Method and system for computer-aided triage of stroke

1. A method for automatically detecting a potential ischemic condition, the method comprising:

at a computing system:

receiving a first set of images associated with a patient and taken at a first point of care;

processing the first set of images, wherein processing the set of images comprises:

producing a mirror image version of each of the first set of images, thereby producing a mirrored set of images;

overlaying and aligning the mirrored set of images with the first set of images, thereby producing an overlaid set of images;

segmenting an ischemic region from the first set of images based on a set of deep learning models, wherein a set of inputs of the set of deep learning models comprises the first set of images and the set of overlaid images;

automatically detecting the potential ischemic condition based on the segmented ischemic region;

compressing the first set of images to produce a compressed set of images;

in response to detecting the potential ischemic condition, automatically:

determining, at the computing system, a specialist associated with a treatment of the potential ischemic condition;

transmitting a notification and at least one image of the compressed set of images to a recipient, wherein the recipient is the specialist, at a client application executing on a user device associated with the specialist; and

receiving an input from the specialist at the client application, wherein the input triggers an assignment of a treatment of the patient to the specialist.

2. The method of claim 1 , wherein the specialist is associated with a second point of care remote from the first point of care.

3. The method of claim 1 , further comprising determining a first image of the at least one image of the compressed set of images, wherein the first image is provided as a thumbnail with the notification.

4. The method of claim 3 , wherein the first image corresponds to a maximum cross section of the ischemic region.

5. The method of claim 1 , further comprising receiving a read receipt at the computing system upon the specialist opening the notification, wherein in an event that the read receipt is not received within a predetermined time threshold, the method further comprises transmitting the notification and the at least one image to a second specialist at a second user device associated with the second specialist.

6. The method of claim 1 , further comprising checking for a set of inclusion criteria of the first set of images based on metadata associated with the first set of images.

7. The method of claim 1 , further comprising, after detecting the potential ischemic condition, notifying a second recipient associated with the potential ischemic condition.

8. The method of claim 7 , further comprising establishing communication between the first and second recipients.

9. The method of claim 8 , wherein the second recipient is a principal investigator associated with a clinical trial.

10. The method of claim 1 , further comprising implementing a buffering protocol, wherein the buffering protocol comprises transmitting a remainder of the compressed set of images to the first recipient at a set of times later than a first time at which the at least one image is transmitted.

11. The method of claim 1 , wherein the set of images is concurrently sent to a standard radiology workflow at the first point of care, wherein the method at least partially overlaps with the standard radiology workflow.

12. A method for automatically detecting a potential ischemic condition, the method comprising:

at a computing system:

receiving a first set of images associated with a patient;

processing the first set of images with a deep learning model, wherein processing the first set of images comprises segmenting an ischemic region corresponding to the ischemic condition, and wherein a set of inputs of the deep learning model comprises the first set of images and a mirrored version of the first set of images;

in response to detecting the potential ischemic condition based on the segmented ischemic region, automatically:

determining, at the computing system, a recipient associated with the potential ischemic condition;

transmitting a notification and at least one image determined based on the first set of images to the recipient at a client application executing on a user device associated with the recipient;

receiving an input from the recipient at the client application.

13. The method of claim 12 , wherein the ischemic condition is an ischemic core.

14. The method of claim 12 , wherein the input triggers an assignment of a treatment of the patient to a care team associated with the recipient.

15. The method of claim 14 , wherein the recipient is a specialist of the care team, wherein the care team is a stroke care team.

16. The method of claim 15 , further comprising:

transmitting the notification and the at least one image to a second recipient at a second client application executing on a second user device associated with the second recipient, wherein the second recipient is part of the stroke care team; and

establishing a communication interface between the first and second client applications.

17. The method of claim 12 , wherein the at least one image is a compressed version of an image of the first set of images.

18. The method of claim 12 , wherein the recipient is a principal investigator associated with a clinical trial.

19. The method of claim 12 , wherein a first image of the at least one image corresponds to a maximum cross section of the hyperdense region.

20. The method of claim 19 , wherein the first image is provided as a thumbnail with the notification.