Development and validation of an intra-tumoral and peri-tumoral radiomics model based on dynamic contrast-enhanced ultrasound for predicting lymph node metastasis in type 2 diabetic patients with thyroid cancer

1

The study developed radiomics models using dynamic contrast-enhanced ultrasound to predict lymph node metastasis in diabetic thyroid cancer patients.
2

A total of 203 diabetic thyroid cancer patients were included, divided into training and validation cohorts for model assessment.
3

Key radiomics features were extracted from CEUS parameters, and the optimal peri-tumoral region was determined to enhance model performance.
4

The combined radiomics model achieved AUCs of 0.930, 0.907, and 0.865 across training and validation cohorts, indicating strong predictive capability.
5

Calibration curves showed good agreement between predicted and actual outcomes, highlighting the model's potential clinical utility.

Frontiers In Endocrinology

by Siyao Li, Yunzhi Zhou, Wanyan Li, Ansheng Liu, Yanjun Hu, Chaoxue Zhang, Yayang Duan
June 23, 2026

1