System and method for neuroactivity detection in infants
A neuroactivity monitoring system includes a camera configured to acquire image data of a patient positioned on the patient support and a monitoring device in communication with the camera. The monitoring device uses the acquired image data of the camera to identify and track patient landmarks, such as facial and/or posture landmarks, and, based on the tracked movement, characterize patient neuroactivity.
1. A neuroactivity monitoring system, comprising:
a patient support;
a camera configured to acquire image data comprising video electroencephalography data of an infant positioned on the patient support; and
a monitoring device in communication with the camera, wherein the monitoring device comprises a memory storing instructions that, when executed by a processor of the monitoring device, cause the monitoring device to:
receive the acquired image data;
identify landmarks of the infant in the image data;
track movement of the identified landmarks in the image data; and
characterize a neuroactivity of the patient based on the tracked movement of the identified landmarks, wherein the landmarks comprise limbs of the infant arranged in a pose and hands detected in a defined hand bounding box comprising hand landmarks of finger tips, joints, and wrists, and wherein the neuroactivity is characterized as a seizure based at least in part on the tracked movement of the hand landmarks and limbs in a pattern.
2. The system of claim 1 , wherein the landmarks further comprise facial features of the infant, and wherein the neuroactivity is characterized as the seizure based at least in part on a determination that an identified first eye and an identified second eye are moving in different directions simultaneously.
3. The system of claim 1 , wherein the landmarks further comprise facial features of the infant comprising eyes, and wherein the neuroactivity is characterized as the seizure based at least in part on the tracked movement of a blink rate of the eyes.
4. The system of claim 1 , wherein the monitoring device is configured to generate an indication to initiate video electroencephalography monitoring based on the characterized neuroactivity.
5. A neuroactivity monitoring system, comprising:
a monitoring camera configured to acquire visible image data comprising video electroencephalography data of an infant positioned on a patient support;
an infrared camera configured to acquire infrared image data of the infant positioned on the patient support; and
a monitoring device in communication with the monitoring camera and the infrared camera, wherein the monitoring device comprises a memory storing instructions that, when executed by a processor of the monitoring device, cause the monitoring device to:
receive the acquired visible image data and the acquired infrared image data;
identify patient landmarks of the infant in the acquired visible image data;
determine a physiological parameter based on the acquired infrared image data; and
characterize a neuroactivity of the patient based on movement of the identified landmarks and the physiological parameter, wherein the landmarks comprise limbs of the infant arranged in a pose and hands detected in a defined hand bounding box comprising hand landmarks of finger tips, joints, and wrists, and wherein the neuroactivity is characterized as a seizure based at least in part on tracked movement of the hand landmarks and limbs in a pattern.
6. The system of claim 5 , wherein the neuroactivity is further characterized as a clonic seizure based on a pattern of rhythmic contraction of one or more of the identified landmarks that repeats every 1-4 seconds.
7. The system of claim 5 , wherein the neuroactivity is further characterized as a myoclonic seizure based on a pattern of isolated contraction of one or more of the identified landmarks.
8. The system of claim 5 , comprising one or more sensors in communication with the monitoring device, wherein the monitoring device receives data from the one or more sensors related to additional physiological parameters.
9. A method, comprising:
receiving image data of infant, wherein the image data comprises video electroencephalography data;
identifying one or more landmarks in the image data;
tracking movement of the one or more landmarks over time in the image data; and
determining that the movement of the one or more landmarks is indicative of a neuroactivity event, wherein the landmarks comprise limbs of the infant arranged in a pose and hands detected in a defined hand bounding box comprising hand landmarks of finger tips, joints, and wrists, and wherein the neuroactivity event is characterized as a seizure based at least in part on the tracked movement of the hand landmarks and limbs in a pattern.