Caracterización del perfil citológico de la mucosa vaginal durante el ciclo estral en perras con ayuda de inteligencia artificial.

Abstract

Characterization of the cytological profile of the vaginal mucosa during the estrous cycle in bitches with the aid of Artificial Intelligence" presents a study whose main objective is to improve the accuracy in the identification of the different phases of the estrous cycle in bitches by using artificial intelligence (AI). This approach aims to overcome the limitations of traditional vaginal cytology methods that, although effective, rely heavily on the clinician's experience, which can lead to errors in diagnosis. The study focuses on the development and application of an AI-based model, specifically using the YOLOv8 technique, to segment and classify vaginal mucosal cells in microscopic images. The model was trained and evaluated using an annotated dataset, and its results were compared with traditional methods. The results show that the model performs well in terms of accuracy and efficiency, suggesting that AI can be a useful tool in veterinary practice for vaginal cytology. This paper concludes that the integration of AI in veterinary medicine not only has the potential to improve diagnostic accuracy, but could also facilitate the automation of clinical processes, reducing practitioner workload and improving outcomes for canine patients.