PCOS Detection using deep learning algorithm

Polycystic Ovary Syndrome (PCOS) is a common hormonal disorder among women of reproductive age, leading to infertility and metabolic complications. This project proposes an automated approach for PCOS detection using deep learning, based on the EfficientNet architecture. A transfer learning strategy was used to fine-tune a pre-trained EfficientNet model on a dataset of ovarian ultrasound images. The system automatically identifies distinctive features such as follicle count, ovarian volume, and morphology. The model achieved high diagnostic accuracy while remaining lightweight and efficient, making it suitable for real-time clinical use. This AI-based diagnostic tool supports early detection of PCOS, reduces diagnostic delays, and enhances healthcare accessibility for women.