Nomogram Based on Shear-Wave Elastography Radiomics Can Improve Preoperative Cervical Lymph Node Staging for...

Area of Science:

• Medical Imaging
• Oncology
• Radiology

Background:

• Accurate preoperative prediction of cervical lymph node (LN) metastasis is crucial for surgical decision-making in papillary thyroid carcinoma (PTC).
• Ultrasound-based radiomics offers a non-invasive approach to assess LN status.

Purpose of the Study:

• To develop and validate an ultrasound radiomics nomogram for the preoperative assessment of LN metastasis in PTC.
• To evaluate the predictive performance of the nomogram using shear-wave elastography (SWE) and B-mode ultrasound (BMUS) features.

Main Methods:

• Radiomics features were extracted from SWE and BMUS images of 147 PTC patients (training set) and 90 patients (external validation set).
• Feature selection algorithms (mRMR and LASSO) were used to construct SWE and BMUS radiomics scores (Rad-scores).
• A nomogram was developed using multivariate logistic regression incorporating Rad-scores, multifocality, and ultrasound-reported LN status.

Main Results:

• Both SWE and BMUS Rad-scores were significantly higher in patients with cervical LN metastasis.
• The radiomics nomogram demonstrated good discrimination and calibration in both training (AUC 0.851) and validation (AUC 0.832) sets.
• The nomogram showed favorable predictive efficacy, even in the clinically relevant LN-negative subgroup (AUC 0.812).

Conclusions:

• The presented radiomics nomogram, particularly based on the SWE radiomics signature, shows a favorable predictive value for LN staging in PTC.
• This tool can assist in preoperative assessment and surgical planning for PTC patients, potentially improving patient outcomes.