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 crucial for the success of experiments. Traditional methods are time-consuming and rely on the subjective judgment of professionals, which limits the efficiency and accuracy of experiments. This study proposes an EfficientNet model to automate the recognition of the estrous cycle of female rats using deep learning techniques. The model optimizes performance through systematic scaling of the network depth, width, and image resolution. A large dataset of physiological data from female rats was used for training and validation. The improved EfficientNet model effectively recognized different stages of the estrous cycle. The model demonstrated high-precision feature capture and significantly improved recognition accuracy compared to conventional methods. The proposed technique enhances experimental efficiency and reduces human error in recognizing the estrous cycle. This study highlights the potential of deep learning to optimize data processing and achieve high-precision recognition in biomedical research. Future work should focus on further validation with larger datasets and integration into experimental workflows.