DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels

James P. Bohnslav

doi:10.7554/eLife.63377

2021-09-02

James P. Bohnslav

Nivanthika K. Wimalasena

Christopher D. Harvey *

DOI：10.7554/eLife.63377

原文链接

原文求助

摘要

En 中文

Videos of animal behavior are used to quantify researcher-defined behaviors of interest to study neural function, gene mutations, and pharmacological therapies. Behaviors of interest are often scored manually, which is time-consuming, limited to few behaviors, and variable across researchers. We created DeepEthogram: software that uses supervised machine learning to convert raw video pixels into an ethogram, the behaviors of interest present in each video frame. DeepEthogram is designed to be general-purpose and applicable across species, behaviors, and video-recording hardware. It uses convolutional neural networks to compute motion, extract features from motion and images, and classify features into behaviors. Behaviors are classified with above 90% accuracy on single frames in videos of mice and flies, matching expert-level human performance. DeepEthogram accurately predicts rare behaviors, requires little training data, and generalizes across subjects. A graphical interface allows beginning-to-end analysis without end-user programming. DeepEthogram's rapid, automatic, and reproducible labeling of researcher-defined behaviors of interest may accelerate and enhance supervised behavior analysis. analysis. Code is available at: https:// github.com/jbohnslav/deepethogram.

Keyword:

TACTILE

期刊

eLife

IF:

论文数:

1.8W

被引数:

机构

Harvard University

学者数:

26.5W

论文数: 22.0W

被引数: 28.7W

引用论文

IF0

PREAI

Real-time analysis of the behaviour of groups of mice via a depth-sensing camera and machine learning 通过深度感应相机和机器学习对小鼠组的行为进行实时分析

NATURE BIOMEDICAL ENGINEERING

IF26.6

2019-05-20

OAAI

de Chaumont, Fabrice; Ey, Elodie; Torquet, Nicolas; Lagache, Thibault; Dallongeville, Stephane; Imbert, Albane; Legou, Thierry; Le Sourd, Anne-Marie; Faure, Philippe; Bourgeron, Thomas; Olivo-Marin, Jean-Christophe

DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning DeepPoseKit，一个使用深度学习快速和强大的动物姿态估计的软件工具包

ELIFE

IF0

2019-10-01

337

OAAI

Graving, Jacob M.; Chae, Daniel; Naik, Hemal; Li, Liang; Koger, Benjamin; Costelloe, Blair R.; Couzin, Iain D.

STAT3 Silencing in Dendritic Cells by siRNA Polyplexes Encapsulated in PLGA Nanoparticles for the Modulation of Anticancer Immune Response

Molecular Pharmaceutics

IF0

2010-09-14

PREAI

Aws Alshamsan; Azita Haddadi; Samar Hamdy; John Samuel; Ayman O. S. El-Kadi; Hasan Uludağ; Afsaneh Lavasanifar

Mapping Sub-Second Structure in Mouse Behavior 鼠标行为中的亚秒级结构映射

NEURON

IF15

2015-12-01

492

OAAI

Wiltschko, Alexander B.; Johnson, Matthew J.; Iurilli, Giuliano; Peterson, Ralph E.; Katon, Jesse M.; Pashkovski, Stan L.; Abraira, Victoria E.; Adams, Ryan P.; Datta, Sandeep Robert

Deep learning-based behavioral analysis reaches human accuracy and is capable of outperforming commercial solutions 基于深度学习的行为分析达到了人类的准确性，并且能够超越商业解决方案

NEUROPSYCHOPHARMACOLOGY

IF7.1

2020-07-25

106

OAAI

Sturman, Oliver; von Ziegler, Lukas; Schlaeppi, Christa; Akyol, Furkan; Privitera, Mattia; Slominski, Daria; Grimm, Christina; Thieren, Laetitia; Zerbi, Valerio; Grewe, Benjamin; Bohacek, Johannes

Scoping the market orientation literature from 2009 to 2013: a review of the concept and the discussions found across a range of academic disciplines

Journal of Strategic Marketing

IF0

2014-10-21

PREAI

Marie Ashwin; Alan Hirst

Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？

Journal of Physical Activity and Health

IF0

2015-07-01

PREAI

Jeff R. Crane; Patti J. Naylor; Ryan Cook; Viviene A. Temple