Clinical features and imaging examination assessment of cervical lymph nodes for thyroid carcinoma

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.

Malignant risk of thyroid nodules with isolated macrocalcifications - A study based on surgery results

OBJECTIVE

To determine the malignancy risk of thyroid nodules with Isolated Macrocalcifications (IMC) based on surgical results and evaluate the postoperative risk of malignant nodules with IMC.

METHODS

A total of 46 thyroid nodules with IMC were enrolled from 3680 consecutive patients who underwent thyroidectomy between August 2018 and September 2023. The malignancy risk of IMC nodules, postoperative risk of malignant nodules, and whether the ultrasonic features of IMC (smooth, lobulated, or focal disruption of the anterior margin) were associated with malignancy were investigated. The nodules were further divided into three groups (group A, maximum diameter < 10 mm; group B, maximum diameter of 10‒14 mm and group C, maximum diameter ≥ 15 mm). Differences in malignancy and Lymph Node Metastasis (LNM) risks were also evaluated among the three groups.

RESULTS

The malignancy risk of the IMC nodules was 30.43% (14/46). Four patients developed LNM. Eight nodules were staged as T1aN0M0 and low-risk, whereas six nodules were staged as T1bN1aM0 and intermediate-risk. Focal disruption of the anterior margin of IMC was significantly associated with malignancy. Malignant and LNM risk showed no differences among nodules with different sizes.

CONCLUSIONS

IMC nodules with different sizes had a lower intermediate risk of malignancy and exhibited the same aggressive behavior. The cutoff value of these nodules for further Fine Needle Aspiration (FNA) warranted further investigation. Interruption of IMC was more often seen in malignant nodules, and more attention should be paid to these nodules.

Tumor Size as a Predictive Indicator for Lymph Node Metastasis in Papillary Thyroid Carcinoma: An Inverted L-Shaped Curve Analysis Based on the SEER Database

BACKGROUND

Papillary thyroid carcinoma (PTC) frequently metastasises to lymph nodes, with lymph node metastasis (LNM) occurring with high frequency in small, early-stage tumors. The present study examines the inverse l-shaped relationship between tumor size and the likelihood of LNM in patients diagnosed with PTC.

METHODS

We performed a detailed retrospective cohort analysis of 48,021 cases of papillary thyroid cancer using data from the Epidemiology, and End Results (SEER) database from 1992 to 2019. Our study used various analytical methods, including logistic regression, spline curve fitting, and variable interaction assessment, to clarify the association between tumor size and LNM rates. We rigorously controlled for potential confounders such as patient age, sex, ethnicity, tumor size, extrathyroidal extension (ETE), histopathological characteristics and distant metastases. In addition, we thoroughly investigated and quantitatively assessed the relationship between adjusted tumor size measurements and the likelihood of LNM development.

RESULTS

The median tumor size among the 48,021 patients diagnosed with PTC was 1.3 cm. Among these patients, 12,365 (25.75%) had LNM, with a median tumor size of 1.9 cm in this group. A comparative analysis shows a significant difference in tumor sizes between PTC patients who were LNM-positive and those who were LNM-negative. The relationship between tumor size and the likelihood of LNM exhibits a distinct nonlinear pattern. Specifically, below a diameter threshold of 1.978 cm, the probability of LNM significantly increases with larger tumor sizes (odds ratio [OR] = 2.363, 95% confidence Interval [CI]: 2.214-2.523). Once this threshold is surpassed, the effect of tumor size on LNM incidence levels off (OR = 1.031, 95% CI: 1.003-1.061).

CONCLUSION

The results of this study confirm that tumor size significantly determines the likelihood of LNM in patients with PTC. We found an inverse l-shaped relationship between tumor size and the probability of LNM. As the tumor size increased below 1.978 cm, the likelihood of LNM increased, but not with tumor size above that threshold. These findings provide new insights into the complex relationship between tumor size and LNM in PTC.

Development and validation of a machine learning model to predict the risk of lymph node metastasis in early-stage supraglottic laryngeal cancer

Background

Cervical lymph node metastasis (LNM) is a significant factor that leads to a poor prognosis in laryngeal cancer. Early-stage supraglottic laryngeal cancer (SGLC) is prone to LNM. However, research on risk factors for predicting cervical LNM in early-stage SGLC is limited. This study seeks to create and validate a predictive model through the application of machine learning (ML) algorithms.

Methods

The training set and internal validation set data were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Data from 78 early-stage SGLC patients were collected from Fujian Provincial Hospital for independent external validation. We identified four variables associated with cervical LNM and developed six ML models based on these variables to predict LNM in early-stage SGLC patients.

Results

In the two cohorts, 167 (47.44%) and 26 (33.33%) patients experienced LNM, respectively. Age, T stage, grade, and tumor size were identified as independent predictors of LNM. All six ML models performed well, and in both internal and independent external validations, the eXtreme Gradient Boosting (XGB) model outperformed the other models, with AUC values of 0.87 and 0.80, respectively. The decision curve analysis demonstrated that the ML models have excellent clinical applicability.

Conclusions

Our study indicates that combining ML algorithms with clinical data can effectively predict LNM in patients diagnosed with early-stage SGLC. This is the first study to apply ML models in predicting LNM in early-stage SGLC patients.

A Nomogram Based on Features of Ultrasonography and Contrast-Enhanced CT to Predict Vessels Encapsulating Tumor Clusters Pattern of Hepatocellular Carcinoma

OBJECTIVE

This study aimed to establish a clinical prediction model for vessels encapsulating tumor clusters (VETC) based on preoperative ultrasonography (US) and contrast-enhanced computed tomography (CECT) imaging in patients with hepatocellular carcinoma (HCC).

METHODS

Data were retrospectively collected from 215 patients who underwent hepatectomy for solitary HCC lesions. They were divided into training and validation cohorts at a ratio of 6:4. Preoperative imaging features were extracted (seven from US and nine from CECT imaging) to explore their relationship with VETC. A VETC prediction model was constructed and graphically depicted as a nomogram. Its performance was evaluated via the receiver operating characteristic (ROC) curve, the calibration curve, and decision curve analysis (DCA).

RESULTS

The VETC incidence for all the lesions was 37.7%. The final variables included in the nomogram were "peritumoral enhancement in CECT", "alpha-fetoprotein level > 200 ng/Ml," "halo in US," "capsule enhancement in CECT," and "posterior acoustic enhancement in US." The area under the curve (AUC) values for the training and validation cohorts were 0.824 and 0.725, respectively. The Hosmer-Lemeshow fit test showed no statistical difference (p = 0.369 and p = 0.067 for the training and validation cohorts, respectively). DCA demonstrated that our nomogram provided clinical benefits to a wide range of patients. According to the nomogram score, the VETC-positive and -negative groups demonstrated significant differences in both the training (p < 0.001) and validation (p = 0.001) cohorts.

CONCLUSION

Our prediction model based on US and CECT imaging features can accurately predict VETC in HCC.

Prognosis analysis and nomogram for predicting lateral lymph node metastasis in Medullary Thyroid Microcarcinoma

BACKGROUND

Currently, the incidence rate of Medullary Thyroid Microcarcinoma (micro-MTC) has an increasing trend, but the incidence of LNM and prognosis were still ambiguous. We analyzed the status of neck LNM of micro-MTC patients and created a prognostic nomogram to predict the probability of lateral lymph node metastasis (LLNM) for clinical practice.

METHODS

This is a retrospective study included patients with micro-MTC from SEER database for the period from 2004 to 2017 and patients from our medical center for the period from 2011 to 2019. A nomogram was constructed and the accuracy and clinical practicability were separately tested by Harrell's C-indexes, calibration plots, Receiver operating characteristic curve (ROC) and decision curve analyses (DCA).

RESULTS

A total of 413 patients with micro-MTC from SEER database and 64 patients with micro-MTC from our department enrolled in the study. There were 16.0% and 9.4% cases in SEER database and 39.1% and 25.0% cases in our department appeared LNM and LLNM, respectively. Besides, a nomogram was constructed to assess the incidence of LLNM with good C-index, which was 0.850 in training cohort and 0.856 in validation cohort. The results of the area under the curve (AUC) were 0.830 in training cohort, 0.801 in validation cohort and 0.832 in external testing cohort, respectively.

CONCLUSION

A relatively high rate of LLNM than expected was found, which should be emphasized. The prediction model could facilitate clinicians to assess the probability of LLNM and make a personalized treatment strategy.

The Association of Pretreatment Systemic Immune Inflammatory Response Index (SII) and Neutrophil-to-Lymphocyte Ratio (NLR) with Lymph Node Metastasis in Patients with Papillary Thyroid Carcinoma

Objective

Immunoinflammatory response can participate in the development of cancer. To investigate the relationship between pretreatment systemic immune inflammatory response index (SII), systemic inflammatory response index (SIRI), neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), lymphocyte-to-monocyte ratio (LMR) and lymph node metastasis in patients with papillary thyroid carcinoma (PTC).

Methods

A retrospective analysis was performed on 547 PTC patients treated in Meizhou People's Hospital from January 2018 to December 2021. Clinicopathological data were collected, including gender, age, Hashimoto's thyroiditis, maximum tumor diameter, extra-membrane infiltration, disease stage, BRAF V600E mutation, pretreatment inflammatory index levels, and lymph node metastasis. The optimal cutoff values of SII, SIRI, NLR, PLR and LMR were calculated by receiver operating characteristic (ROC) curve, and the relationship between inflammatory indexes and other clinicopathological features and lymph node metastasis was analyzed.

Results

There were 303 (55.4%) PTC patients with lymph node metastasis. The levels of SII, SIRI, NLR, and PLR in patients with lymph node metastasis were significantly higher than those in patients without lymph node metastasis, while the levels of LMR were significantly lower than those in patients without lymph node metastasis (all p<0.05). When lymph node metastasis was taken as the endpoint, the critical value of SII was 625.375, the SIRI cutoff value was 0.705, the NLR cutoff value was 1.915 (all area under the ROC curve >0.6). The results of regression logistic analysis showed that age <55 years old (OR: 1.626, 95% CI: 1.009-2.623, p=0.046), maximum tumor diameter >1cm (OR: 2.681, 95% CI: 1.819-3.952, p<0.001), BRAF V600E mutation (OR: 2.709, 95% CI: 1.542-4.759, p=0.001), SII positive (≥625.375/<625.375, OR: 2.663, 95% CI: 1.560-4.546, p<0.001), and NLR positive (≥1.915/<1.915, OR: 1.808, 95% CI: 1.118-2.923, p=0.016) were independent risk factors for lymph node metastasis of PTC.

Conclusion

Age <55 years old, maximum tumor diameter >1cm, BRAF V600E mutation, SII positive, and NLR positive were independent risk factors for lymph node metastasis in PTC.