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 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.
ABSTRACT
Premature ovarian insufficiency (POI) induced by chemotherapy is an intractable disorder with a considerable incidence that commonly results in insufficient fertility and concomitant complications in female patients. Due to limitations in the current progress in POI diagnosis and treatment, there is an urgent need to develop novel remedies to improve ovarian function and protect fertility. The ameliorative effect of human umbilical cord mesenchymal stem cells (hUCMSCs) and exosomes derived from them in POI treatment could be a new hope for patients. Herein, we identified exosomes from hUCMSCs (hUCMSC-Exos). Then, systematic infusion of hUCMSC-Exos was accomplished via tail intravenous injection to investigate the feasibility of the treatment of rats with chemotherapy-induced POI by intraperitoneal injection of cyclophosphamide (CTX) and busulfan (BUS). Ovarian functions in the indicated group were evaluated, including oestrous cycle, serum sex hormone levels, follicle counts, ovarian pathological changes, proliferation and apoptosis of granulosa cells (GCs), and reproductive ability testing. Furthermore, the potential influence of hUCMSC-Exos on ovarian tissues was illuminated by conducting RNA-seq and multifaceted bioinformatics analyses. POI rats with hUCMSC-Exos transplantation exhibited a decrease in follicle-stimulating hormone (FSH) and apoptosis of GCs but an increase in oestradiol (E2), anti-Müllerian hormone (AMH), and the number of ovarian follicles and foetuses in the uterus. And the immunomodulation- and cellular vitality-associated gene sets in rats had also undergone moderate changes. Our data indicated the feasibility of hUCMSC-Exos in improving ovarian function and protecting fertility in chemotherapy-induced POI rats. HUCMSC-Exos can improve the local microenvironment of ovarian tissue in POI rats by participating in immune regulation, cellular viability, inflammation regulation, fibrosis and metabolism, and other related signal pathways.