Radiomics Nomogram for Identifying Sub-1 cm Benign and Malignant Thyroid Lesions

Area of Science:

• Radiology
• Oncology
• Medical Imaging Analysis

Background:

• Distinguishing benign from malignant thyroid lesions, especially those under 1 cm, is challenging.
• Accurate preoperative differentiation is crucial for appropriate patient management and treatment planning.

Purpose of the Study:

• To develop and validate a radiomics nomogram for the identification of sub-1 cm benign and malignant thyroid lesions.
• To assess the diagnostic performance and clinical usefulness of the developed nomogram.

Main Methods:

• Retrospective collection of 171 patients with sub-1 cm thyroid lesions.
• Extraction of radiomics features from CT images; selection using LASSO logistic regression.
• Construction of a radiomics nomogram combining radiomics signature and clinical factors (age, TI-RADS).

Main Results:

• A radiomics signature with 13 features demonstrated high prediction efficiency.
• The nomogram showed good calibration and discrimination in both training (AUC: 0.853) and validation (AUC: 0.851) sets.
• Decision curve analysis confirmed the clinical usefulness of the nomogram.

Conclusions:

• The radiomics nomogram is an effective noninvasive tool for preoperative prediction of sub-1 cm thyroid lesions.
• It integrates radiomics features and clinical factors to improve diagnostic accuracy.
• This approach offers a promising method for differentiating benign and malignant thyroid nodules.