Device and method of automatic classification of animal behaviors using vocalizations

Patent metadata

Field	Value
Publication number	US-10806129-B2
Application number	US-201715667467-A
Country	US
Kind code	B2
Filing date	Aug 2, 2017
Priority date	Aug 2, 2017
Publication date	Oct 20, 2020
Grant date	Oct 20, 2020

Abstract

The field of this invention is classifying animal behaviors. In particular the fields of this invention include using animals in vivariums, such as rodents, particularly mice. Animal behaviors are classified according to behaviors consistent with healthy or unhealthy organs or locations within organs, such as the brain. Injected neoplastic cells may be used to create an unhealthy organ or location within an organ. Classifications also include responses to different therapies. The behavior of the animals is observed using fully automatic, continuous monitoring using per-cage ultrasonic and video sensors, where behavior recording is free of human, manual actions. Observed behavior is consistent with healthy or unhealthy behaviors specific to the injection site. Both positive and negative baseline behaviors are collected, typically using the same system or method. Classification is responsive to differences between treated and untreated animals, comparing to both the positive and negative baselines, using multi-dimensional analysis.

First claim

We claim:

1. A device for automatically classifying animal behaviors comprising:
cells of a first neoplasm type;
a study animal type;
a vivarium comprising a set of study animals, of the study animal type, in a plurality of cages; wherein each animal in the set of study animals comprises a first organ and wherein each animal in the set of study animals receives by injection a first quantity of cells of the first neoplasm type in the first organ;
a non-transitory first memory comprising a first set of negative baseline behaviors; wherein the first set of negative baseline behaviors comprises behaviors consistent with animals of the study animal type receiving no injection of cells of the first neoplasm type and no therapeutic treatment;
a non-transitory second memory comprising a second set of positive baseline behaviors; wherein the second set of positive baseline behaviors comprises behaviors consistent with unhealthy functioning of the first organ of animals of the study animal type;
a first treatment subset of the set of study animals; wherein each animal in the first treatment subset receives a first therapeutic treatment;
at least one ultrasonic audio sensor proximal to each cage of the plurality of cages;
at least one video sensor proximal to each cage of the plurality of cages;
wherein the at least one ultrasonic sensor and the at least one video sensor detect and automatically communicate first communicated behaviors comprising one or more audio and video behaviors, from the at least one cage in the plurality of cages, respectively
a first processor adapted to identify a first selected set of behaviors derived from the first communicated behaviors, wherein each behavior in the first selected set of behaviors is consistent with one or both of at least one behavior in the first set of negative baseline behaviors, or at least one behavior in the second set of positive baseline behaviors;
a second processor adapted to classify the first selected set of behaviors responsive to at least both of: (a) a least difference between the first selected set of behaviors and the first set of negative baseline behaviors, and (b) a largest difference between the first selected set of behaviors and the second set of positive baseline behaviors;
wherein the first and second processors are configurable to operate as a same processor;
wherein each of the automatically classified animal behaviors by the device is quantified;
wherein the at least a subset of the automatically classified animal behaviors comprising classified ultrasonic vocalization is then used as accepted dispositive animal behavior.

2. The device of claim 1 , wherein:
the classified ultrasonic vocalizations comprise two or more vocalizations from the Markush group of accent; upward; downward; flat; chevron; U-shaped; and complex.

3. The device of claim 2 , wherein:
the first therapeutic treatment is treatment with a first drug and the second therapeutic treatment is treatment with a second, different drug.

4. The device of claim 1 , wherein:
the classified ultrasonic vocalizations comprise two or more vocalizations from the Markush group of: shape of pitch v. time; intensity; number of times a vocalization occurs within a predetermined time window; change in pitch measured as Hz/time; and simultaneous vocalizations below 25 KHz.

5. The device of claim 1 , wherein:
either the first set of negative baseline behaviors or the second set of positive baseline behaviors, or both, comprise both at least one video behavior and at least one audio behavior.

6. The device of claim 1 , wherein:
the classifying by the second processor comprises:
at least one substitution of a video behavior with an audio behavior or a substitution of an audio behavior with a video behavior, or both, prior to computation of the least difference and prior to the computation of the largest difference.

7. The device of claim 1 , wherein:
the first set of negative baseline behaviors is generated using the same vivarium environment and the same animal type as the set of study animals.

8. The device of claim 1 , wherein:
the classified ultrasonic vocalizations comprise identification of vocalization in one of two predetermined frequency bands, wherein a range of the two predetermined frequency bands are responsive to the study animal type.

9. The device of claim 1 , further comprising:
a second treatment subset of the set of study animals; wherein each animal in the second treatment subset receives a second therapeutic treatment;
wherein at least one sensor proximal to each cage comprising at least one of the animals in the second treatment subset adapted to detect and communicate second communicated behaviors comprising one or more audio and video behaviors from the at least one cage in the plurality of cages, respectively;
a third processor adapted to identify a second selected set of behaviors from the second communicated behaviors, wherein each behavior in the second selected set is consistent with one or both of at least one behavior in the first set of negative baseline, or at least one behavior in the second set of positive baseline behaviors;
a fourth processor adapted to classify the second selected set of behaviors; wherein the classifying is responsive to at least all of: (a) a least difference between the second selected set of behaviors and the first set of negative baseline behaviors, (b) a largest difference between the second selected set of behaviors and the second set of positive baseline behaviors, and (c) a difference between second selected set of behaviors and the first selected set of behaviors;
wherein the third and fourth processor are configurable to operate as a same processor;
wherein the third processor is configurable to operate as the same processor;
wherein the fourth processor is configurable to operate as the same processor;
wherein each of the automatically classified animal behaviors by the device is quantified.

10. The device of claim 1 , wherein:
the organ is a brain.

11. The device of claim 1 , wherein:
the vivarium cages are free of electronic penetrations and are the home cages of their respective animals.

12. The device of claim 1 , wherein:
the at least one video or ultrasonic sensor is mechanically independent of the proximal cage such that at least one sensor or the proximal cage are configurable to be replaced without mechanically moving the proximal cage or the at least one video or ultrasonic sensor, respectively.

13. The device of claim 1 , wherein:
the device is free of manually observed behavior of the study animals, and free of manually communicated behavior of the study animals, and free of manual classifying of sets of behaviors.

14. The device of claim 1 , wherein:
the detection and communication of animal behaviors is continuous.

15. The device of claim 1 , wherein:
the study animals, after receiving the injection the first quantity of cells, remain in their respective home cages during a study.

16. The device of claim 1 , further comprising:
a stereotaxic device, wherein the stereotaxic device is used to determine a point of injection for the injection of the first quantity of cells.

17. The device of claim 1 , wherein:
the first neoplasm type is free of a known biomarker.

18. The device of claim 1 , further comprising:
a wireless animal scale inside of each cage comprising at least two of the animals in the first treatment subset;
an automated animal ID sensor proximal to each cage comprising at least two of the anima

Assignees

• Vium Inc
• Vium Inc A

Inventors

• Betts-Lacroix Jonathan
• Schaevitz Laura

Classifications

• A01K1/031

  Cages for laboratory animals; Cages for measuring metabolism of animals · CPC title

• A61B5/165

  Evaluating the state of mind, e.g. depression, anxiety · CPC title

• A61B2503/40

  Animals · CPC title

• A01K1/00

  Housing animals; Equipment therefor · CPC title

• A01K29/005 Primary

  Monitoring or measuring activity · CPC title