CT Habitat Imaging Predicts Occult Central Lymph Node Metastasis in Papillary Thyroid Cancer

In a retrospective two-center study, a CT habitat-based radiomics model combined with clinical factors predicted occult central node metastases in papillary thyroid cancer, achieving an AUC of 0.878 on external validation.

• A combined model integrating intratumoral habitat, peritumoral radiomics from arterial and venous phase CT, and clinical factors (age, TSH, PLT) achieved AUC 0.932 in training and 0.878 in external validation.
• The peritumoral radiomics model alone (venous phase) had AUC 0.884 training, 0.850 validation.

Automated summary

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