Sonographic Imaging of Cervical Lymph Nodes in Patients with Thyroid Cancer

Incorporation of a machine learning pathological diagnosis algorithm into the thyroid ultrasound imaging data improves the diagnosis risk of malignant thyroid nodules

Objective

This study aimed at establishing a new model to predict malignant thyroid nodules using machine learning algorithms.

Methods

A retrospective study was performed on 274 patients with thyroid nodules who underwent fine-needle aspiration (FNA) cytology or surgery from October 2018 to 2020 in Xianyang Central Hospital. The least absolute shrinkage and selection operator (lasso) regression analysis and logistic analysis were applied to screen and identified variables. Six machine learning algorithms, including Decision Tree (DT), Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Naive Bayes Classifier (NBC), Random Forest (RF), and Logistic Regression (LR), were employed and compared in constructing the predictive model, coupled with preoperative clinical characteristics and ultrasound features. Internal validation was performed by using 10-fold cross-validation. The performance of the model was measured by the area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, F1 score, Shapley additive explanations (SHAP) plot, feature importance, and correlation of features. The best cutoff value for risk stratification was identified by probability density function (PDF) and clinical utility curve (CUC).

Results

The malignant rate of thyroid nodules in the study cohort was 53.2%. The predictive models are constructed by age, margin, shape, echogenic foci, echogenicity, and lymph nodes. The XGBoost model was significantly superior to any one of the machine learning models, with an AUC value of 0.829. According to the PDF and CUC, we recommended that 51% probability be used as a threshold for determining the risk stratification of malignant nodules, where about 85.6% of patients with malignant nodules could be detected. Meanwhile, approximately 89.8% of unnecessary biopsy procedures would be saved. Finally, an online web risk calculator has been built to estimate the personal likelihood of malignant thyroid nodules based on the best-performing ML-ed model of XGBoost.

Conclusions

Combining clinical characteristics and features of ultrasound images, ML algorithms can achieve reliable prediction of malignant thyroid nodules. The online web risk calculator based on the XGBoost model can easily identify in real-time the probability of malignant thyroid nodules, which can assist clinicians to formulate individualized management strategies for patients.

Imaging of Cervical Lymph Nodes in Thyroid Cancer: Ultrasound and Computed Tomography

Sonographic evaluation of cervical lymph nodes in patients with thyroid malignancy is important both for preoperative staging and for post-treatment surveillance, and contrast-enhanced computed tomography plays a complementary role. Knowledge of anatomy and surgical approaches, combined with an understanding of the various imaging features that distinguish malignant from benign lymph nodes, allows for accurate staging, thereby enabling complete surgical initial resection.

Ultrasound lymphatic imaging for the diagnosis of metastatic central lymph nodes in papillary thyroid cancer

OBJECTIVES

Up to 40% of papillary thyroid cancer (PTC) patients have lymph node metastasis, a condition that implies persistent, recurrent, or progressive disease. However, the American Joint Committee on Cancer Manual states that there is no reliable examination for adequate lymph node staging. Therefore, our aim is to develop a lymphatic imaging technique using ultrasonography to address this challenge.

METHODS

We consecutively enrolled PTC patients who underwent ultrasound (US) lymphatic imaging via the peritumoral injection of contrast media. Identification of the sentinel lymph nodes and the targeted sentinel lymph nodes was separately based on the lymphatic drainage pathway and the enhancement patterns. Every identified targeted node was assigned a score, according to the features on conventional US and enhancement patterns, and was referred for ultrasound-guided fine-needle aspiration. Cytological and histopathologic results represented the statuses of the targeted lymph nodes and overall central lymph nodes, respectively, which were applied to evaluate the diagnostic performance of US lymphatic imaging.

RESULTS

In total, 100 PTC patients were included. On the basis of the cytological results, the sensitivity (97.1%, 95% confidence interval [CI]: 84.7-99.9%) of detecting positive targeted nodes by US lymphatic imaging significantly increased by 45.5% at a threshold of 4 or higher (p = 0.0001), without loss of specificity (p = 1.0000). The surgical results showed that the metastatic degree was positively correlated with an increase in the score (τ: 0.671, p < 0.001).

CONCLUSION

Ultrasound lymphatic imaging has a high diagnostic performance, and its corresponding scoring system facilitates grading of the nodal burden in the central compartment.

KEY POINTS

• Ultrasound neck lymphatic imaging is an effective contrast-enhanced ultrasound (CEUS) technique (applied after the peritumoral injection of contrast media) for identifying sentinel lymph nodes in the central compartment by tracing the imaged afferent lymphatic vessel. • Lack of enhancement or perfusion defects is the typical enhancement pattern for recognizing the involved central lymph nodes. • Ultrasound lymphatic imaging for identification of positive central lymph nodes before surgery may effectively avoid complications associated with the surgical sentinel node procedure.

Development and validation of a nomogram for preoperative prediction of level VII nodal spread in papillary thyroid cancer: Radiologic-pathologic correlation

PURPOSE

To develop and validate a diagnostic nomogram for preoperative prediction of the level VII nodal spread in papillary thyroid cancer (PTC) by incorporating CT features.

METHODS

A dataset of 7896 patients experiencing thyroidectomy for thyroid cancer was collected retrospectively from two hospitals, and 300 patients were finally included in this study. The CT features of metastatic LN were extracted with a one by one match of radiologic-pathologic correlation. Multivariable binary logistic regression analysis was used to develop predicting model, and then a nomogram was developed utilizing a primary cohort of 152 patients from hospital #1. The nomogram was validated in external cohort of 62 patients from hospital #2 and an independent cohort of 86 patients from hospital #1. The performance of the nomogram was evaluated with respect to its calibration, discrimination.

RESULTS

531 LNs from 300 patients were analyzed. 42.6% LNs were > 5 mm in short diameter. A total of 7 selected CT features were significantly associated with LN status (P < 0.05), including nodular enhancement, cystic change, calcification and so on. These features were contained in the prediction nomogram. The model showed good discrimination and good calibration, with a C-index of 0.938 (95% CI, 0.913 to 0.963) and 0. 795 (95% CI, 0. 726 to 0.864) for the primary cohort and the validation cohort, respectively. Decision curve analysis demonstrated that the nomogram was clinically applicable.

CONCLUSIONS

This nomogram incorporating pathologically relevant CT features has demonstrated a high diagnostic value for predicting level VII nodal spread in PTC. Our work may help thyroid surgeon to decide whether upper mediastinal lymphadenectomy should be performed, which is associated with thoracotomy or other surgery.

The American Association of Endocrine Surgeons Guidelines for the Definitive Surgical Management of Thyroid Disease in Adults

OBJECTIVE

To develop evidence-based recommendations for safe, effective, and appropriate thyroidectomy.

BACKGROUND

Surgical management of thyroid disease has evolved considerably over several decades leading to variability in rendered care. Over 100,000 thyroid operations are performed annually in the US.

METHODS

The medical literature from 1/1/1985 to 11/9/2018 was reviewed by a panel of 19 experts in thyroid disorders representing multiple disciplines. The authors used the best available evidence to construct surgical management recommendations. Levels of evidence were determined using the American College of Physicians grading system, and management recommendations were discussed to consensus. Members of the American Association of Endocrine Surgeons reviewed and commented on preliminary drafts of the content.

RESULTS

These clinical guidelines analyze the indications for thyroidectomy as well as its definitions, technique, morbidity, and outcomes. Specific topics include Pathogenesis and Epidemiology, Initial Evaluation, Imaging, Fine Needle Aspiration Biopsy Diagnosis, Molecular Testing, Indications, Extent and Outcomes of Surgery, Preoperative Care, Initial Thyroidectomy, Perioperative Tissue Diagnosis, Nodal Dissection, Concurrent Parathyroidectomy, Hyperthyroid Conditions, Goiter, Adjuncts and Approaches to Thyroidectomy, Laryngology, Familial Thyroid Cancer, Postoperative Care and Complications, Cancer Management, and Reoperation.

CONCLUSIONS

Evidence-based guidelines were created to assist clinicians in the optimal surgical management of thyroid disease.

Added Value of Computed Tomography to Ultrasonography for Assessing LN Metastasis in Preoperative Patients with Thyroid Cancer: Node-By-Node Correlation

Diagnostic accuracy of US in the evaluation of lymph node (LN) metastasis for thyroid cancer patients is limited. We investigated the value of CT added to US for characterizing LNs in preoperative thyroid cancer patients by node-by-node correlation. A total of 225 primary thyroid cancer patients who underwent LN biopsy were included. Based on node-by-node correlation, 274 LNs were classified into probably benign, indeterminate, and suspicious categories on US, CT, and combined US/CT. Malignancy risks were calculated for each category and were compared between US/CT concordant and discordant cases. On US, CT, and combined US/CT, malignancy risks were 1.7%, 8.7%, and 0% in the probably benign category, 22.4%, 5.9%, and 8.0% in the indeterminate category, and 77.2%, 82.0%, and 75.6% in the suspicious category, respectively. Malignancy risk of the concordant suspicious category was higher than that of the discordant suspicious category (84.7% vs. 43.2%, p < 0.001). The addition of CT helped correctly detect additional metastasis in 16.4% of the US indeterminate LNs and in 1.7% of the US probably benign LNs. CT may complement US for LN characterization in thyroid cancer patients by suggesting the diagnostic confidence level for the suspicious category and helping correctly detect metastasis in US indeterminate LNs.

Clinical Diagnostic Evaluation of Thyroid Nodules

The presence of a thyroid nodule may be recognized by the patient or the clinician on palpation of the neck or it may be an incidental finding during an imaging study for some other indication. The method of detection is less important, however, than distinguishing benign lesions from more aggressive neoplasms. This article outlines the diagnostic algorithm for the evaluation of thyroid nodules including biochemical testing, imaging, and, when appropriate, fine-needle aspiration. In addition, the authors review the natural history of benign nodules, follow-up strategies, and indications for repeat aspiration.

Elastography as a potential modality for screening cervical lymph nodes in patients with papillary thyroid cancer: A review of literature

Papillary thyroid cancer often presents with cervical lymph node involvement and has a high incidence of recurrence, which requires routine follow-up with ultrasound imaging. Elastography is a novel ultrasound technique that has been demonstrated to be effective clinically in detecting tissue pathology in areas such as the liver and breast. Preliminary data suggest that it may be effective in screening tissues in the neck for malignancy, specifically cervical lymph nodes. However, diagnostic criteria and elastographic techniques vary significantly among the studies we have reviewed, which all tend to focus on populations of patients with many different types of primary malignancies. Further research is required on the feasibility of creating standardized and reproducible clinical criteria in a specific patient population. To study the clinical utility of elastography in cervical lymph nodes, patients with diagnosed papillary thyroid carcinoma may serve as an ideal population because of their need for ultrasound surveillance and the propensity of papillary thyroid cancer to metastasize to and recur in cervical lymph nodes. We will review the limitations, techniques, and reported clinical utility of elastography on cervical lymph nodes and its potential as a screening modality for papillary thyroid cancer.

Syncope caused by a pleomorphic adenoma: Case report and literature review

Pleomorphic adenomas are considered the most common salivary gland tumors, although they rarely occur in the parapharyngeal space. To the best of our knowledge, this is the first case report of a parapharyngeal parotid pleomorphic adenoma causing syncope. A 57-year-old man was admitted for left-sided blurred vision, left-sided weakness, dysarthria, lightheadedness, and syncope. Upon his admission, an electrocardiogram showed sinus bradycardia, and computed tomography of the neck with contrast showed a large parapharyngeal mass involving the prestyloid compartment, leading to compression of blood flow through the internal carotid artery. The mass was biopsied via intraoral fine-needle aspiration, which revealed cytology consistent with pleomorphic adenoma. The mass was resected via a transcervical approach, and a total parotidectomy was performed. The patient's hypotensive and bradycardic episodes disappeared after surgery. Surgical pathology showed a benign pleomorphic adenoma with a hemorrhagic and necrotic center and without capsular invasion or malignant transformation.

Risk prediction in children and adults less than 45 years old with papillary thyroid cancer

The incidence of papillary thyroid cancer is increasing faster than any other cancer in young patients. The purpose of this review is to discuss the most recent determinants of risk of recurrence and compromised outcomes in this population. Areas covered: This review discusses the most updated data on patient age, including children and young adults, extent of disease and subsequent dynamic staging over time, molecular markers for disease aggressiveness, adequacy of surgical resection and surgeon volume, and novel therapies for advanced non-resectable disease as predictors of patient outcomes. Expert commentary: Young patients enjoy excellent outcomes, with long-term survivorship, but face higher risks of short-term complications and disease recurrence. Thoughtful evaluation of the extent of disease, tumor features associated with more aggressive behavior, the presence of locoregional or distant metastases, and an understanding of molecular changes in their tumors are important areas of consideration. High-volume surgeons should work collaboratively with endocrinologists, radiologists, and pathologists specializing in thyroid cancer to help patients achieve excellent outcomes. Emerging data challenging the status quo regarding the relative importance of patient age, tumor features, and dynamic risk-adjustment for overall prognosis of these patients will likely impact future care and staging systems.

The relevance of preoperative ultrasound cervical mapping in patients with thyroid cancer

BACKGROUND

Cervical lymph node involvement in thyroid cancer is associated with locoregional recurrence and decreased disease-free survival. Preoperative lymph node mapping helps in planning surgery for neck dissection and improves patient outcomes. We sought to perform a qualitative and quantitative analysis of ultrasound mapping for thyroid cancer and evaluate the clinical importance of this exam in terms of identifying the group of patients who would benefit most from subsequent surgical dissection.

METHODS

We retrospectively reviewed the cases of 263 patients who underwent thyroid surgery between 2009 and 2013. We calculated the positive predictive values (PPVs) of ultrasound mapping of both the lateral and central compartments together and the lateral or central compartment individually. A quantitative analysis was performed by comparing the number of positive lymph nodes at ultrasound imaging with histopathologic evaluation.

RESULTS

A total of 136 cases of thyroid cancer in 120 patients met the inclusion criteria for ultrasound mapping analysis. The PPVs (and 95% confidence intervals) were 83.82 (0.76-0.89) for the lateral and central compartments, 85.39% (0.76-0.91) for the lateral compartment, and 80.48% (0.7-0.87) for the central compartment. When comparing the positive lymph nodes at ultrasound imaging with histopathologic evaluation, the result was χ(2) = 10.33 (p = 0.006).

CONCLUSION

This single-institution study indicated that preoperative ultrasound mapping is an accurate imaging procedure for predicting lymphatic spread in differentiated and medullary thyroid cancer. Ultrasound mapping can be used as an efficient tool for surgical planning and prognosis determination, as well as for identifying the group of patients who would benefit most from subsequent surgical intervention.

Preoperative Lymph Node Staging by FDG PET/CT With Contrast Enhancement for Thyroid Cancer: A Multicenter Study and Comparison With Neck CT

Objectives

The purpose of this study was to compare lymph node (LN) staging using ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) with contrast-enhancement (CE) PET/CT and contrast-enhanced neck CT (neck CT) in patients with thyroid cancer with level-by-level comparison with various factors.

Methods

This was a retrospective multicenter study. A total of 85 patients were enrolled. Patients who underwent a preoperative evaluation by CE PET/CT and neck CT for thyroid cancer were enrolled. The gold standard for LN was the combination of surgical pathology and clinical follow-up. We compared CE PET/CT with neck CT using a level-by-level method. Factors, including age, sex, camera, arm position, tumor size, extra-thyroidal extension, tumor location, number of primary tumors, primary tumor maximum standardized uptake value, and the interval from scan to operation were also analyzed.

Results

Overall accuracy was 81.2% for CE PET/CT and 68.2% for neck CT. CE PET/CT was more sensitive than neck CT (65.8% vs. 44.7%). Also, CE PET/CT showed higher negative predictive value (77.2% vs. 66.1%). CE PET/CT showed good agreement with the gold standard (weighted kappa [κ], 0.7) for differentiating N0, N1a, and N1b, whereas neck CT showed moderate agreement (weighted κ, 0.5). CE PET/CT showed better agreement for the number of levels involved with the gold standard (weighted κ, 0.7) than that of neck CT with the gold standard (weighted κ, 0.5). The accuracies for differentiating N0, N1a, and N1b were 81.2% for CE PET/CT and 68.2% for neck CT. Level-by-level analysis showed that CE PET/CT was more sensitive and has higher negative predictive value for detecting ipsilateral level IV and level VI LNs than neck CT. Other analyzed factors were not related to accuracies of both modalities.

Conclusion

CE PET/CT was more sensitive and reliable than neck CT for preoperative LN staging in patients with thyroid cancer.

Ultrasound-based clinical prediction rule model for detecting papillary thyroid cancer in cervical lymph nodes: A pilot study

PURPOSE

To identify sonographic features of cervical lymph nodes (LNs) that are associated with papillary thyroid cancer (PTC) and to develop a prediction model for classifying nodes as metastatic or benign.

METHODS

This retrospective study included the records of postthyroidectomy patients with PTC who had undergone cervical ultrasound and LN biopsy. LN location, size, shape, hilum, echopattern, Doppler flow, and microcalcifications were assessed. Model selection was used to identify features associated with malignant LNs and to build a predictive, binary-outcome, generalized linear mixed model. A cross-validated receiver operating characteristic analysis was conducted to assess the accuracy of the model for classifying metastatic nodes.

RESULTS

We analyzed records from 71 LNs (23 metastatic) in 44 patients (16 with PTC). The predictive model included a nonhomogeneous echopattern (odds ratio [OR], 5.73; 95% confidence interval [CI], 1.07-30.74; p = 0.04), microcalcifications (OR, 4.91; 95% CI, 0.91-26.54; p = 0.06), and volume (OR, 2.57; 95% CI, 0.66-9.99; p = 0.16) as predictors. The model had an area under the curve of 0.74 (95% CI, 0.60-0.85), sensitivity of 65% (95% CI, 50% to 78%), and specificity of 85% (95% CI, 73% to 94%) at the Youden optimal cut point of 0.38.

CONCLUSIONS

Nonhomogeneous echopattern, microcalcifications, and node volume were predictive of malignant LNs in patients with PTC. A larger sample is needed to validate this model.

American Thyroid Association statement on preoperative imaging for thyroid cancer surgery

BACKGROUND

The success of surgery for thyroid cancer hinges on thorough and accurate preoperative imaging, which enables complete clearance of the primary tumor and affected lymph node compartments. This working group was charged by the Surgical Affairs Committee of the American Thyroid Association to examine the available literature and to review the most appropriate imaging studies for the planning of initial and revision surgery for thyroid cancer.

SUMMARY

Ultrasound remains the most important imaging modality in the evaluation of thyroid cancer, and should be used routinely to assess both the primary tumor and all associated cervical lymph node basins preoperatively. Positive lymph nodes may be distinguished from normal nodes based upon size, shape, echogenicity, hypervascularity, loss of hilar architecture, and the presence of calcifications. Ultrasound-guided fine-needle aspiration of suspicious lymph nodes may be useful in guiding the extent of surgery. Cross-sectional imaging (computed tomography with contrast or magnetic resonance imaging) may be considered in select circumstances to better characterize tumor invasion and bulky, inferiorly located, or posteriorly located lymph nodes, or when ultrasound expertise is not available. The above recommendations are applicable to both initial and revision surgery. Functional imaging with positron emission tomography (PET) or PET-CT may be helpful in cases of recurrent cancer with positive tumor markers and negative anatomic imaging.

[Cysts in the posterior triangle of the neck in adults]

Cystic lesions of the posterior triangle are a pathologic entity whose diagnosis is made in the first two years of life. Its presentation in adulthood is an incidental finding and the differential diagnosis includes cystic lymphangioma, lymphatic metastasis of thyroid cancer and branchial cyst. Often with the finding of a cervical lump, FNA is made before diagnostic imaging is performed, however, this procedure is not always advisable. We reviewed the cases of patients who came last year to our department with a cystic mass in this location and correlating the imaging findings with pathologic specimen. We show characteristic findings of these lesions in order to make an early diagnosis and thus to get the approach and treatment appropriate of adult patients with a cystic lesion in the posterior cervical triangle.

Current and future lymphatic imaging modalities for tumor staging

Tumor progression is supported by the lymphatic system which should be scanned efficiently for tumor staging as well as the enhanced therapeutic outcomes. Poor resolution and low sensitivity is a limitation of traditional lymphatic imaging modalities; thus new noninvasive approaches like nanocarriers, magnetic resonance imaging, positron-emission tomography, and quantum dots are advantageous. Some newer modalities, which are under development, and their potential uses will also be discussed in this review.

Thyroid ultrasonography: pitfalls and techniques

Thyroid ultrasonography (US) plays a key role in the diagnosis and management of thyroid-related diseases. The aim of this article was to illustrate various pitfalls that can occur in utilizing thyroid US and techniques to prevent them. In this article, we present cases demonstrating the common pitfalls associated with US equipment, performance, normal thyroid structures, misinterpretations, and surrounding structures. Knowledge of these areas is essential to avoid misdiagnosis or improper disease management.

The role of 18F-fluorodeoxyglucose positron emission tomography in differentiated thyroid cancer before surgery

The incidence of thyroid cancer in both men and women is increasing faster than that of any other cancer. Although positron emission tomography (PET) using (18)F-fluorodeoxyglucose (FDG) has received much attention, the use of FDG PET for the management of thyroid cancer is limited primarily to postoperative follow-up. However, it might have a role in selected, more aggressive pathologies, and so patients at a high risk of distant metastasis may benefit from PET before surgery. As less FDG-avid thyroid cancers may lower the diagnostic accuracy of PET in preoperative assessment, an understanding of FDG avidity is important for the evaluation of thyroid cancer. FDG avidity has been shown to be associated with tumor size, lymph node metastasis, and glucose transporter expression and differentiation. As PET is commonly used in clinical practice, the detection of incidentalomas by PET is increasing. However, incidentalomas detected by PET have a high risk of malignancy. Clinicians handling cytologically indeterminate nodules face a dilemma regarding a procedure for a definitive diagnosis, usually lobectomy. With 'nondiagnostic (ND)' fine-needle biopsy (FNA), PET has shown a negative predictive value (NPV) of 100%, which indicates that negative uptake in a ND FNA procedure accurately excludes malignancy. With 'atypia of undetermined significance' or 'follicular neoplasm', the sensitivity and NPV of PET are 84 and 88%. PET does not provide additional information for the preoperative assessment of thyroid cancer. However, factors associated with FDG positivity are related to a poor prognosis; therefore, FDG PET scans before surgery may facilitate the prediction of the prognosis of differentiated thyroid cancer.

Translational imaging of lymphatics in cancer

Imaging in the lymphatic system has gone through much advancement over the past 70 years since its beginnings. In this review, we will examine the modalities available for lymphatic imaging. We will explore the modern uses of early modalities, such as ultrasound as well as more modern modalities, such as Positron-Emission Tomography (PET). We will also describe some of the new modalities currently in development and their potential uses for the future as well as some of the current imaging modalities being studied in animal models.