Dentin Normalization Boosts CBCT Radiomics for Granuloma vs Cyst Differentiation

Dentin-normalized CBCT radiomics with XGBoost achieved an AUC of 0.78 for differentiating periapical granulomas from radicular cysts, significantly higher than raw radiomics (AUC 0.68, P<.05).

• Study included 140 patients with histopathologically confirmed lesions (100 granulomas, 40 cysts).
• Dentin normalization improved AUC in first-order/texture feature models, suggesting benefit for gray-value-dependent features.
• External validation across different CBCT systems is required before clinical use.

Automated summary

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