EM2AI achieves higher accuracy than ThakaaMed for tooth numbering on panoramic radiographs, with gains in third molar detection

In 595 panoramic radiographs, EM2AI achieved 99.48% accuracy vs ThakaaMed’s 96.81% for tooth detection and numbering (excluding third molars). EM2AI was significantly more sensitive in upper anterior, lower anterior, and lower posterior regions, with no specificity difference. E…

• Excluding third molars, overall accuracy was 99.48% for EM2AI vs 96.81% for ThakaaMed.
• EM2AI demonstrated significantly higher sensitivity in upper anterior, lower anterior, and lower posterior regions; no significant specificity differences were observed.
• EM2AI was superior in detecting third molars, which were analyzed separately due to variable developmental stages.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.