Related Experiment Video
Updated: Jun 18, 2025
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
A Prediction Model for Assessing the Efficacy of Thermal Ablation in Treating Benign Thyroid Nodules ≥ 2 cm: A
Meng-Yu Lu1, Ying Zhou2, Xiao-Wan Bo1
1Department of Medical Ultrasound, Center of Minimally Invasive Treatment for Tumor, Shanghai Tenth People's Hospital, Ultrasound Research and Education Institute, Clinical Research Center for Interventional Medicine, School of Medicine, Tongji University, Shanghai, China; Shanghai Engineering Research Center of Ultrasound Diagnosis and Treatment, Shanghai, China.
Objectives:
To develop and validate a prediction model utilizing clinical and ultrasound (US) data for preoperative assessment of efficacy following US-guided thermal ablation (TA) in patients with benign thyroid nodules (BTNs) ≥ 2 cm.
Materials And Methods:
We retrospectively assessed 962 patients with 1011 BTNs who underwent TA at four tertiary centers between May 2018 and July 2022. Ablation efficacy was categorized into therapeutic success (volume reduction rate [VRR] > 50%) and non-therapeutic success (VRR ≤ 50%). We identified independent factors influencing the ablation efficacy of BTNs ≥ 2 cm in the training set using multivariate logistic regression. On this basis, a prediction model was established. The performance of model was further evaluated by discrimination (area under the curve [AUC]) in the validation set.
Results:
Of the 1011 nodules included, 952 (94.2%) achieved therapeutic success at the 12-month follow-up after TA. Independent factors influencing VRR > 50% included sex, nodular composition, calcification, volume, and largest diameter (all p < 0.05). The prediction equation was established as follows: p = 1/1 + Exp∑[8.113 -2.720 × (if predominantly solid) -2.790 × (if solid) -1.275 × (if 10 mL < volume ≤ 30mL) -1.743 × (if volume > 30 mL) -1.268 × (if with calcification) -2.859 × (if largest diameter > 3 cm) +1.143 × (if female)]. This model showed great discrimination, with AUC of 0.908 (95% confidence interval [CI]: 0.868-0.947) and 0.850 (95% CI: 0.748-0.952) in the training and validation sets, respectively.
Conclusions:
A clinical prediction model was successfully developed to preoperatively predict the therapeutic success of BTNs larger than 2 cm in size following US-guided TA. This model aids physicians in evaluating treatment efficacy and devising personalized prognostic plans.
