AUTHOR=Pu Xiaodi , Liu Longyi , Zhou Yonglai , Xu Zihan 

TITLE=Determination of the rat estrous cycle vased on EfficientNet

JOURNAL=Frontiers in Veterinary Science

VOLUME=Volume 11 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/veterinary-science/articles/10.3389/fvets.2024.1434991

DOI=10.3389/fvets.2024.1434991

ISSN=2297-1769

ABSTRACT=In the field of biomedical research, rats are widely used as experimental animals due to their short gestation period and strong reproductive ability. Accurate monitoring of the estrous cycle is the key to the success of experiments, but traditional methods are time-consuming and rely on the subjective judgment of professionals, which limits the efficiency and accuracy of experiments. In this paper, we propose an EfficientNet model to automate the recognition of the estrous cycle of female rats through deep learning techniques, aiming to improve the accuracy and efficiency of the detection process.The EfficientNet model optimizes the model performance through the systematic scaling of the network depth, width, and image resolution, and realizes the high-precision capture of the features of the estrous cycle of rats. This study demonstrates how the improved EfficientNet model can effectively recognize different stages of the estrous cycle by training and validating a large amount of physiological data from female rats. Compared with conventional methods, this technique significantly improves experimental efficiency, reduces human error, achieves high-precision recognition of the estrous cycle, and optimizes the data processing flow with the potential of deep learning.