Vascular dissection detection and visualization using a superimposed image
Methods and systems for detecting a dissection in surface of an elongated structure in a three dimensional medical image. One system includes an electronic processor configured to receive the three dimensional medical image and determine a periphery of the elongated structure included in the three dimensional medical image. The electronic processor is also configured to generate a non-contrast image representing the periphery of the elongated structure and superimpose a contrast image associated with the three dimensional image on top of the non-contrast image to generate a superimposed image. The electronic processor is also configured to detect at least one dissection in the elongated structure using the superimposed image and output a medical report identifying the at least one dissection detected in the elongated structure.
1. A system for detecting a dissection in surface of an elongated structure in a three dimensional medical image, the system comprising:
an electronic processor configured to
receive the three dimensional medical image,
determine a periphery of the elongated structure included in the three dimensional medical image,
generate a non-contrast image representing the periphery of the elongated structure,
superimpose a contrast image associated with the three dimensional image on top of the non-contrast image to generate a superimposed image,
detect at least one dissection in the elongated structure using the superimposed image,
output a medical report identifying the at least one dissection detected in the elongated structure, and
in response to detecting the at least one dissection of the elongated structure, increasing a priority level associated with a medical study associated with the three dimensional medical image.
2. The system of claim 1 , wherein the electronic processor is configured to detect the at least one dissection using at least one selected from a group consisting of a radial measurement of the periphery of the elongated structure, a comparison of an area measurement for the non-contrast image to an area measurement for the contrast image, and a volumetric false lumen size criteria.
3. The system of claim 1 , wherein the electronic processor is configured to determine the periphery of the elongated structure by
determining a centerline of the elongated structure, and
performing a single segmentation of a non-enhancing part of the elongated structure.
4. The system of claim 1 , wherein the electronic processor is configured to determine the periphery of the elongated structure by
determining a centerline of the elongated structure, and
determining segmentation of an enhancing part of the elongated structure and a non-enhancing part of the elongated structure.
5. The system of claim 1 , wherein the three dimensional medical image is a non-contrast medical image.
6. The system of claim 1 , wherein the electronic processor is configured to provide an alert to a user by at least one selected from a group consisting of providing an alert to an emergency room, routing a medical study associated with the three dimensional medical image to a particular specialist or a particular practice, and directly notifying the particular specialist.
7. The system of claim 1 , wherein the electronic processor is further configured to classify the at least one dissection as at least one selected from a group consisting of a Stanford type A and a Stanford type B.
8. The system of claim 1 , wherein the non-contrast image includes a true lumen.
9. The system of claim 1 , wherein the electronic processor is configured to detect a hematoma by analyzing the superimposed image using machine learning.
10. The system of claim 1 , wherein the electronic processor is configured to detect an ulcer by analyzing the superimposed image using machine learning.
11. A method for detecting a vascular dissection in an elongated structure in a three dimensional medical image, the method comprising:
receiving, with an electronic processor, the three dimensional medical image;
determining, with the electronic processor, a periphery of the elongated structure included in the three dimensional medical image;
generating, with the electronic processor, a non-contrast image representing the periphery of the elongated structure;
superimposing, with the electronic processor, a contrast image associated with the three dimensional image on top of the non-contrast image to generate a superimposed image;
detecting, with the electronic processor, at least one dissection of the elongated structure using the superimposed image;
outputting, with the electronic processor, a medical report identifying the at least one dissection detected in the elongated structure, and
in response to detecting the at least one dissection of the elongated structure, increasing a priority level associated with a medical study associated with the three dimensional medical image.
12. The method of claim 11 , wherein detecting the periphery of the elongated structure includes
determining a centerline of the elongated structure, and
detecting a plurality of two dimensional cross sections of the three dimensional medical image based on the centerline.
13. The method of claim 11 , wherein detecting the periphery of the elongated structure included in the three dimensional medical image includes detecting the periphery of the elongated structure included in the three dimensional medical image without using a contrast agent.
14. The method of claim 11 , further comprising:
in response to detecting the at least one dissection of the elongated structure, providing an alert to a user.
15. The method of claim 14 , wherein providing the alert to the user includes at least one selected from a group consisting of providing the alert to an emergency room, routing a medical study associated with the three dimensional medical image to a particular specialist or a particular practice, and directly notifying the particular specialist.
16. The method of claim 11 , wherein detecting the periphery of the elongated structure included in the three dimensional medical image includes detecting a vessel contour that includes a true lumen and a false lumen.
17. The method of claim 11 , wherein detecting the at least one dissection of the elongated structure includes analyzing the superimposed image using machine learning to detect the at least one dissection of the elongated structure.
18. A non-transitory computer readable medium including instructions that, when executed by an electronic processor, causes the electronic processor to execute a set of functions, the set of functions comprising:
receiving the three dimensional medical image;
determining a periphery of the elongated structure included in the three dimensional medical image;
generating a non-contrast image representing the periphery of the elongated structure;
superimposing a contrast image associated with the three dimensional image on top of the non-contrast image to generate a superimposed image;
detecting at least one dissection of the elongated structure using the superimposed image;
outputting a medical report identifying the at least one dissection detected in the elongated structure; and
in response to detecting the at least one dissection of the elongated structure, increasing a priority level associated with a medical study associated with the three dimensional medical image.
19. The non-transitory computer readable medium of claim 18 , wherein the set of functions further comprises:
in response to detecting the at least one dissection of the elongated structure, providing an alert to a user,
wherein providing the alert to the user includes at least one selected from a group consisting of increasing a priority level associated with a medical study associated with the three dimensional medical image, providing the alert to an emergency room, routing the medical study associated with the three dimensional medical image to a particular specialist or a particular practice, and directly notifying the particular specialist.