Automatic analysis system and method of rodent tail suspension experiment based on deep learning

Abstract

The invention discloses an automatic analysis system and method of a rodent tail suspension experiment based on deep learning. The automatic analysis system and method are used for solving the problems that in the tail suspension experiment, due to a series of influences of the inertia effect, mouse physical strength and other influences on an experiment result, the false negative or false positive probability of related drug effect evaluation is high, the experiment cost is high, and the experiment time is long. The automatic analysis system comprises a tail suspension experiment module, a video analysis module and a data output module. According to the automatic analysis system and method, full-automatic tracking and fine behavior index extraction are realized through a deep learning technology without depending on other experimental hardware equipment, so that the experimental cost is greatly reduced, 14 body key points of rodents are analyzed, and full-automatic accurate tracking is realized; and compared with a traditional method for judging immobility and struggling time through changes of a trunk area and the gravity center of a mouse, cost is low, and time is short.

Description

technical field [0001] The invention relates to the technical field of rodent tail suspension experiments, in particular to an automatic analysis system and method for rodent tail suspension experiments based on deep learning. Background technique [0002] The tail suspension test is a widely used method for screening potential antidepressant drugs. Treatment with various antidepressant drugs, regardless of their primary mechanism of action, reduces immobility time in mice. However, for research on drug development and drug efficacy evaluation that relies on tail suspension experiments, at present, it mainly relies on traditional computer vision technology, which can only obtain rough macro behavioral indicators, such as: the change of mouse outline area per unit time , to judge the mouse struggling and immobile state (desperate state). In the tail suspension experiment, due to a series of influences on the experimental results due to inertial effects and other effects suc...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve a series of influences on the experimental results due to the inertial effect and other influences such as the physical strength of the mouse in the tail suspension experiment, resulting in a high probability of false negative or false positive in the evaluation of the relevant drug efficacy, and the cost of the experiment is large. Due to the problem of long experiment time, an automated analysis system and method based on deep learning rodent tail suspension experiment is proposed

Images