel.
12. The system according to claim 1 , wherein the prompt for the seed is part of user aided recovery of seed selection.
13. The system according to claim 1 , wherein the seed includes a first seed in a first common carotid at a first position of two centimeters above a lung slice and a second seed in a second common carotid at a second position of two centimeters above a lung slice.
14. The system according to claim 1 , further comprising:
automatically identifying a first seed in a first common carotid, wherein the prompt for the seed is for a second seed in a second common carotid at a same slice where the first seed in the first common carotid is identified.
15. The system according to claim 1 , wherein the prompt for the seed is for seeds in middle cerebral arteries in a slice of 1.5 centimeters below a slice with a largest cross section in a brain segmentation.
16. The system according to claim 1 , further comprising:
automatically identifying a first seed in middle cerebral arteries, wherein the prompt for the seed is for a second seed in the middle cerebral arteries at a same slice where the first seed in the middle cerebral arteries is identified.
17. The system according to claim 1 , wherein the prompt of the seed is for seeds in a basilar artery in a middle slice between a skull base slice and a slice where seeds of middle cerebral arteries are located.
18. The system according to claim 17 , wherein the prompt of the seed is for seeds in a basilar artery in an average of a middle slice between a skull base slice and a slice where seeds of middle cerebral arteries are located.
19. The system according to claim 1 , wherein the prompt for the seed is for seeds in vertebral arteries and includes a seed on a lowest slice of a region of interest.
20. The system according to claim 1 , further comprising:
automatically identifying a first seed in vertebral arteries, wherein the prompt for the seed is for a second seed in the vertebral arteries at a same slice where the first seed in the vertebral arteries is identified.