Improving Automated Dental Diagnostics Utilizing YOLO9- Based Framework

Abstract

The dental diagnostics sector has advanced significantly due to the formation of artificial intelligence (AI) in recent years. YOLO9's key breakthroughs, such as improved feature extraction, deeper convolution layers, and increased anchor box processes, are thoroughly described. These enhancements enable the diagnosis of it is not visible and more delicate dental defects, which were difficult to detect in prior editions. This paper harnesses the capabilities of the YOLO9-based framework to provide a novel way to improve automated dentistry diagnostics. Through the use of intraoral and dental X-ray images, the proposed system in this paper seeks to increase the precision and efficacy of the detection and diagnosis of dental disorders, such as caries, periodontal disease, and other abnormalities of the mouth. The proposed system uses the YOLO9 architecture, which is known for its outstanding detection speed and precision, to scan X-ray dental pictures, offering reliable diagnostic results in real-time. In addition, the paper investigates how YOLO9 might be used with current treatment approaches and post-processing algorithms to improve diagnostic accuracy. The experimental results reveal that the YOLO9-based framework is effective in a variety of diagnostic circumstances, with considerable improvements in sensitivity and specificity when compared to traditional approaches and previous versions of YOLO. Where the proposed system provides on average 22% improvement in accuracy. The system's robustness is demonstrated by rigorous testing on an assortment of datasets, including panoramic radiographs and X-rays.