Vol. 12, Issue 1, Part A (2026)

Wax tooth carving is a fundamental component of preclinical dental education, aimed at developing students’ understanding of tooth morphology and manual dexterity. Conventionally, the evaluation of wax carvings relies on visual inspection by faculty members, making the process subjective and examiner dependent. Such assessment methods often lead to inter-examiner variability, limited scalability, and delayed feedback.

To address these challenges, the present study introduces Carve. Me, a structured digital framework designed to standardize the evaluation of wax tooth carvings. The system enables dental students to upload images of their carvings in five standardized views—labial, lingual, mesial, distal, and occlusal—after selecting the appropriate tooth number or type. Rule-based validation logic ensures completeness of submissions and penalizes incorrect tooth-type uploads. Provisional scores are assigned to each view, promoting fairness and consistency in assessment.

The framework is compatible with the Windows platform and can function offline, making it suitable for institutional use. Although the current version does not incorporate trained artificial intelligence models, the system provides a scalable foundation for future integration of deep learning-based automated evaluation. Carve. Me demonstrates potential to reduce evaluator bias, improve consistency, and encourage student self-assessment in preclinical dental training.