Dental cavities are one of the most common oral health problems, and early identification can support timely dental care. This study presents a deep learning based dental cavity detection system using the Ultralytics YOLO11n (YOLOv11 Nano) object detection model. A dental image dataset containing annotated cavity and normal samples was prepared and divided into training, validation, and test sets. The model was trained in Google Colab with image preprocessing and augmentation to improve its ability to detect cavity regions. Model performance was evaluated using precision, recall, mAP50, and mAP50-95. The trained model was then used to predict cavity regions in unseen dental images. The proposed approach provides an automated and efficient method for preliminary cavity detection and can assist dental professionals as a decision-support tool. Future work can focus on larger and more diverse datasets, improved annotation quality, and realworld clinical validation. Keywords— dental cavity detection; deep learning; YOLO11n; object detection; dental images; computer vision.

Akshaya.N, Pauravi.B, Dharsani.T S, Dharaneesh.A, Vidhyabharathi.T,"Deep Learning Based Dental Cavity Detection" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(5): Page(758-761) September - October 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.