Prediction of lymph node metastasis in patients with papillary thyroid cancer based on radiomics analysis and intraoperative frozen section analysis: A retrospective study
View abstract on PubMed
Summary
This summary is machine-generated.A new nomogram combining radiomics, frozen section analysis, and clinical data shows promise for predicting lymph node metastasis in papillary thyroid cancer patients.
Area Of Science
- Oncology
- Radiology
- Medical Imaging
Background
- Papillary thyroid cancer (PTC) poses diagnostic challenges regarding lymph node (LN) metastasis.
- Accurate prediction of LN metastasis is crucial for effective patient management and treatment planning.
Purpose Of The Study
- To evaluate the diagnostic efficiency of a clinical model, a radiomics model, and a combined nomogram for predicting LN metastasis in PTC.
- To compare the predictive performance of these models using ultrasound-derived radiomics features, frozen section analysis, and clinical characteristics.
Main Methods
- A total of 208 PTC patients were divided into training (n=146) and validation (n=62) groups.
- Radiomics features were extracted from ultrasound images using Least Absolute Shrinkage and Selection Operator (LASSO) regression.
- Clinical, radiomics, and combined nomogram models were developed using logistic regression machine learning.
Main Results
- Multivariate analysis identified age, size group, Adler grade, ACR score, and psammoma body group as independent predictors of LN metastasis.
- The nomogram demonstrated superior performance compared to the radiomics model and showed a trend towards better performance than the clinical model.
- The nomogram exhibited improved sensitivity, potentially reducing false negatives in predicting lymph node metastasis.
Conclusions
- The developed nomogram is a promising tool for predicting lymph node metastasis in patients with papillary thyroid cancer.
- The integration of radiomics, frozen section analysis, and clinical data enhances diagnostic accuracy for LN metastasis in PTC.

