PXseg, a novel approach for tooth segmentation, numbering and abnormal morphology detection in panoramic X-ray (PX), was designed and promoted through optimizing annotation and applying pre-training. Derived from multicenter, ctPXs generated from cone beam computed tomography (CBCT) with accurate 3D labels were utilized for pre-training, while conventional PXs (cPXs) with 2D labels were input for training. Visual and statistical analyses were conducted using the internal dataset to assess segmentation and numbering performances of PXseg and compared with the model without ctPX pre-training, while the accuracy of PXseg detecting abnormal teeth was evaluated using the external dataset consisting of cPXs with complex dental diseases. Besides, a diagnostic testing was performed to contrast diagnostic efficiency with and without PXseg’s assistance. The DSC and F1-score of PXseg in tooth segmentation reached 0.882 and 0.902, which increased by 4.6% and 4.0% compared to the model without pre-training. For tooth numbering, the F1-score of PXseg reached 0.943 and increased by 2.2%. Based on the promotion in segmentation, the accuracy of abnormal tooth morphology detection exceeded 0.957 and was 4.3% higher. A website was constructed to assist in PX interpretation, and the diagnostic efficiency was greatly enhanced with the assistance of PXseg. The application of accurate labels in ctPX increased the pre-training weight of PXseg and improved the training effect, achieving promotions in tooth segmentation, numbering and abnormal morphology detection. Rapid and accurate results provided by PXseg streamlined the workflow of PX diagnosis, possessing significant clinical application prospect.

Periodontal disease is one of the most common diseases in stomatology. With the continuous development of artificial intelligence (AI), its integration with periodontology is rapidly evolving. However, a comprehensive bibliometric analysis mapping this interdisciplinary field is currently lacking. We conducted a bibliometric analysis by retrieving publications related to AI and periodontal disease from the Web of Science Core Collection (WoSCC) for the period January 2007 to July 2025. Data processing and visualization were performed using R (Bibliometrix), VOSviewer, and CiteSpace. A total of 496 relevant articles (437 research papers; 59 reviews) were included. Annual publication output has shown sustained growth, particularly since 2021. China contributed the most publications (153 articles), followed by the United States. Among institutions, Pusan National University, South Korea (32 articles), and Saveetha Institute of Medical and Technical Science, India (31 articles) were the most productive. BMC Oral Health published the highest number of articles (n = 23). The co-authorship network involved 2,604 authors, with Pradeep Kumar Yadalam being the most prolific (15 articles). Co-citation analysis identified Orhan Kaan, Abu Patricia Angela R., and Falk Schwendicke as the most cited authors. Keyword analysis revealed “periodontitis,” “machine learning,” and “artificial intelligence” as core research foci, while burst detection indicated “progression” and “expression” as emerging thematic directions. This study provides a systematic overview of the research landscape, highlighting evolving trends, key contributors, and knowledge structure in AI applications for periodontal disease. The findings offer valuable insights to help dentists and researchers understand current applications, identify frontiers, and potentially guide the future clinical translation of AI technologies in periodontology.

To provide the public and non-specialist readers with clear insight, we re-evaluate a published study claiming that artificial intelligence (AI) software p