Prophylactic Central Neck Dissection for cN1b Papillary Thyroid Carcinoma: A Systematic Review and Meta-Analysis

Prediction of lymph node metastasis in papillary thyroid carcinoma using non-contrast CT-based radiomics and deep learning with thyroid lobe segmentation: A dual-center study

Objectives

This study aimed to develop a predictive model for lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) patients by deep learning radiomic (DLRad) and clinical features.

Methods

This study included 271 thyroid lobes from 228 PTC patients who underwent preoperative neck non-contrast CT at Center 1 (May 2021-April 2024). LNM status was confirmed via postoperative pathology, with each thyroid lobe labeled accordingly. The cohort was divided into training (n = 189) and validation (n = 82) cohorts, with additional temporal (n = 59 lobes, Center 1, May-August 2024) and external (n = 66 lobes, Center 2) test cohorts. Thyroid lobes were manually segmented from the isthmus midline, ensuring interobserver consistency (ICC ≥ 0.8). Deep learning and radiomics features were selected using LASSO algorithms to compute DLRad scores. Logistic regression identified independent predictors, forming DLRad, clinical, and combined models. Model performance was evaluated using AUC, calibration, decision curves, and the DeLong test, compared against radiologists' assessments.

Results

Independent predictors of LNM included age, gender, multiple nodules, tumor size group, and DLRad. The combined model demonstrated superior diagnostic performance with AUCs of 0.830 (training), 0.799 (validation), 0.819 (temporal test), and 0.756 (external test), outperforming the DLRad model (AUCs: 0.786, 0.730, 0.753, 0.642), clinical model (AUCs: 0.723, 0.745, 0.671, 0.660), and radiologist evaluations (AUCs: 0.529, 0.606, 0.620, 0.503). It also achieved the lowest Brier scores (0.167, 0.184, 0.175, 0.201) and the highest net benefit in decision-curve analysis at threshold probabilities > 20 %.

Conclusions

The combined model integrating DLRad and clinical features exhibits good performance in predicting LNM in PTC patients.

Predictive risk-scoring model for lateral lymph node metastasis in papillary thyroid carcinoma

This study aims to evaluate candidate risk factors for lateral lymph node metastasis (LLNM) and develop a predictive model to identify high-risk groups among patients with papillary thyroid carcinoma (PTC). Additionally, we identified risk factors for recurrence to inform postoperative therapeutic decisions and follow-up for physicians and patients. A total of 4107 patients (4884 lesions) who underwent lymph node dissection at our hospital from 2005 to 2014 were evaluated. LLNM risk was stratified, and a risk-scoring model was developed based on identified independent risk factors for LLNM. Cox's proportional hazards regression model was used to investigate the risk factors for recurrence. Lateral Lymph Node (LLN) metastasis was observed in 10.49% (431/4107) of patients. Multivariate analysis identified the following independent risk predictors for LLN metastasis: Age ≤ 35 years (P = 0.002), tumor size > 1.0 cm (P = 0.000), lobe dissemination (+) (P = 0.000), and CLNM (+) (P = 0.000). A 12-point risk-scoring model was constructed to predict stratified LLNM in PTC patients, with an area under the receiver operating characteristic curve (AUROC) of 0.794 (95% CI: 0.774-0.814) (P < 0.01). The Cox regression model indicated that tumor size > 1.0 cm, lobe dissemination (+), multifocality, Central Lymph Node Metastasis (CLNM), and LLNM were significant risk factors associated with poor outcomes. Based on the risk scoring model, additional investigations and comprehensive considerations are recommended for patients with a total score greater than 5, and prophylactic cervical lymph node dissection is performed if necessary. Additionally, more aggressive treatment and more frequent follow-ups should be considered for patients with tumor size > 1.0 cm, lobe dissemination (+), multifocality, CLNM, and LLNM.

Meta-analysis of prediction models for predicting lymph node metastasis in thyroid cancer

BACKGROUND

The purpose of this systematic review and meta-analysis is to assess the efficacy of various machine learning (ML) techniques in predicting preoperative lymph node metastasis (LNM) in patients diagnosed with papillary thyroid carcinoma (PTC). Although prior studies have investigated the potential of ML in this context, the current evidence is not sufficiently strong. Hence, we undertook a thorough analysis to ascertain the predictive accuracy of different ML models and their practical relevance in predicting preoperative LNM in PTC patients.

MATERIALS AND METHODS

In our search, we thoroughly examined PubMed, Cochrane Library, Embase, and Web of Science, encompassing their complete database history until December 3rd, 2022. To evaluate the potential bias in the machine learning models documented in the included studies, we employed the Prediction Model Risk of Bias Assessment Tool (PROBAST).

RESULTS

A total of 107 studies, involving 136,245 patients, were included. Among them, 21,231 patients showed central LNM (CLNM) and 4,637 had lateral LNM (LLNM). The meta-analysis results revealed that the c-index for predicting LNM, CLNM, and LLNM were 0.762 (95% CI: 0.747-0.777), 0.762 (95% CI: 0.747-0.777), and 0.803 (95% CI: 0.773-0.834) in the training set, and 0.773 (95% CI: 0.754-0.791), 0.762 (95% CI: 0.747-0.777), and 0.829 (95% CI: 0.779-0.879) in the validation set, respectively. A total of 134 machine learning-based prediction models were included, covering 10 different types. Logistic Regression (LR) was the most commonly used model, accounting for 81.34% (109/134) of the included models.

CONCLUSIONS

Machine learning methods have shown a certain level of accuracy in predicting preoperative LNM in PTC patients, indicating their potential as a predictive tool. Their use in the clinical management of PTC holds great promise. Among the various ML models investigated, the performance of logistic regression-based nomograms was deemed satisfactory.

Can Unilateral Therapeutic Central Lymph Node Dissection Be Performed in Papillary Thyroid Cancer with Lateral Neck Metastasis?

Objectives

Unilateral or bilateral prophylactic central neck dissection (CND) in papillary thyroid cancer (PTC) is still controversial. We aimed to evaluate the risk factors for contralateral paratracheal lymph node metastasis and whether CND might be performed unilaterally.

Methods

Prospectively collected data of patients who underwent bilateral CND and lateral neck dissection (LND) with thyroidectomy due to PTC with lateral metastases, between January 2012 and November 2019, were evaluated retrospectively. The patients were divided into two groups according to the presence (Group 1) and absence (Group 2) of metastasis in the contralateral paratracheal region.A total of 42 patients (46 ±15.7 years) were operated. In the contralateral paratracheal region, Group 1 (35.7%) had metastases, while Group 2 (64.3%) had no metastases. In groups 1 and 2, metastasis rates were 100% vs 77.8% (p=0.073), 46.7% vs 18.5% (p=0.078), and 80% vs 40.7% (p=0.023) for the ipsilateralparatracheal, prelaryngeal and pretracheal lymph nodes, respectively.The number of metastatic lymph nodes in the central region was significantly higher in Group 1 compared to Group 2 as; 10.7±8.4 vs. 2.6±2.4 (p=0.001) in bilateral central region material; 8.3±7.4 vs. 2.9±2.7 (p=0.001) in lateral metastasis with ipsilateral unilateral central region; 3.8±3.4 vs. 1.9±1.9 (p=0.023) in ipsilateralparatracheal area; and 3.7±4.6 vs. 0.6±0.9 (p=0.001) in pretracheal region, respectively. However, no significant difference was found regarding the prelaryngeal region material (0.9±1.8 vs. 0.2±0.4 (p=0.71)).

Results

>2 metastatic central lymph nodes in unilateral CND material (AUC: 0.814, p<0.001, J=0.563) can estimate contralateral paratracheal metastasis with 93% sensitivity, 63% specificity, while >2 pretracheal metastatic lymph nodes (AUC: 0.795, p<0.001, J: 0.563) can estimate contralateral paratracheal metastasis with 60% sensitivity and 96.3% specificity.

Conclusion

In patients with lateral metastases, the rate of ipsilateralparatracheal metastasis is 85%, while the rate of contralateral paratracheal metastasis is 35.7%. The number of ipsilateral central region or pretracheal lymph node metastases may be helpful in predicting contralateral paratracheal lymph node metastases. Notably, unilateral CND may be performed in the presence of ≤ 2 metastases in the ipsilateral central region.

Radiomics features from whole thyroid gland tissue for prediction of cervical lymph node metastasis in the patients with papillary thyroid carcinoma

OBJECTIVE

We aimed to develop a clinical-radiomics nomogram that could predict the cervical lymph node metastasis (CLNM) of patients with papillary thyroid carcinoma (PTC) using clinical characteristics as well as radiomics features of dual energy computed tomography (DECT).

METHOD

Patients from our hospital with suspected PTC who underwent DECT for preoperative assessment between January 2021 and February 2022 were retrospectively recruited. Clinical characteristics were obtained from the medical record system. Clinical characteristics and rad-scores were examined by univariate and multivariate logistic regression. All features were incorporated into the LASSO regression model, with penalty parameter tuning performed using tenfold cross-validation, to screen risk factors for CLNM. An easily accessible radiomics nomogram was constructed. Receiver Operating Characteristic (ROC) curve together with Area Under the Curve (AUC) analysis was conducted to evaluate the discrimination performance of the model. Calibration curves were employed to assess the calibration performance of the clinical-radiomics nomogram, followed by goodness-of-fit testing. Decision curve analysis (DCA) was performed to determine the clinical utility of the established models by estimating net benefits at varying threshold probabilities for training and testing groups.

RESULTS

A total of 461 patients were retrospectively recruited. The rates of CLNM were 49.3% (70 /142) in the training cohort and 53.3% (32/60) in the testing cohort. Out of the 960 extracted radiomics features, 192 were significantly different in positive and negative groups (p < 0.05). On the basis of the training cohort, 12 stable features with nonzero coefficients were selected using LASSO regression. LASSO regression identified 7 risk factors for CLNM, including male gender, maximum tumor size > 10 mm, multifocality, CT-reported central CLN status, US-reported central CLN status, rad-score, and TGAb. A nomogram was developed using these factors to predict the risk of CLNM. The AUC values in each cohort were 0.850 and 0.797, respectively. The calibration curve together with the Hosmer-Lemeshow test for the nomogram indicated good agreement between predicted and pathological CLN statuses in the training and testing cohorts. Results of DCA proved that the nomogram offers a superior net benefit for predicting CLNM compared to the "treat all or none" strategy across the majority of risk thresholds.

CONCLUSION

A nomogram comprising the clinical characteristics as well as radiomics features of DECT and US was constructed for the prediction of CLNM for patients with PTC, which in determining whether lateral compartment neck dissection is warranted.

A Nod to the Nodes: An Overview of the Role of Central Neck Dissection in the Management of Papillary Thyroid Carcinoma

Lymph node metastasis in thyroid cancer is common and associated with an increased risk of locoregional recurrence (LRR). Although therapeutic central neck dissection is well established, prophylactic central node dissection (pCND) for microscopic occult nodal involvement is controversial and recommendations are based on low-level evidence. The potential benefits of pCND such as reducing LRR and re-operation, refining staging, and improving surveillance are enthusiastically debated and the decision to perform pCND must be weighed up against the increased risks of complications.

Integrated gene profiling of fine-needle aspiration sample improves lymph node metastasis risk stratification for thyroid cancer

BACKGROUND

Lymph node metastasis risk stratification is crucial for the surgical decision-making of thyroid cancer. This study investigated whether the integrated gene profiling (combining expression, SNV, fusion) of Fine-Needle Aspiration (FNA) samples can improve the prediction of lymph node metastasis in patients with papillary thyroid cancer.

METHODS

In this retrospective cohort study, patients with papillary thyroid cancer who went through thyroidectomy and central lymph node dissection were included. Multi-omics data of FNA samples were assessed by an integrated array. To predict lymph node metastasis, we built models using gene expressions or mutations (SNV and fusion) only and an Integrated Risk Stratification (IRS) model combining genetic and clinical information. Blinded histopathology served as the reference standard. ROC curve and decision curve analysis was applied to evaluate the predictive models.

RESULTS

One hundred and thirty two patients with pathologically confirmed papillary thyroid cancer were included between 2016-2017. The IRS model demonstrated greater performance [AUC = 0.87 (0.80-0.94)] than either expression classifier [AUC = 0.67 (0.61-0.74)], mutation classifier [AUC = 0.61 (0.55-0.67)] or TIRADS score [AUC = 0.68 (0.62-0.74)] with statistical significance (p < 0.001), and the IRS model had similar predictive performance in large nodule [>1 cm, AUC = 0.88 (0.79-0.97)] and small nodule [≤1 cm, AUC = 0.84 (0.74-0.93)] subgroups. The genetic risk factor showed independent predictive value (OR = 10.3, 95% CI:1.1-105.3) of lymph node metastasis in addition to the preoperative clinical information, including TIRADS grade, age, and nodule size.

CONCLUSION

The integrated gene profiling of FNA samples and the IRS model developed by the machine-learning method significantly improve the risk stratification of thyroid cancer, thus helping make wise decisions and reducing unnecessary extensive surgeries.

Preoperative Cervical Lymph Node Metastasis Prediction in Papillary Thyroid Carcinoma: A Noninvasive Clinical Multimodal Radiomics (CMR) Nomogram Analysis

This study aimed to evaluate the feasibility of applying a clinical multimodal radiomics nomogram based on ultrasonography (US) and multiparametric magnetic resonance imaging (MRI) for the prediction of cervical lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) preoperatively. We performed retrospective evaluations of 133 patients with pathologically confirmed PTC, who were assigned to the training cohort and validation cohort (7 : 3), and extracted radiomics features from the preoperative US, T2-weighted (T2WI),diffusion-weighted (DWI), and contrast-enhanced T1-weighted (CE-T1WI) images. Optimal subsets were selected using minimum redundancy, maximum relevance, and recursive feature elimination in the support vector machine (SVM). For LNM prediction, the radiomics model was constructed by SVM, and Multi-Omics Graph cOnvolutional NETworks (MOGONET) was used for the effective classification of multiradiomics data. Multivariable logistic regression incorporating multiradiomics signatures and clinical risk factors was used to generate a nomogram, whose performance and clinical utility were assessed. Results showed that the nine most predictive features were separately selected from US, T2WI, DWI, and CE-T1WI images, and 18 features were selected in the combined model. The combined radiomics model showed better performance than models based on US, T2WI, DWI, and CE-T1WI. In a comparison of the combined radiomics and MOGONET model, receiver operating curve analysis showed that the area under the curve (AUC) value (95% CI) was 0.84 (0.76-0.93) and 0.84 (0.71-0.96) for the MOGONET model in the training and validation cohorts, respectively. The corresponding values (95% CI) for the combined radiomics model were 0.82 (0.74-0.90) and 0.77 (0.61-0.94), respectively. The MOGONET model had better performance and better prediction specificity compared with the combined radiomics model. The nomogram including the MOGONET signature showed a better predictive value (AUC: 0.81 vs. 0.88) in the training and validation (AUC: 0.74vs. 0.87) cohorts, as compared with the clinical model. Calibration curves showed good agreement in both cohorts. The applicability of the clinical multimodal radiomics (CMR) nomogram in clinical settings was validated by decision curve analysis. In patients with PTC, the CMR nomogram could improve the prediction of cervical LNM preoperatively and may be helpful in clinical decision-making.

Clinical-Radiomics Nomogram Based on Contrast-Enhanced Ultrasound for Preoperative Prediction of Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma

This study aimed to establish a new clinical-radiomics nomogram based on ultrasound (US) for cervical lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC). We collected 211 patients with PTC between June 2018 and April 2020, then we randomly divided these patients into the training set (n = 148) and the validation set (n = 63). 837 radiomics features were extracted from B-mode ultrasound (BMUS) images and contrast-enhanced ultrasound (CEUS) images. The maximum relevance minimum redundancy (mRMR) algorithm, least absolute shrinkage and selection operator (LASSO) algorithm, and backward stepwise logistic regression (LR) were applied to select key features and establish a radiomics score (Radscore), including BMUS Radscore and CEUS Radscore. The clinical model and clinical-radiomics model were established using the univariate analysis and multivariate backward stepwise LR. The clinical-radiomics model was finally presented as a clinical-radiomics nomogram, the performance of which was evaluated by the receiver operating characteristic curves, Hosmer-Lemeshow test, calibration curves, and decision curve analysis (DCA). The results show that the clinical-radiomics nomogram was constructed by four predictors, including gender, age, US-reported LNM, and CEUS Radscore. The clinical-radiomics nomogram performed well in both the training set (AUC = 0.820) and the validation set (AUC = 0.814). The Hosmer-Lemeshow test and the calibration curves demonstrated good calibration. The DCA showed that the clinical-radiomics nomogram had satisfactory clinical utility. The clinical-radiomics nomogram constructed by CEUS Radscore and key clinical features can be used as an effective tool for individualized prediction of cervical LNM in PTC.

Intraoperative quantitative assessment of parathyroid blood flow during total thyroidectomy using indocyanine green fluorescence imaging - surgical strategies for preserving the function of parathyroid glands

Objective

We investigated the factors affecting postoperative parathyroid gland (PTG) function and devised an objective index to predict the postoperative PTG function during total thyroidectomy.

Method

This was a retrospective clinical review of 21 consecutive patients who were diagnosed with papillary thyroid carcinoma and underwent total thyroidectomy. The maximum intensity ratio (MIR) was determined as the maximum fluorescence intensity after ICG injection divided by the intensity before ICG injection.

Results

Postoperative hypoparathyroidism is significantly associated with simultaneous central neck dissection (CND) and lateral neck dissection (LND) (p = .032). The Spearman correlation test showed a moderate correlation between the MIR and iPTH levels (p = .0047). The optimal MIR cutoff value for predicting postoperative hypoparathyroidism was 2.14 with area under the curve = 0.904 (sensitivity: 0.769 and specificity: 1.00).

Conclusion

CND + LND was significantly associated with postoperative hypoparathyroidism. MIR was found useful in predicting the postoperative PTG function.

Level of Evidence 3b