Invasion in thyroid cancer: Controversies and best practices

Machine learning based on SEER database to predict distant metastasis of thyroid cancer

OBJECTIVE

Distant metastasis of thyroid cancer often indicates poor prognosis, and it is important to identify patients who have developed distant metastasis or are at high risk as early as possible. This paper aimed to predict distant metastasis of thyroid cancer through the construction of machine learning models to provide a reference for clinical diagnosis and treatment.

MATERIALS & METHODS

Data on demographic and clinicopathological characteristics of thyroid cancer patients between 2010 and 2015 were extracted from the National Institutes of Health (NIH) Surveillance, Epidemiology, and End Results (SEER) database. Our research used univariate and multivariate logistic models to screen independent risk factors, respectively. Decision Trees (DT), ElasticNet (ENET), Logistic Regression (LR), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Multilayer Perceptron (MLP), Radial Basis Function Support Vector Machine (RBFSVM) and seven machine learning models were compared and evaluated by the following metrics: the area under receiver operating characteristic curve (AUC), calibration curve, decision curve analysis (DCA), sensitivity(also called recall), specificity, precision, accuracy and F1 score. Interpretable machine learning was used to identify possible correlation between variables and distant metastasis.

RESULTS

Independent risk factors for distant metastasis, including age, gender, race, marital status, histological type, capsular invasion, and number of lymph nodes metastases were screened by multifactorial regression analysis. Among the seven machine learning algorithms, RF was the best algorithm, with an AUC of 0.948, sensitivity of 0.919, accuracy of 0.845, and F1 score of 0.886 in the training set, and an AUC of 0.960, sensitivity of 0.929, accuracy of 0.906, and F1 score of 0.908 in the test set.

CONCLUSIONS

The machine learning model constructed in this study helps in the early diagnosis of distant thyroid metastases and helps physicians to make better decisions and medical interventions.

Correlation of pN Stage and Hypoechogenicity with Tumour Encapsulation and Vascular Invasion in Thyroid Cancer (TC): A Comprehensive Analysis and Clinical Outcomes

In this retrospective study, the relationship between the pN stage of TC and the ultrasound hypoechogenicity of tumour encapsulation and vascular invasion was investigated. The data of a total of 678 TC patients were analysed. The goal of this study was to assess the significance of the pTNM score and preoperative ultrasound features in predicting cancer prognosis and guiding therapeutic decisions in patients with TC. The main research methods included a retrospective analysis of patient data, mainly the pTNM score and presence of tumour encapsulation and vascular invasion obtained from histopathological results and preoperative ultrasound imaging. Patients with well-differentiated TCs (papillary and follicular) were extracted from TC patients to better unify the results because of similar clinical strategies for these TCs. Significant associations were observed between advanced pN stage and the presence of encapsulation and vessel invasion. The majority of pN1a patients exhibited encapsulation (77.71%; p < 0.0001) and vascular invasion (75.30%; p < 0.0001), as did the majority of pN1b patients (100%; p < 0.0001 and 100%; p < 0.0001, respectively). Less than half of the patients with hypoeghogenic patterns presented with encapsulation (43.30%; p < 0.0001) and vascular invasion (43.52%; p < 0.0001), while the vast majority of patients without hypoechogenicity did not present with encapsulation (90.97%; p < 0.0001) or vascular invasion (90.97%; p < 0.0001). Hypoechogenicity was found to be indicative of aggressive tumour behaviour. The results of this study underscore the importance of accurate N staging in TC and suggests the potential use of ultrasound features in predicting tumour behaviour. Further research is needed to confirm these findings and explore additional prognostic markers to streamline TC management strategies and improve patient outcomes.

Pathology and new insights in thyroid neoplasms in the 2022 WHO classification

PURPOSE OF REVIEW

The assessment of thyroid nodules is a common clinical problem, linked to the high incidence of thyroid nodules in the population and the low incidence of aggressive thyroid carcinoma. The screening is therefore one of the strengths of our patient care. Recently, the 2023 Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) and 2022 WHO classification of thyroid neoplasms have been released based on the definition of new entities and the growing impact of molecular testing. The aim of this review is to analyze how these upgrades can help us in the daily routine practice diagnosis of thyroid cancer.

RECENT FINDINGS

Our review is focused on the most frequent thyroid tumors derived from thyroid follicular cell. Fine needle aspiration (FNA) is the gold standard for the screening of thyroid nodules with very high levels of sensitivity and specificity. These sensitivity and specificity are improved by molecular testing, which refines the risk of malignancy. The 2023 TBSRTC integrates molecular data and the upgrades integrated in the 2022 WHO classification such as the 'low-risk neoplasms' and the 'high-grade follicular-cells derived carcinoma'. The morphological examination remains crucial since the capsular and/or vascular invasion are key features of malignancy in the follicular thyroid neoplasms. Low-risk neoplasms represent a clinical challenge since no specific guidelines are available. Challenges remain regarding oncocytic thyroid lesions, which are not associated with specific diagnostic molecular biomarkers. Molecular testing can help not only in deciphering the prognosis but also in the targeted therapeutic strategy.

SUMMARY

While molecular testing has succeeded to substantially improve the pre and postoperative diagnosis and risk stratification of thyroid tumors, the morphological examination is still central in the daily routine diagnosis of thyroid pathology. Future is the integrated diagnosis of clinical, morphological, molecular and epigenetic features with the help of artificial intelligence algorithms.

Exploring the clinical utility of angioinvasion markers in papillary thyroid cancer: a literature review

Papillary thyroid cancer (PTC) is the most common type of thyroid cancer, and angioinvasion, the invasion of blood vessels by cancer cells, is a crucial pathological feature associated with disease progression and poor prognosis. Thus, a comprehensive search of scientific databases was conducted to identify relevant studies investigating angioinvasion markers in PTC. The selected studies were reviewed and analyzed to assess the clinical significance and potential utility of these markers in predicting angioinvasion and guiding treatment decisions. Numerous studies have investigated various markers associated with angioinvasion in PTC, including oxidative stress, vascular endothelial growth factor (VEGF), matrix metalloproteinases (MMPs), and other angiogenic factors. The results indicate that increased expression of these markers is correlated with the presence and extent of angioinvasion in PTC. Moreover, some studies suggest that these markers can serve as prognostic indicators and guide therapeutic strategies, such as selecting patients for more aggressive treatment approaches or targeted therapies. The findings from the reviewed literature highlight the potential clinical utility of angioinvasion markers in PTC. The identification and validation of reliable markers can aid in assessing the risk of angioinvasion, predicting disease progression, and optimizing treatment decisions for patients with PTC. However, further research and validation on larger patient cohorts are necessary to establish the robustness and generalizability of these markers in clinical practice.

Factors influencing extrathyroidal extension of papillary thyroid cancer and evaluation of ultrasonography for its diagnosis: a retrospective analysis

Pathologists usually explore extrathyroidal extensions (ETEs) in thyroid cancer; however, sonographers are often not concerned with ETEs. We investigated factors influencing ETEs and the efficacy of ultrasound evaluation of thyroid capsule invasion. We retrospectively analysed 1933 papillary thyroid carcinoma patients who underwent thyroidectomy during 2018-2021. Patients were divided into three groups: no ETE, minor ETE (mETE), and gross ETE. Clinical characteristic differences were assessed using binary logistic regression analysis to identify ETE predictors, and the kappa test was performed to analyse consistency between ultrasonographic and pathological diagnoses of ETE. The mETE group was more likely to have larger tumour diameters and more extensive lymph node metastasis (LNM) than the no ETE group and more likely to be diagnosed in the isthmus. In the multivariate logistic regression analysis, longest tumour diameter, lesion site, LNM extent, and thyroglobulin concentration were significant mETE predictors. Minimal consistency existed between pathological and ultrasonographic examinations for neighbouring tissue invasion. Many clinical differences were observed between the no ETE and mETE groups, suggesting the importance of considering mETE. Therefore, sonographers should pay more attention to relationships between nodules and capsule and indicate these on ultrasound reports to provide more accurate preoperative ETE information for surgeons.

Clinical significance of oxidative stress markers as angioinvasion and metastasis indicators in papillary thyroid cancer

Angioinvasion remains the important prognostic feature in papillary thyroid cancer (PTC) patients. Literature data indicates several markers that may be associated with oxidative stress and/or angioinvasion. Therefore, we assessed the utility of selected parameters in angioinvasion and metastasis screening in serum of PTC patients. Serum antioxidant capacity (TAC) and sirtuin 3 (SIRT3) levels were decreased (all p < 0.05) and both DNA/RNA oxidative stress damage products (DNA/RNA OSDP) and malondialdehyde (MDA) levels were increased in PTC patients with angioinvasion and metastasis (study group) when compared with PTC patients without these features (all p < 0.01). The highest screening utility in differentiation between angioinvasion and metastasis presence and absence in PTC patients was presented for DNA/RNA OSDP (AUC = 0.71), SIRT3 (AUC = 0.70), and TAC (AUC = 0.67) (all p < 0.05). Our study suggests that peripheral concentration of oxidative stress markers could be useful as angioinvasion and metastasis indicator in PTC patients.

Preoperative prediction of extrathyroidal extension: radiomics signature based on multimodal ultrasound to papillary thyroid carcinoma

BACKGROUND

There is a recognized need for additional approaches to improve the accuracy of extrathyroidal extension (ETE) diagnosis in papillary thyroid carcinoma (PTC) before surgery. Up to now, multimodal ultrasound has been widely applied in disease diagnosis. We investigated the value of radiomic features extracted from multimodal ultrasound in the preoperative prediction of ETE.

METHODS

We retrospectively pathologically confirmed PTC lesions in 235 patients from January 2019 to April 2022 in our hospital, including 45 ETE lesions and 205 non-ETE lesions. MaZda software was employed to obtain radiomics parameters in multimodal sonography. The most valuable radiomics features were selected by the Fisher coefficient, mutual information, probability of classification error and average correlation coefficient methods (F + MI + PA) in combination with the least absolute shrinkage and selection operator (LASSO) method. Finally, the multimodal model was developed by incorporating the clinical records and radiomics features through fivefold cross-validation with a linear support vector machine algorithm. The predictive performance was evaluated by sensitivity, specificity, accuracy, F1 scores and the area under the receiver operating characteristic curve (AUC) in the training and test sets.

RESULTS

A total of 5972 radiomics features were extracted from multimodal sonography, and the 13 most valuable radiomics features were selected from the training set using the F + MI + PA method combined with LASSO regression. The multimodal prediction model yielded AUCs of 0.911 (95% CI 0.866-0.957) and 0.716 (95% CI 0.522-0.910) in the cross-validation and test sets, respectively. The multimodal model and radiomics model showed good discrimination between ETE and non-ETE lesions.

CONCLUSION

Radiomics features based on multimodal ultrasonography could play a promising role in detecting ETE before surgery.

Challenges in Encapsulated Follicular-Patterned Tumors: How Much Is Enough? Evaluation of Nuclear Atypia, Architecture, and Invasion

Thyroid pathology is notoriously fraught with high interobserver variability, and follicular-patterned tumors are among some of the most challenging to assess accurately and reproducibly. Given that encapsulated or well-circumscribed follicular-patterned tumors often have similar molecular profiles, that is, frequent RAS or RAS-like alterations, the diagnosis usually relies on histopathologic examination alone. Unfortunately, many of the features that are used for diagnosis and prognosis of these tumors have long been controversial and frequently debated topics, both due to their subjectivity and their evolving (or not yet resolved) definitions. In more recent years, the introduction of noninvasive follicular thyroid neoplasm with papillary-like nuclear features has added further complexity to this discussion. In particular, the criteria and significance of nuclear features of papillary thyroid carcinoma, architectural patterns, and invasive growth still pose significant diagnostic challenges and confusion. This review explores some of the challenges in evaluating encapsulated follicular-patterned tumors, focusing on those histologic elements.

Ultrasound-guided thermal ablation for papillary thyroid microcarcinoma: A systematic review

OBJECTIVE

Thyroidectomy is the first-line treatment for papillary thyroid microcarcinoma (PTMC), but often involves aggressive overtreatment. Thermal ablation (TA) has been gradually used for the treatment of recurrent PTMC. However, it is not recommended for the treatment of primary PTMC according to the Korean and Italian guidelines. Therefore, this systematic review aimed to analyse the indications, efficacy, and safety of TA in the treatment of PTMC.

DESIGN

Systematic review.

PATIENTS AND MEASUREMENTS

A search strategy was developed in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement. A total of 27 articles were included in this study until January 2022.

RESULTS

According to current guidelines and studies, we divided the indications of TA for PTMC into six primary and three secondary indications. Laser ablation (LA) has the advantages of a small needle, accurate output energy and precision ablation, and it is safe to important organs around the lesion. The patients recover quickly after radiofrequency ablation (RFA), with no major complications, recurrence, or lymph node metastasis. The volume reduction rate after RFA was the highest, followed by microwave ablation and LA, and the improvement in patient quality of life after TA was significantly better than after thyroidectomy.

CONCLUSIONS

TA is an effective alternative method for surgery in the treatment of low-risk PTMC and has the advantages of being minimally invasive, economical, having less bleeding and having a high postoperative quality of life.

Risk Factors for Contralateral Occult Papillary Thyroid Carcinoma in Patients with Clinical Unilateral Papillary Thyroid Carcinoma: A Case-Control Study

INTRODUCTION

Papillary thyroid cancer (PTC) is one of the most prevalent endocrine malignancies that has increased in recent decades around the world. Although the indicator for navigating the surgical extent in PTC patients is still in debate, a key issue is how to predict that there are undetected preoperative tumors in the contralateral thyroid lobe. This study aims to find risk factors for contralateral occult papillary thyroid cancer (COPTC) to facilitate more accurate surgical decisions made for patients with PTC.

MATERIALS AND METHODS

In our study, we included 229 patients who underwent total thyroidectomy plus central and ipsilateral lateral lymph nodes dissection from January 1, 2019, to September 1, 2021. Univariate and multivariate logistic regression analyses were conducted to assess the association between COPTC and clinical-pathological characteristics, as well as the relation between the diameter of the occult lesions and predictors. The forest plot was plotted to visualize the prediction factors from the output of the multivariate regression analysis. A ROC curve was used to evaluate the combining potency of all the risk factors.

RESULTS

Of the 229 patients included in our study, 46 with COPTC were assigned to the case group, representing 20.1% in this study. Multifocality in one lobe (OR = 2.21, P=0.03), intact capsule (OR = 2.54, P=0.01), central lymph node metastasis (OR = 3.00, P=0.02), and Hashimoto's thyroiditis (OR = 2.08, P = 0.04) are more prone to present contralateral occult papillary thyroid carcinoma. The ROC curve of the aggregate potency of the risk factors presents AUC = 0.701 (P < 0.001), and the best cutoff value was 2.02, with a sensitivity of 78.3% and specificity of 55.2%. Furthermore, there was no statistical correlation between the diameter of the occult tumor and the four obtained variables.

CONCLUSION

Patients with multifocality in one lobe, intact capsule, central lymph node metastasis, and HT may harbor contralateral papillary thyroid carcinoma. It is essential to be prudent to make a surgical or follow-up decision on these patients. In addition, more clinical rather than postoperative pathological indicators need to be revealed in the future.