Everton Flaiban

This study aimed to assess the diagnostic performance of the Brazilian-developed artificial intelligence system DIO Inteligência® for automatic detection and classification of primary and permanent teeth in panoramic radiographs of patients in mixed dentition, using expert radiologist consensus as the reference standard. In this retrospective diagnostic accuracy study, 110 digital panoramic radiographs from patients aged 6-12 years were analyzed. The AI system automatically identified and classified individual teeth according to FDI notation. A total of 4622 teeth with definitive reference classification were included. The system's output was compared with a gold standard established by consensus of two experienced dentomaxillofacial radiologists. Diagnostic performance metrics, including accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were calculated. Overall, the AI system demonstrated high diagnostic performance, achieving an accuracy of 91%, sensitivity of 92%, and specificity of 72%. The PPV was 99%, whereas the NPV was 29%. Performance remained consistently high across most permanent tooth groups, with accuracy values around 96% and PPVs close to 100%. Third molars showed slightly lower metrics compared with other permanent groups. Primary teeth also demonstrated favorable classification performance, with high sensitivity and PPV. These findings may suggest that the DIO Inteligência® system shows robust performance in detecting and classifying primary and permanent teeth in mixed dentition panoramic radiographs, supporting its potential role as a reliable adjunct tool in pediatric dental imaging interpretation.

Radiomics has recently begun as a transformative approach in medical imaging, shifting radiology from qualitative description to quantitative analysis. By extracting high-throughput features from CT (Computed Tomography), MRI (Magnetic Resonance Imaging), PET/CT (Positron Emission Tomography/Computed Tomography), and CBCT (Cone Beam Computed Tomography), radiomics enables the characterization of tissue heterogeneity and the development of imaging biomarkers with diagnostic, prognostic, and predictive values. This narrative review explores the historical evolution of radiomics and its methodological foundations, including acquisition, segmentation, feature extraction and modeling, and platforms supporting these workflows. Clinical applications are highlighted in oncology, cardiology, neurology, and musculoskeletal and dentomaxillofacial imaging. Despite being promising, radiomics faces challenges related to standardization, reproducibility, PACS/RIS (Picture Archiving and Communication System/Radiology Information System) integration and interpretability. Professional initiatives, such as the Image Biomarker Standardization Initiative (IBSI) and guidelines from radiological societies, are addressing these barriers by promoting harmonization and clinical translation. The ultimate vision is a radiomics-augmented radiology report in which validated biomarkers and predictive signatures complement conventional findings, thus enhancing objectivity, reproducibility, and advancing precision medicine.