Seizure detection

• US 10,147,184 B2
• Filed: 12/30/2016
• Issued: 12/04/2018
• Est. Priority Date: 12/30/2016
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: Kusens, Michael, Kusens, Neil
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US15/396,263
• Publication Number:
  US 20180189946A1
• Time in Patent Office: 704 Days
• Field of Search: 382100, 382103, 382106-107, 382128-134, 382154-155, 382162, 382168, 382173, 382181, 382190, 382199, 382203, 382209, 382214, 382219, 382232, 382254, 382274, 382276, 382286-291, 382305, 382312, 128903, 705 2, 600476, 600474, 3482221, 348135
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/0016 involving temporal comparison
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G08B 21/043 detecting an emergency event, e.g. a fall
• CPC Class Codes: G08B 21/0476 Cameras to detect unsafe condition, e.g. video cameras

Abstract

Systems, methods and media for detecting a seizure use one or more 3D cameras to monitor an individual. The 3D cameras may detect rigidity and/or rapid movements associated with the tonic or clonic phases of a seizure. Body position and/or movements consistent with a seizure may cause the system or media to alert the individual, a central monitoring system, caregivers, and/or others.

Claims

1. A system for detecting seizures, the system comprising:

one or more 3D motion sensors located to provide the one or more 3D motion sensors with a view of a person to be monitored, the 3D motion sensors configured to collect a series of images of the person;

a computerized monitoring system communicatively coupled to the one or more 3D motion sensors, the computerized monitoring system configured to;

establish a detection zone defining an area or volume less than the full view captured by the 3D motion sensor around the person,

using data captured from within the detection zone, identify one or more reference points on a detected skeleton of the person,

determine a rate of movement and a duration of movement for one or more reference points within the detection zone between two or more images in the series of images, and

determine whether the rate of movement and the duration of movement are consistent with a seizure; and

a computerized communication system communicatively coupled to the computerized monitoring system, the computerized communication system configured to send an alert to one or more designated recipients based on a determination that the rate of movement and the duration of movement are consistent with a seizure.

2. The system of claim 1, further comprising a central monitoring system communicatively coupled to the computerized communication system, the central monitoring system configured to display at least a portion of the series of images of the person.

3. The system of claim 2, wherein the central monitoring system comprises a primary display and an alert display.

4. The system of claim 3, wherein the alert display is a dedicated portion of the primary display.

5. The system of claim 3, wherein if the computerized monitoring system determines the rate and duration of movement is consistent with a seizure, the computerized communication system sends an alert to the central monitoring system, and the central monitoring system moves a display of at least a portion of the series of images of the person from the primary display to the alert display.

6. The system of claim 2, wherein the computerized communication system is configured to send a message to the person being monitored.

7. The system of claim 2, further comprising a database communicatively coupled to at least one of the computerized communication system and the central monitoring system.

8. A computerized method for detecting seizure symptoms, the method implemented by one or more processors and comprising:

receiving, from a 3D motion sensor, two or more images of a person taken at different time points;

identifying the person in the two or more images;

establishing a detection zone defining an area or volume less than the full view captured by the 3D motion sensor around the person;

based on data from the detection zone, determining a rate of movement and a duration of movement for at least a portion of the person in the images;

determining whether the rate of movement and the duration of movement are consistent with a seizure; and

communicating a determination that the rate of movement and duration of movement are consistent with a seizure.

9. The method of claim 8, wherein the detection zone is automatically adjusted to move with movement of the person.

10. The method of claim 8, wherein it is determined that the rate and duration of movement is consistent with a seizure if one or both of the rate and duration of movement exceeds a predefined threshold.

11. The method of claim 10, further comprising alerting the person or a designated recipient if the rate and duration of movement is consistent with a seizure.

12. The method of claim 10, wherein the person is alerted, and further comprising monitoring whether the rate and duration of movement changes after alerting the person.

13. The method of claim 12, further comprising alerting a designated recipient if, after alerting the person, the person does not provide a response recognized as reassuring.

14. The method of claim 13, wherein the designated recipient comprises a caregiver or a central monitoring system.

15. The method of claim 14, wherein the designated recipient comprises a central monitoring system, and alerting the central monitoring system causes a display of the images of the person to move from a primary monitoring display to an alert monitoring display.

16. The method of claim 8, wherein identifying the person in the images comprises detecting a skeleton of the person.

17. The method of claim 16, wherein determining the rate of movement and the duration of movement comprises determining a rate of movement and a duration of movement for one or more reference points on the detected skeleton.

18. The method of claim 8, wherein identifying the patient comprises detecting a blob of a size within a range of pre-determined sizes using infrared images from the 3D motion sensor.

19. The method of claim 18, wherein determining the rate of movement and the duration of movement comprises determining a rate of movement and a duration of movement for the blob or one or more sub blobs within the blob.

20. The method of claim 8, wherein the detection zone is automatically established upon identifying the person within the two or more images.