Automated Image Quality Evaluation of Periapical Radiographs Using Deep Learning

The manual assessment of periapical radiographs for image quality is inherently subjective, labor-intensive, and time-consuming. This study aimed to develop an automated solution by evaluating the efficacy of a deep learning algorithm, ResNet50, in detecting common image quality defects. A dataset of 3594 periapical radiographs was retrospectively collected and partitioned into training and testing sets in a 9:1 ratio. Each image was annotated for ten categories of tooth position and six types of quality defects, which served as the ground truth for training the model. Performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, F1 score, and loss value. The model demonstrated excellent performance, achieving AUC values of 0.997 for tooth position, and 0.996 (poor vertical angle), 1.000 (poor horizontal angle), 1.000 (incomplete crown coverage), 0.994 (incomplete apical coverage), 0.999 (cone cut), and 0.924 (scratch) for the various quality defects. These results indicate that the ResNet50 algorithm provides an effective and highly accurate approach for the automated detection of image quality issues in periapical radiographs. This AI tool holds significant potential for clinical translation; its integration into digital dental imaging systems could offer real-time, objective feedback, thereby improving diagnostic accuracy, reducing retake rates to minimize patient radiation exposure, and enhancing overall workflow efficiency in dental clinics.