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

• US 7,643,655 B2
• Filed: 01/11/2006
• Issued: 01/05/2010
• Est. Priority Date: 11/24/2000
• Status: Expired due to Fees

• Current Assignee: Clever Sys Incorporated
• Original Assignee: Clever Sys Incorporated
• Inventors: Bai, Xuesheng, Liang, Yiqing, Kobla, Vikrant
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US11/329,573
• Publication Number:
  US 20060110049A1
• Time in Patent Office: 1,455 Days
• Field of Search: 382/100, 382/103, 382106-110, 382/117, 382/118, 382/128, 382/129, 382/151, 382/156, 382/173, 382/174, 382/190, 382/203, 382/214, 382/243, 382/254, 382/256, 382/302, 382/305, 382/286, 424/185.1, 424/158.1, 435/325, 119/421, 514/282, 348/143, 702/141
• US Class Current: 382/110
• CPC Class Codes: A01K 1/031 Cages for laboratory animals; Cages for measuring metabolism of animals
• CPC Class Codes: A01K 29/005 Monitoring or measuring activity, e.g. detecting heat or mating
• CPC Class Codes: A61B 2503/40 Animals
• CPC Class Codes: A61B 2503/42 for laboratory research
• CPC Class Codes: A61B 5/1113 Local tracking of patients, e.g. in a hospital or private home
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/1128 using image analysis A61B5/1127 takes precedence
• CPC Class Codes: A61B 5/4094 Diagnosing or monitoring seizure diseases, e.g. epilepsy
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A system and method for analyzing video images including images of an animal to detect and classify seizure behavior of the animal. Seizure-salient features are detected from identified postures and identified movements of body parts of the animal. The seizure-salient features are used to detect and classify the occurrences of seizures.

Claims

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.

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.

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.