System and method for animal seizure detection and classification using video analysis

1. A system for detecting animal seizure behavior, comprising:

a seizure analysis module implementable by a processor configured to analyze video images including images of an animal to detect and classify seizure behavior of the animal,

wherein the seizure analysis module comprises:

an animal identification module configured to segregate images of the animal from the video images;

a posture and body part identification module configured to identify a posture of the animal as one of a set of predetermined postures and to identify at least one body part of the animal;

a seizure-salient feature detection module configured to detect at least one of seizure-salient features using the posture and the at least one body part of the animal; and

a seizure detection and classification module configured to detect and classify occurrences of seizure behavior in the video images using the seizure-salient features and to calculate seizure parameters, including a type of seizure.

2. The system of claim 1 , further comprising a behavior identification module configured to identify a behavior of the animal as one of a set of predetermined behaviors.

3. The system of claim 1 , wherein the seizure-salient features include a Tail Raise feature.

4. The system of claim 1 , wherein the seizure-salient features include a Lordotic Posture feature.

5. The system of claim 1 , wherein the seizure-salient features include a Forelimb Clonus feature.

6. The system of claim 1 , wherein the seizure-salient features include an Overall Body Motion feature.

7. The system of claim 1 , wherein the seizure-salient features include a Bounding Box feature.

8. The system of claim 1 , wherein the seizure-salient features include a Rearing feature.

9. The system of claim 1 , wherein the seizure-salient features include a Chewing Motion feature.

10. The system of claim 1 , wherein the type of seizure is a type P3, a type P4,or a type P5.

11. The system of claim 1 , wherein the animal is a mouse.

12. The system of claim 1 , wherein the animal is a rat.

13. A method for detecting animal seizure behavior, the method comprising:

acquiring video image data of an animal;

electronically communicating the video image data to a seizure analysis module;

segregating one or more images of the animal from the video image data using the seizure analysis module;

identifying using the seizure analysis module at least one posture of the animal as one of a set of postures based on the segregated one or more images of the animal;

identifying using the seizure analysis module at least one body part of the animal based on the segregated one or more images of the animal;

detecting using the seizure analysis module at least one seizure-salient feature of the animal using the at least one identified posture and the at least one body part of the animal; and

detecting and classifying using the seizure analysis module occurrences of one or more seizures using the at least one detected seizure-salient feature, comprising calculating seizure parameters, including classifying a detected seizure as a type of seizure;

whereing at least the steps of image segregation, posture identification, body part identification, and seizure detection are implementable by a processor.

14. The method of claim 13 , further comprising identifying a behavior of the animal as one of a set of predetermined behaviors using a behavior identification module.

15. The method of claim 13 , wherein the seizure-salient features include a Tail Raise feature.

16. The method of claim 13 , wherein the seizure-salient features include a Lordotic Posture feature.

17. The method of claim 13 , wherein the seizure-salient features include a Forelimb Clonus feature.

18. The method of claim 13 , wherein the seizure-salient features include an Overall Body Motion feature.

19. The method of claim 13 , wherein the seizure-salient features include a Bounding Box feature.

20. The method of claim 13 , wherein the seizure-salient features include a Rearing feature.

21. The method of claim 13 , wherein the seizure-salient features include a Chewing Motion feature.

22. The method of claim 13 , wherein the type of seizure is a type P3, a type P4, or a type P5.

23. The method of claim 13 , wherein the animal is a mouse.

24. The method of claim 13 , wherein the animal is a rat.

25. A computer-readable medium comprising instructions for detecting animal seizure behavior by:

acquiring video images of an animal;

segregating images of the animal from the video images;

identifying at least one posture of the animal as one of a set of predetermined postures using the segregated images of the animal;

identifying at least one body part of the animal using the segregated images of the animal;

detecting at least one of seizure-salient features of the animal using the at least one posture and the at least one body part of the animal; and

detecting and classifying occurrences of seizures using the seizure-salient features, comprising calculating seizure parameters, including classifying a detected seizure as a type of seizure;

wherein at least the steps of image segregation, posture identification, body part identification, and seizure detection are implementable by a processor.

26. The computer-readable medium of claim 25 , further comprising instructions for:

identifying a behavior of the animal as one of a set of predetermined behaviors.

27. The computer-readable medium of claim 25 , wherein the seizure-salient features include a Tail Raise feature.

28. The computer-readable medium of claim 25 , wherein the seizure-salient features include a Lordotic Posture feature.

29. The computer-readable medium of claim 25 , wherein the seizure-salient features include a Forelimb Clonus feature.

30. The computer-readable medium of claim 25 , wherein the seizure-salient features include an Overall Body Motion feature.

31. The computer-readable medium of claim 25 , wherein the seizure-salient features include a Bounding Box feature.

32. The computer-readable medium of claim 25 , wherein the seizure-salient features include a Rearing feature.

33. The computer-readable medium of claim 25 , wherein the seizure-salient features include a Chewing Motion feature.

34. The method of claim 13 further comprising:

displaying the video image including the image of the animal;

displaying an extracted foreground image of the animal;

displaying a table comprising a frame number and the posture of the animal identified for that frame;

displaying a table comprising a frame number and the behavior of the animal identified for that frame; and

displaying a plot of the detected seizure behavior.

35. The method of claim 34 , further comprising displaying a user settings graphical user interface.

36. The method of claim 34 , wherein the extracted foreground image of the animal includes labels for body parts of the animal.