Artificial intelligence-assisted detection of soft tissue calcifications and ossifications in CBCT.

OBJECTIVES

This study aimed to integrate soft tissue calcifications and ossifications (STCO) detected on cone beam computed tomography (CBCT) into an artificial intelligence (AI) system and assess its diagnostic accuracy in both single-class and multi-class classification.

STUDY

DESIGN

CBCT images from 287 patients were retrospectively reviewed. STCOs were identified in axial, coronal, and sagittal planes, with segmentation performed in the axial plane. The AI model was trained to detect arterial calcifications, phleboliths, tonsilloliths, styloid ligament ossification, osteoma cutis, antroliths, laryngeal cartilage calcifications, sialoliths, lymph node calcifications, and rhinoliths as well as a single combined class. Data were split into training (80%), testing (10%), and validation (10%) sets, and performance was evaluated using sensitivity, precision, and F1-score.

RESULTS

In the single-class model, sensitivity, precision, and F1-score were 0.98, 0.91, and 0.94, respectively. In the multi-class model, these values were 0.88, 0.80, and 0.84.

CONCLUSION

The AI system achieved high accuracy in detecting STCOs, with superior results in single-class classification. AI-assisted CBCT evaluation may improve diagnostic efficiency, facilitate multidisciplinary collaboration, and support clinical decision-making.