Effective Cervical Cancer Detection using Deep Learning Techniques

Uncontrolled cell growth, known as cancer or carcinoma, appears in various forms, among them cervical cancer (CC) is most caused breast cancer all over the world. It claims nearly 700 lives daily. However, early detection in its precancerous stages significantly improves treatment outcomes. This study, Enhanced Cervical Cancer Detection Using YOLOv9, focuses on utilizing the YOLOv9 object detection model to form a highly accurate and a system which is efficient for identifying cervical cancer in medical images. To train the data an annotated dataset containing medical images that highlight different cervical abnormalities, including precancerous lesions was used. By leveraging advanced deep learning techniques, this approach strengthens diagnostic accuracy in medical imaging. The system is evaluated using evaluation metrics such as recall, F1-Score,precision,mAP. Additionally, test datasets are examined alongside model predictions to assess detection accuracy, with special attention given to false positives and false negatives. Identifying these errors helps in refining the model for improved reliability. By analyzing results and their implications, this research showcases YOLOv9’s capability in aiding cervical cancer diagnosis, contributing to more effective early detection and improved patient care.