Detecting Polycystic Ovary Syndrome (PCOS) is crucial due to its significant impact on both physical and mental well-being. This hormonal disorder necessitates effective prediction methods, with various techniques utilizing diverse data types such as clinical parameters or ultrasound images. This particular study focuses on the utilization of ultrasound images for PCOS prediction, leveraging the capabilities of deep learning Convolutional Neural Network (CNN) models, renowned for their high accuracy and low error rates in image classification tasks. Data augmentation involves creating variations of the original images by applying random transformations such as rotation, flipping, and scaling. This strategy helps the model generalize better to different scenarios and increases its ability to detect patterns in various forms. The Inception v3 model, a state-ofthe- art architecture known for its efficiency in image recognition tasks, was chosen for this study. The model demonstrated an impressive overall accuracy of approximately 99%, showcasing its effectiveness in distinguishing PCOS-related patterns within ultrasound images. Inception v3 incorporates advanced features such as multiple convolutional layers and global average pooling, allowing it to capture intricate patterns and relationships within the data.