Multi-step vessel segmentation and analysis
Multi-step vessel segmentation and analysis is provided. In various embodiments, a branch detection algorithm is applied to a medical image to determine a plurality of branches of a blood vessel appearing in the medical image. A plurality of segments of the blood vessel appearing in the medical image is determined. Each of the plurality of segments is bounded by one of the plurality of branches. An edge detection algorithm is applied piecewise to each of the plurality of segments. A composite blood vessel outline is formed from the piecewise edge detection.
1. A method comprising:
applying a branch detection algorithm to a medical image to determine a plurality of branches of a blood vessel appearing in the medical image;
determining a plurality of segments of the blood vessel appearing in the medical image, each of the plurality of segments being bounded by one of the plurality of branches;
applying an edge detection algorithm piecewise to each of the plurality of segments;
forming a composite blood vessel outline from the piecewise edge detection.
2. The method of claim 1 , further comprising:
adding annotations to the medical image corresponding to each of the plurality of segments.
3. The method of claim 1 , further comprising:
measuring a width of the blood vessel within each of the plurality of segments.
4. The method of claim 1 , further comprising:
determining the relative dominance of each of the plurality of segments.
5. The method of claim 3 , further comprising:
determining the presence of stenosis based on the width.
6. The method of claim 1 , wherein the medical image originates from a modality, the modality being x-ray angiography, X-ray plain film, ultrasound, magnetic resonance, nuclear medicine imaging, positron emission tomography, or computed tomography.
7. The method of claim 1 , further comprising determining a centerline of the blood vessel from the composite blood vessel outline.
8. The method of claim 1 , further comprising:
registering at least one of the plurality of segments in an anatomical atlas.
9. The method of claim 8 , further comprising:
exporting the plurality of segments to a reporting system or a hemodynamic system.
10. The method of claim 3 , further comprising:
determining a stenosis value based on the width of the blood vessel within each of the plurality of segments.
11. The method of claim 9 , wherein exporting the plurality of segments comprises applying syntax scoring.
12. The method of claim 9 where the completed automatic segmentation, labelling and stenosis values are displayed in the viewing and reporting systems as a coronary tree diagram.
13. A method comprising:
displaying to a user a first plurality of medical images;
receiving from a user indications of edges of blood vessels in the first plurality of medical images;
training a neural network based on the indications of edges of blood vessels;
applying the neural network to a second plurality of medical images;
receiving from the neural network indications of edges of blood vessels in the second plurality of medical images;
displaying to a user the indications of edges of blood vessels in the second plurality of medical images;
receiving from the user an acceptance or rejection of each of the indications of edges of blood vessels in the second plurality of medical images;
further training the neural network based on those indications of edges of blood vessels in the second plurality of medical images accepted by the user.
14. A computer program product for vessel segmentation, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:
applying a branch detection algorithm to a medical image to determine a plurality of branches of a blood vessel appearing in the medical image;
determining a plurality of segments of the blood vessel appearing in the medical image, each of the plurality of segments being bounded by one of the plurality of branches;
applying an edge detection algorithm piecewise to each of the plurality of segments;
forming a composite blood vessel outline from the piecewise edge detection.
15. The computer program product of claim 14 , further comprising:
adding annotations to the medical image corresponding to each of the plurality of segments.
16. The computer program product of claim 14 , further comprising:
measuring a width of the blood vessel within each of the plurality of segments.
17. The computer program product of claim 16 , further comprising:
determining the presence of stenosis based on the width.
18. The computer program product of claim 14 , further comprising:
determining the relative dominance of each of the plurality of segments.
19. The computer program product of claim 14 , wherein the medical image originates from a modality, the modality being x-ray angiography, X-ray plain film, ultrasound, magnetic resonance, nuclear medicine imaging, positron emission tomography, or computed tomography.
20. The computer program product of claim 14 , further comprising determining a centerline of the blood vessel from the composite blood vessel outline.