A novel method for estrous cycle staging using supervised object detection.

The estrous cycle regulates reproductive events and hormone changes in female mammals and is analogous to the menstrual cycle in humans. Monitoring this cycle is necessary as it serves as a biomarker for overall health and is crucial for interpreting study results. The estrous cycle comprises four stages influenced by fluctuating levels of hormones, mainly estradiol and progesterone. Tracking the cycle traditionally relies on vaginal cytology, which categorizes stages based on three epithelial cell concentrations. However, this method has limitations, including time-consuming training and variability among researchers. This study assesses the feasibility and reliability of two previous image classification models as well as introducing an alternative method of machine learning to address the challenges posed by manual vaginal cytology and image classification. An object detection-based machine learning model, Object Detection Estrous Staging (ODES), was employed to identify cell types throughout the estrous cycle in mice. A dataset of 730 vaginal cytology images with four different stains was used, with 335 images for training, 45 for validation, and 350 for testing. A novel, accurate set of rules for classification was derived by analyzing training images. ODES achieved an average accuracy of 80% in classifying cycle stages, comparable to human accuracy (66%) and previous image classification models (41-79%). The efficiency of ODES, processing 100 test images in just 2.67 minutes, makes it a valuable tool for large-scale neuropsychiatric studies involving female rodents and also encourages the integration of this variable into neurological and psychiatric research. These results demonstrate that ODES offers a fast, reliable, and accessible method for estrous cycle monitoring, potentially improving how researchers approach sex-based variables in neuropsychiatric studies.