Reviewed by Lexie CornerApr 1 2025
Ateneo Laboratory for Intelligent Visual Environments (ALIVE) and global researchers created a deep learning model that could transform dentistry. This model can identify tooth and sinus structures in dental X-rays with an impressive accuracy rate of 98.2 %.
Sample dental X-rays or dental panoramic radiographs (DPRs) as seen by the YOLO 11n deep learning model. Image Credit: Pei-Yi Wu et al., 2025
Notoriously Difficult To Diagnose
Using an advanced object detection algorithm, the system was trained to enhance the rapid and accurate detection of odontogenic sinusitis. This condition, often confused with general sinusitis, can lead to severe complications such as the spread of infection to the face, eyes, and brain if left untreated.
Odontogenic sinusitis, caused by infections or complications related to the upper teeth, is difficult to diagnose. Its symptoms, including nasal congestion, foul-smelling nasal discharge, and occasional tooth pain, resemble those of common sinusitis.
Additionally, only about one-third of patients experience noticeable dental pain, which can result in misdiagnosis by general practitioners. Traditionally, an accurate diagnosis requires collaboration between dentists and otolaryngologists, leading to potential delays in treatment.
You Only Look Once
By training deep learning models using dental panoramic radiograph (DPR) images, the researchers developed a method to identify key anatomical relationships, such as the proximity of tooth roots to sinuses, with high accuracy. The study used the YOLO 11n deep learning model, achieving an accuracy rate of 98.2 %, which outperforms traditional detection methods.
You Only Look Once (YOLO) is a widely used object detection algorithm known for its speed and precision. The YOLO 11n model, an optimized version for medical imaging, can identify teeth and sinus structures with high accuracy in a single image analysis.
Unlike traditional diagnostic methods that require multiple steps and expert input, YOLO 11n quickly locates the affected areas in real time, making it a highly effective tool for dental professionals.
AI’s Growing Role in Medicine
This AI-powered method offers practical benefits in addition to its accuracy. It reduces patient exposure to radiation by minimizing reliance on CT scans, which are currently the standard for diagnosing odontogenic sinusitis.
Furthermore, it provides an affordable screening tool, particularly beneficial in areas with limited resources where advanced imaging technology may not be available. By identifying potential cases early, the system facilitates timely intervention, preventing complications and reducing the burden on healthcare professionals.
This advancement highlights the growing role of AI in medical diagnostics, addressing areas where human expertise alone may fall short. With further validation of its effectiveness, this technology could become a standard tool in dental and ENT clinics, ensuring more patients receive timely and accurate diagnoses.
Dr. Patricia Angela R. Abu, head of ALIVE, and her collaborators from Chang Gung Memorial Hospital, National Cheng Kung University, Chung Yuan Christian University, and Ming Chi University of Technology in Taiwan conducted the research.
Journal Reference:
Wu, Y, P., et al. (2025) Department of Information Systems & Computer Science Faculty Publications. Bioengineering. doi.org/10.3390/bioengineering12020134