Thyroid cancer neck lymph nodes metastasis: Meta-analysis of US and CT diagnosis

Application of deep-learning to the automatic segmentation and classification of lateral lymph nodes on ultrasound images of papillary thyroid carcinoma

PURPOSE

It is crucial to preoperatively diagnose lateral cervical lymph node (LN) metastases (LNMs) in papillary thyroid carcinoma (PTC) patients. This study aims to develop deep-learning models for the automatic segmentation and classification of LNM on original ultrasound images.

METHODS

This study included 1000 lateral cervical LN ultrasound images (consisting of 512 benign and 558 metastatic LNs) collected from 728 patients at the Chongqing General Hospital between March 2022 and July 2023. Three instance segmentation models (MaskRCNN, SOLO and Mask2Former) were constructed to segment and classify ultrasound images of lateral cervical LNs by recognizing each object individually and in a pixel-by-pixel manner. The segmentation and classification results of the three models were compared with an experienced sonographer in the test set.

RESULTS

Upon completion of a 200-epoch learning cycle, the loss among the three unique models became negligible. To evaluate the performance of the deep-learning models, the intersection over union threshold was set at 0.75. The mean average precision scores for MaskRCNN, SOLO and Mask2Former were 88.8%, 86.7% and 89.5%, respectively. The segmentation accuracies of the MaskRCNN, SOLO, Mask2Former models and sonographer were 85.6%, 88.0%, 89.5% and 82.3%, respectively. The classification AUCs of the MaskRCNN, SOLO, Mask2Former models and sonographer were 0.886, 0.869, 0.90.2 and 0.852 in the test set, respectively.

CONCLUSIONS

The deep learning models could automatically segment and classify lateral cervical LNs with an AUC of 0.92. This approach may serve as a promising tool to assist sonographers in diagnosing lateral cervical LNMs among patients with PTC.

Predictive Values of Clinical Features and Multimodal Ultrasound for Central Lymph Node Metastases in Papillary Thyroid Carcinoma

Papillary thyroid carcinoma (PTC), the predominant pathological type among thyroid malignancies, is responsible for the sharp increase in thyroid cancer. Although PTC is an indolent tumor with good prognosis, 60-70% of patients still have early cervical lymph node metastasis, typically in the central compartment. Whether there is central lymph node metastasis (CLNM) or not directly affects the formulation of preoperative surgical procedures, given that such metastases have been tied to compromised overall survival and local recurrence. However, detecting CLNM before operation can be challenging due to the limited sensitivity of preoperative approaches. Prophylactic central lymph node dissection (PCLND) in the absence of clinical evidence of CLNM poses additional surgical risks. This study aims to provide a comprehensive review of the risk factors related to CLNM in PTC patients. A key focus is on utilizing multimodal ultrasound (US) for accurate prognosis of preoperative CLNM and to highlight the distinctive role of US-based characteristics for predicting CLNM.

Prediction of lymph node metastasis in patients with papillary thyroid cancer based on radiomics analysis and intraoperative frozen section analysis: A retrospective study

INTRODUCTION

To evaluate the diagnostic efficiency among the clinical model, the radiomics model and the nomogram that combined radiomics features, frozen section (FS) analysis and clinical characteristics for the prediction of lymph node (LN) metastasis in patients with papillary thyroid cancer (PTC).

METHODS

A total of 208 patients were randomly divided into two groups randomly with a proportion of 7:3 for the training groups (n = 146) and the validation groups (n = 62). The Least Absolute Shrinkage and Selection Operator (LASSO) regression was used for the selection of radiomics features extracted from ultrasound (US) images. Univariate and multivariate logistic analyses were used to select predictors associated with the status of LN. The clinical model, radiomics model and nomogram were subsequently established by logistic regression machine learning. The area under the curve (AUC), sensitivity and specificity were used to evaluate the diagnostic performance of the different models. The Delong test was used to compare the AUC of the three models.

RESULTS

Multivariate analysis indicated that age, size group, Adler grade, ACR score and the psammoma body group were independent predictors of lymph node metastasis (LNM). The results showed that in both the training and validation groups, the nomogram showed better performance than the clinical model, albeit not statistically significant (p > .05), and significantly outperformed the radiomics model (p < .05). However, the nomogram exhibits a slight improvement in sensitivity that could reduce the incidence of false negatives.

CONCLUSION

We propose that the nomogram holds substantial promise as an effective tool for predicting LNM in patients with PTC.

Development and Validation of a Computed Tomography-Based Radiomics Nomogram for the Preoperative Prediction of Central Lymph Node Metastasis in Papillary Thyroid Microcarcinoma

RATIONALE AND OBJECTIVES

This study aims to develop and validate a computed tomography (CT)-based radiomics nomogram for pre-operatively predicting central lymph node metastasis (CLNM) in patients with papillary thyroid microcarcinoma (PTMC) and explore the underlying biological basis by using RNA sequencing data.

METHODS

This study trained 452 PTMC patients across two hospitals from January 2012 to December 2020. The sets were randomly divided into the training (n = 339), internal test (n = 86), external test (n = 27) sets. Radiomics features were extracted from primary lesion's pre-operative CT images for each patient. After screening for features, five algorithms such as K-nearest neighbor, logistics regression, linear-support vector machine (SVM), Gaussian SVM, and polynomial SVM were used to establish the radiomics models. The performance of these five algorithms was evaluated and compared directly to radiologist's interpretation (CT-reported lymph node status). The radiomics signature score (Rad-score) was generated using a linear combination of the selected features. By combining the clinical risk factors and Rad score, a radiomics nomogram was established and compared with Rad-score and clinical model. The performance of the nomogram was evaluated based on the receiver operating characteristic (ROC) curve, calibration curve, and the decision curve analysis (DCA). The potential biological basis of nomogram was revealed by performing genetic analysis based on the RNA sequencing data.

RESULTS

A total of 25 radiomic features were ultimately selected to train the machine learning models, and the five machine learning models outperformed the radiologists' interpretation by achieving area under the ROC curves (AUCs) ranging from 0.606 to 0.730 in the internal test set. By incorporating the Rad score and clinical risk factors (sex, age, tumor-diameter, and CT-reported lymph node status), this nomogram achieved AUCs of 0.800 and 0.803 in the internal and external test set, which were higher than that of the Rad-score and clinical model, respectively. Calibration curves and DCA also showed that the nomogram had good performance. As for the biological basis exploration, in patients predicted by nomogram to be PTC patients with CLMN, 109 genes were dysregulated, and some of them were associated with pathways and biological processes such as tumor angiogenesis.

CONCLUSION

This radiomics nomogram successfully identified CLNM on pretreatment imaging across multiple institutions, exceeding the diagnostic ability of radiologists and had the potential to be integrated into clinical decision making as a non-invasive pre-operative tool.

Predicting central cervical lymph node metastasis in papillary thyroid carcinoma with Hashimoto's thyroiditis: a practical nomogram based on retrospective study

Background

In papillary thyroid carcinoma (PTC) patients with Hashimoto's thyroiditis (HT), preoperative ultrasonography frequently reveals the presence of enlarged lymph nodes in the central neck region. These nodes pose a diagnostic challenge due to their potential resemblance to metastatic lymph nodes, thereby impacting the surgical decision-making process for clinicians in terms of determining the appropriate surgical extent.

Methods

Logistic regression analysis was conducted to identify independent risk factors associated with central lymph node metastasis (CLNM) in PTC patients with HT. Then a prediction model was developed and visualized using a nomogram. The stability of the model was assessed using ten-fold cross-validation. The performance of the model was further evaluated through the use of ROC curve, calibration curve, and decision curve analysis.

Results

A total of 376 HT PTC patients were included in this study, comprising 162 patients with CLNM and 214 patients without CLNM. The results of the multivariate logistic regression analysis revealed that age, Tg-Ab level, tumor size, punctate echogenic foci, and blood flow grade were identified as independent risk factors associated with the development of CLNM in HT PTC. The area under the curve (AUC) of this model was 0.76 (95% CI [0.71-0.80]). The sensitivity, specificity, accuracy, and positive predictive value of the model were determined to be 88%, 51%, 67%, and 57%, respectively.

Conclusions

The proposed clinic-ultrasound-based nomogram in this study demonstrated a favorable performance in predicting CLNM in HT PTCs. This predictive tool has the potential to assist clinicians in making well-informed decisions regarding the appropriate extent of surgical intervention for patients.

Prediction of cervical lymph node metastasis in differentiated thyroid cancer based on radiomics models

OBJECTIVE

The accurate clinical diagnosis of cervical lymph node metastasis plays an important role in the treatment of differentiated thyroid cancer (DTC). This study aimed to explore and summarize a more objective approach to detect cervical malignant lymph node metastasis of DTC via radiomics models.

METHODS

PubMed, Web of Science, MEDLINE, EMBASE, and Cochrane databases were searched for all eligible studies. Articles using radiomics models based on ultrasound, computed tomography, or magnetic resonance imaging to assess cervical lymph node metastasis preoperatively were included. Characteristics and diagnostic accuracy measures were extracted. Bias and applicability judgments were evaluated by the revised QUADAS-2 tool. The estimates were pooled using a random-effects model. Additionally, the leave-one-out method was conducted to assess the heterogeneity.

RESULTS

Twenty-nine radiomics studies with 6160 validation set patients were included in the qualitative analysis, and 11 studies with 3863 validation set patients were included in the meta-analysis. Four of them had an external independent validation set. The studies were heterogeneous, and a significant risk of bias was found in 29 studies. Meta-analysis showed that the pooled sensitivity and specificity for preoperative prediction of lymph node metastasis via US-based radiomics were 0.81 (95% CI, 0.73-0.86) and 0.87 (95% CI, 0.83-0.91), respectively.

CONCLUSIONS

Although radiomics-based models for cervical lymphatic metastasis in DTC have been demonstrated to have moderate diagnostic capabilities, broader data, standardized radiomics features, robust feature selection, and model exploitation are still needed in the future.

ADVANCES IN KNOWLEDGE

The radiomics models showed great potential in detecting malignant lymph nodes in thyroid cancer.

Analysis of preoperative computed tomography radiomics and clinical factors for predicting postsurgical recurrence of papillary thyroid carcinoma

BACKGROUND

Postsurgical recurrence is of great concern for papillary thyroid carcinoma (PTC). We aim to investigate the value of computed tomography (CT)-based radiomics features and conventional clinical factors in predicting the recurrence of PTC.

METHODS

Two-hundred and eighty patients with PTC were retrospectively enrolled and divided into training and validation cohorts at a 6:4 ratio. Recurrence was defined as cytology/pathology-proven disease or morphological evidence of lesions on imaging examinations within 5 years after surgery. Radiomics features were extracted from manually segmented tumor on CT images and were then selected using four different feature selection methods sequentially. Multivariate logistic regression analysis was conducted to identify clinical features associated with recurrence. Radiomics, clinical, and combined models were constructed separately using logistic regression (LR), support vector machine (SVM), k-nearest neighbor (KNN), and neural network (NN), respectively. Receiver operating characteristic analysis was performed to evaluate the model performance in predicting recurrence. A nomogram was established based on all relevant features, with its reliability and reproducibility verified using calibration curves and decision curve analysis (DCA).

RESULTS

Eighty-nine patients with PTC experienced recurrence. A total of 1218 radiomics features were extracted from each segmentation. Five radiomics and six clinical features were related to recurrence. Among the 4 radiomics models, the LR-based and SVM-based radiomics models outperformed the NN-based radiomics model (P = 0.032 and 0.026, respectively). Among the 4 clinical models, only the difference between the area under the curve (AUC) of the LR-based and NN-based clinical model was statistically significant (P = 0.035). The combined models had higher AUCs than the corresponding radiomics and clinical models based on the same classifier, although most differences were not statistically significant. In the validation cohort, the combined models based on the LR, SVM, KNN, and NN classifiers had AUCs of 0.746, 0.754, 0.669, and 0.711, respectively. However, the AUCs of these combined models had no significant differences (all P > 0.05). Calibration curves and DCA indicated that the nomogram have potential clinical utility.

CONCLUSIONS

The combined model may have potential for better prediction of PTC recurrence than radiomics and clinical models alone. Further testing with larger cohort may help reach statistical significance.

CT Radiomics-Based Nomogram for Predicting the Lateral Neck Lymph Node Metastasis in Papillary Thyroid Carcinoma: A Prospective Multicenter Study

RATIONALE AND OBJECTIVES

This study is based on multicenter cohorts and aims to utilize computed tomography (CT) images to construct a radiomics nomogram for predicting the lateral neck lymph node (LNLN) metastasis in the papillary thyroid carcinoma (PTC) and further explore the biological basis under its prediction.

MATERIALS AND METHODS

In the multicenter study, 1213 lymph nodes from 409 patients with PTC who underwent CT examinations and received open surgery and lateral neck dissection were included. A prospective test cohort was used in validating the model. Radiomics features were extracted from the CT images of each patient's LNLNs. Selectkbest, maximum relevance and minimum redundancy and the least absolute shrinkage and selection operator (LASSO) algorithm were used in reducing the dimensionality of radiomics features in the training cohort. Then, a radiomics signature (Rad-score) was calculated as the sum of each feature multiplied by the nonzero coefficient from LASSO. A nomogram was generated using the clinical risk factors of the patients and Rad-score. The nomograms' performance was analyzed in terms of accuracy, sensitivity, specificity, confusion matrix, receiver operating characteristic curves, and areas under the receiver operating characteristic curve (AUCs). The clinical usefulness of the nomogram was evaluated by decision curve analysis. Moreover, three radiologists with different working experiences and nomogram were compared to one another. Whole transcriptomics sequencing was performed in 14 tumor samples; the correlation of biological functions and high and low LNLN samples predicted by the nomogram was further investigated.

RESULTS

A total of 29 radiomics features were used in constructing the Rad-score. Rad-score and clinical risk factors (age, tumor diameter, location and number of suspected tumors) compose the nomogram. The nomogram exhibited good discrimination performance of the nomogram for predicting LNLN metastasis in the training cohort (AUC, 0.866), internal test cohort (0.845), external test cohort (0.725), and prospective test cohort (0.808) and showed diagnostic capability comparable to senior radiologists, significantly outperforming junior radiologists (p < 0.05). Functional enrichment analysis suggested that the nomogram can reflect the ribosome-related structures of cytoplasmic translation in patients with PTC.

CONCLUSION

Our radiomics nomogram provides a noninvasive method that incorporates radiomics features and clinical risk factors for predicting LNLN metastasis in patients with PTC.

Ultrasound-guided thermal ablation for papillary thyroid microcarcinoma: the devil is in the details

Thermal ablation (TA) has harvested favorable outcomes in treating low-risk papillary thyroid microcarcinoma (PTMC). Preoperative assessment, intraoperative procedures and postoperative follow-up are all closely linked with the success and safety of TA on PTMC. However, many details in these aspects have not been systematically reviewed. This review firstly described the influence of preoperative assessment, especially for the risk of lymph node metastasis (LNM), as well as the molecular testing on the selection of TA for PTMC. Besides, we also summarized the experiences in treating special PTMC cases by TA, like multifocal lesions, PTMC located in the isthmus or adjacent to the dorsal capsule. At last, we discussed the follow-up strategies, the influence of the thyroid-stimulating hormone (TSH) level on the prognosis of PTMCs, and the management for recurrent cases. In conclusion, the procedures during the entire perioperative period should be standardized to improve the outcomes of TA in treating PTMC patients.

Safety and efficacy of microwave ablation for the treatment of low-risk papillary thyroid microcarcinoma: a prospective multicenter study

OBJECTIVES

To assess the safety and efficacy of ultrasound-guided thermal ablation for low-risk papillary thyroid microcarcinoma (PTMC) via a prospective multicenter study.

METHODS

From January 2017 through June 2021, low-risk PTMC patients were screened. The management details of active surveillance (AS), surgery, and thermal ablation were discussed. Among patients who accepted thermal ablation, microwave ablation (MWA) was performed. The main outcome was disease-free survival (DFS). The secondary outcomes were tumor size and volume changes, local tumor progression (LTP), lymph node metastasis (LNM), and complication rate.

RESULTS

A total of 1278 patients were included in the study. The operation time of ablation was 30.21 ± 5.14 min with local anesthesia. The mean follow-up time was 34.57 ± 28.98 months. Six patients exhibited LTP at 36 months, of whom 5 patients underwent a second ablation, and 1 patient received surgery. The central LNM rate was 0.39% at 6 months, 0.63% at 12 months, and 0.78% at 36 months. Of the 10 patients with central LNM at 36 months, 5 patients chose ablation, 3 patients chose surgery and the other 2 patients chose AS. The overall complication rate was 1.41%, and 1.10% of patients developed hoarseness of the voice. All of the patients recovered within 6 months.

CONCLUSIONS

Thermal ablation of low-risk PTMC was observed to be safe and efficacious with few minor complications. This technique may help to bridge the gap between surgery and AS as treatment options for patients wishing to have their PTMC managed in a minimally invasive manner.

CLINICAL RELEVANCE STATEMENT

This study proved that microwave ablation is a safe and effective treatment method for papillary thyroid microcarcinoma.

KEY POINTS

Percutaneous US-guided microwave ablation of papillary thyroid microcarcinoma is a very minimally invasive treatment under local anesthesia during a short time period. The local tumor progression and complication rate of microwave ablation in the treatment of papillary thyroid microcarcinoma are very low.

Role of computed tomography in the evaluation of regional metastasis in well-differentiated thyroid cancer

Background

Accurate neck staging is essential for performing appropriate surgery and avoiding undue morbidity in thyroid cancer. The modality of choice for evaluation is ultrasonography (US), which has limitations, particularly in the central compartment, that can be overcome by adding a computed tomography (CT).

Methods

A total of 314 nodal levels were analyzed in 43 patients with CT, and US; evaluations were done between January 2013 and November 2015. The images were reviewed by two radiologists independently who were blinded to histopathological outcomes. The sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), and accuracy of US, CT, and US + CT were calculated using histology as the gold standard.

Results

The overall sensitivity, specificity, PPV, and NPV for US, CT, and US + CT were 53.9%, 88.8%, 74.1%, and 76.4%; 81.2%, 68.0%, 60.1%, and 85.9%; and 84.6%, 66.0%, 59.6%, and 87.8%, respectively. The overall accuracy of the US was 75.80%, the CT scan was 72.93%, and the US + CT scan was 72.93%. For the lateral compartment, the sensitivity, specificity, PPV, and NPV for the US, CT, and US + CT were 56.6%, 91.4%, 77.1%, and 80.5%; 80.7%, 70.6%, 58.3%, and 87.8%; and 84.3%, 68.7%, 57.9%, and 89.6%, respectively. The accuracy of the US was 79.67%, the CT scan was 73.98%, and the US + CT scan was 73.98% for the lateral compartment. For the central compartment, the sensitivity, specificity, PPV, and NPV for the US, CT, and US + CT were 47.1%, 76.5%, 66.7%, and 59.1%; 82.4%, 55.9%, 65.1%, and 76.0%; and 85.3%, 52.9%, 64.4%, and 78.3%, respectively. The accuracy of the US was 61.76%, the CT scan was 69.12%, and the US + CT scan was 69.12% for the central compartment.

Conclusions

This study demonstrated that CT has higher sensitivity in detecting nodal metastasis; however, its role is complementary to US due to low specificity.

Artificial intelligence-based prediction of cervical lymph node metastasis in papillary thyroid cancer with CT

OBJECTIVES

To develop an artificial intelligence (AI) system for predicting cervical lymph node metastasis (CLNM) preoperatively in patients with papillary thyroid cancer (PTC) based on CT images.

METHODS

This multicenter retrospective study included the preoperative CT of PTC patients who were divided into the development, internal, and external test sets. The region of interest of the primary tumor was outlined manually on the CT images by a radiologist who has eight years of experience. With the use of the CT images and lesions masks, the deep learning (DL) signature was developed by the DenseNet combined with convolutional block attention module. One-way analysis of variance and least absolute shrinkage and selection operator were used to select features, and a support vector machine was used to construct the radiomics signature. Random forest was used to combine the DL, radiomics, and clinical signature to perform the final prediction. The receiver operating characteristic curve, sensitivity, specificity, and accuracy were used by two radiologists (R1 and R2) to evaluate and compare the AI system.

RESULTS

For the internal and external test set, the AI system achieved excellent performance with AUCs of 0.84 and 0.81, higher than the DL (p = .03, .82), radiomics (p < .001, .04), and clinical model (p < .001, .006). With the aid of the AI system, the specificities of radiologists were improved by 9% and 15% for R1 and 13% and 9% for R2, respectively.

CONCLUSIONS

The AI system can help predict CLNM in patients with PTC, and the radiologists' performance improved with AI assistance.

CLINICAL RELEVANCE STATEMENT

This study developed an AI system for preoperative prediction of CLNM in PTC patients based on CT images, and the radiologists' performance improved with AI assistance, which could improve the effectiveness of individual clinical decision-making.

KEY POINTS

• This multicenter retrospective study showed that the preoperative CT image-based AI system has the potential for predicting the CLNM of PTC. • The AI system was superior to the radiomics and clinical model in predicting the CLNM of PTC. • The radiologists' diagnostic performance improved when they received the AI system assistance.

Deep learning prediction model for central lymph node metastasis in papillary thyroid microcarcinoma based on cytology

Controversy exists regarding whether patients with low-risk papillary thyroid microcarcinoma (PTMC) should undergo surgery or active surveillance; the inaccuracy of the preoperative clinical lymph node status assessment is one of the primary factors contributing to the controversy. It is imperative to accurately predict the lymph node status of PTMC before surgery. We selected 208 preoperative fine-needle aspiration (FNA) liquid-based preparations of PTMC as our research objects; all of these instances underwent lymph node dissection and, aside from lymph node status, were consistent with low-risk PTMC. We separated them into two groups according to whether the postoperative pathology showed central lymph node metastases. The deep learning model was expected to predict, based on the preoperative thyroid FNA liquid-based preparation, whether PTMC was accompanied by central lymph node metastases. Our deep learning model attained a sensitivity, specificity, positive prediction value (PPV), negative prediction value (NPV), and accuracy of 78.9% (15/19), 73.9% (17/23), 71.4% (15/21), 81.0% (17/21), and 76.2% (32/42), respectively. The area under the receiver operating characteristic curve (value was 0.8503. The predictive performance of the deep learning model was superior to that of the traditional clinical evaluation, and further analysis revealed the cell morphologies that played key roles in model prediction. Our study suggests that the deep learning model based on preoperative thyroid FNA liquid-based preparation is a reliable strategy for predicting central lymph node metastases in thyroid micropapillary carcinoma, and its performance surpasses that of traditional clinical examination.

A combination of computed tomography scan and ultrasound provides optimal detection of cervical lymph node metastasis in papillary thyroid carcinomas: A systematic review and meta-analysis

BACKGROUND

Lymph node metastasis (LNM) in patients with papillary thyroid carcinoma (PTC) is common. This meta-analysis assesses the diagnostic accuracy of computed tomography (CT), ultrasound (US), and CT + US in detecting central and lateral LNM.

METHODS

A systematic review and meta-analysis was performed by searching PubMed, Embase, and Cochrane for studies published up to April 2022. The pooled sensitivity, specificity, and diagnostic odds ratio (DOR) were calculated. The area under the curve (AUC) for summary receiver operating curves (sROC) were compared.

RESULTS

The study population included 7902 patients with a total of 15 014 lymph nodes. Twenty-four studies analyzed the sensitivity of the overall neck region in which dual CT + US imaging (55.9%) had greater sensitivities (p < 0.001) than either US (48.4%) or CT (50.4%) alone. The specificity of US alone (89.0%) was greater (p < 0.001) than CT alone (88.5%) or dual imaging (86.8%). The DOR for dual CT + US imaging was greatest (p < 0.001) at 11.134, while the AUCs of the three imaging modalities were similar (p > 0.05). Twenty-one studies analyzed the sensitivity of the central neck region in which both CT (45.8%) and CT + US imaging (43.4%) had greater sensitivities (p < 0.001) than US alone (35.3%). The specificity of all three modalities was higher than 85%. The DOR for CT (7.985) was greater than US alone (4.723, p < 0.001) or dual CT + US imaging (4.907, p = 0.015). The AUC of both CT + US (0.785) and CT alone (0.785) were significantly greater (p < 0.001) than US alone (0.685). Of the 19 studies that reported lateral LNM, CT + US imaging sensitivity (84.5%) was higher than CT alone (69.2%, p < 0.001) and US alone (79.7%, p = 0.038). The specificity of all imaging techniques was all greater than 80.0%. CT + US imaging DOR (35.573) was greater than CT (20.959, p = 0.024) and US (15.181, p < 0.001) individually. The AUC of independent imaging was high (CT: 0.863, US: 0.858) and improved significantly when combined (CT + US: 0.919, p = 0.024 and p < 0.001, respectively).

CONCLUSIONS

We report an up-to-date analysis elucidating the diagnostic accuracy of LNM detection by either CT, US, or in combination. Our work suggests dual CT + US to be the best for overall detection of LNM and CT to be preferable in detecting central LNM. The use of either CT or US alone may detect lateral LNM with acceptable accuracy, yet dual imaging (CT + US) significantly improved detection rates.

Comparison of health-related quality of life and cosmetic outcome between traditional gasless trans-axillary endoscopic thyroidectomy and modified gasless trans-axillary endoscopic thyroidectomy for patients with papillary thyroid microcarcinoma

BACKGROUND

Gasless trans-axillary endoscopic thyroidectomy (GTET) has been proved to provide better cosmetic results; however, it has limitations as dissection of central neck lymph nodes is difficult. We developed a modified approach (MGTET-modified GTET) and compared it with the traditional one in terms of patients' health-related quality of life (HRQoL) and cosmetic results in order to provide more convincing therapeutic results.

METHODS

Between January 2021 and June 2021, 100 cN0 patients who had a confirmed diagnosis of papillary thyroid microcarcinoma were randomized to undergo either MGTET (n = 50) or GTET (n = 50). These two groups' baseline characteristics, intraoperative and postoperative findings, were compared. The Patient and Observer Scar Assessment Scale (POSAS) was determined 6 months after surgery. Thyroid Cancer-Specific Quality of Life Questionnaire was used to assess HRQoL at 1, 3, 6, and 12 months after surgery.

RESULTS

M-GTET was associated with a larger number of lymph nodes dissected (p < 0.001), lower drainage volume (p < 0.001), shorter hospital stay (p < 0.001), and shorter axillary incision (p < 0.001). POSAS was more favorable in M-GTET. HRQoL was significantly better for MGTET in terms of less problems with scar (p < 0.001).

CONCLUSION

Our study suggests that MGTET provides better therapeutic, cosmetic, and HRQoL outcomes.

Deep learning to predict cervical lymph node metastasis from intraoperative frozen section of tumour in papillary thyroid carcinoma: a multicentre diagnostic study

Background

Lymph node metastasis (LNM) assessment in patients with papillary thyroid carcinoma (PTC) is of great value. This study aimed to develop a deep learning model applied to intraoperative frozen section for prediction of LNM in PTC patients.

Methods

We established a deep-learning model (ThyNet-LNM) with the multiple-instance learning framework to predict LNM using whole slide images (WSIs) from intraoperative frozen sections of PTC. Data for the development and validation of ThyNet-LNM were retrospectively derived from four hospitals from January 2018 to December 2021. The ThyNet-LNM was trained using 1987 WSIs from 1120 patients obtained at the First Affiliated Hospital of Sun Yat-sen University. The ThyNet-LNM was then validated in the independent internal test set (479 WSIs from 280 patients) as well as three external test sets (1335 WSIs from 692 patients). The performance of ThyNet-LNM was further compared with preoperative ultrasound and computed tomography (CT).

Findings

The area under the receiver operating characteristic curves (AUCs) of ThyNet-LNM were 0.80 (95% CI 0.74-0.84), 0.81 (95% CI 0.77-0.86), 0.76 (95% CI 0.68-0.83), and 0.81 (95% CI 0.75-0.85) in internal test set and three external test sets, respectively. The AUCs of ThyNet-LNM were significantly higher than those of ultrasound and CT or their combination in all four test sets (all P < 0.01). Of 397 clinically node-negative (cN0) patients, the rate of unnecessary lymph node dissection decreased from 56.4% to 14.9% by ThyNet-LNM.

Interpretation

The ThyNet-LNM showed promising efficacy as a potential novel method in evaluating intraoperative LNM status, providing real-time guidance for decision. Furthermore, this led to a reduction of unnecessary lymph node dissection in cN0 patients.

Funding

National Natural Science Foundation of China, Guangzhou Science and Technology Project, and Guangxi Medical High-level Key Talents Training "139" Program.

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.

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.

Correlation between Sonographic Features and Central Neck Lymph Node Metastasis in Solitary Solid Papillary Thyroid Microcarcinoma with a Taller-Than-Wide Shape

Purpose: This study aimed to investigate the correlation between sonographic features and central neck lymph node metastasis (CNLM) in solitary solid papillary thyroid microcarcinoma (PTMC) with a taller-than-wide shape. Methods: A total of 103 patients with solitary solid PTMC with a taller-than-wide shape on ultrasonography who underwent surgical histopathological examination were retrospectively selected. Based on the presence or absence of CNLM, patients with PTMC were divided into a CNLM (n = 45) or nonmetastatic (n = 58) group, respectively. Clinical findings and ultrasonographic features, including a suspicious thyroid capsule involvement sign (STCS, which is defined as PTMC abutment or a disrupted thyroid capsule), were compared between the two groups. Additionally, postoperative ultrasonography was performed to assess patients during the follow-up period. Results: Significant differences were observed in sex and the presence of STCS between the two groups (p < 0.05). The specificity and accuracy of the male sex for predicting CNLM were 86.21% (50/58 patients) and 64.08% (66/103 patients), respectively. The sensitivity, specificity, positive predictive value (PPV), and accuracy of STCS for predicting CNLM were 82.22% (37/45 patients), 70.69% (41/58 patients), 68.52% (37/54 patients), and 75.73% (78/103 patients), respectively. The specificity, PPV, and accuracy of the combination of sex and STCS for predicting CNLM were 96.55% (56/58 patients), 87.50% (14/16 patients), and 67.96% (70/103 patients), respectively. A total of 89 (86.4%) patients were followed up for a median of 4.6 years, with no patient having recurrence as detected on ultrasonography and pathological examination. Conclusions: STCS is a useful ultrasonographic feature for predicting CNLM in patients with solitary solid PTMC with a taller-than-wide shape, especially in male patients. Solitary solid PTMC with a taller-than-wide shape may have a good prognosis.

Deep learning-based multifeature integration robustly predicts central lymph node metastasis in papillary thyroid cancer

BACKGROUND

Few highly accurate tests can diagnose central lymph node metastasis (CLNM) of papillary thyroid cancer (PTC). Genetic sequencing of tumor tissue has allowed the targeting of certain genetic variants for personalized cancer therapy development.

METHODS

This study included 488 patients diagnosed with PTC by ultrasound-guided fine-needle aspiration biopsy, collected clinicopathological data, analyzed the correlation between CLNM and clinicopathological features using univariate analysis and binary logistic regression, and constructed prediction models.

RESULTS

Binary logistic regression analysis showed that age, maximum diameter of thyroid nodules, capsular invasion, and BRAF V600E gene mutation were independent risk factors for CLNM, and statistically significant indicators were included to construct a nomogram prediction model, which had an area under the curve (AUC) of 0.778. A convolutional neural network (CNN) prediction model built with an artificial intelligence (AI) deep learning algorithm achieved AUCs of 0.89 in the training set and 0.78 in the test set, which indicated a high prediction efficacy for CLNM. In addition, the prediction models were validated in the subclinical metastasis and clinical metastasis groups with high sensitivity and specificity, suggesting the broad applicability of the models. Furthermore, CNN prediction models were constructed for patients with nodule diameters less than 1 cm. The AUCs in the training set and test set were 0.87 and 0.76, respectively, indicating high prediction efficacy.

CONCLUSIONS

The deep learning-based multifeature integration prediction model provides a reference for the clinical diagnosis and treatment of PTC.

Preoperative strain ultrasound elastography can predict occult central cervical lymph node metastasis in papillary thyroid cancer: a single-center retrospective study

Objective

To determine whether preoperative ultrasound elastography can predict occult central cervical lymph node metastasis (CCLNM) in patients with papillary thyroid cancer.

Methods

This retrospective study included 541 papillary thyroid cancer patients with clinically negative lymph nodes prior to surgery between July 2019 and December 2021. Based on whether CCLNM was present on postoperative pathology, patients were categorized as CCLNM (+) or CCLNM (-). Preoperative clinical data, conventional ultrasound features, and ultrasound elastography indices were compared between the groups. Univariate and multivariate logistic regression analysis were performed to identify the independent predictors of occult CCLNM.

Results

A total of 36.60% (198/541) patients had confirmed CCLNM, while 63.40% (343/541) did not. Tumor location, bilaterality, multifocality, echogenicity, margin, shape, vascularity, capsule contact, extrathyroidal extension, aspect ratio, and shear wave elasticity parameters were comparable between the groups (all P > 0.05). Univariate analysis showed statistically significant differences between the two groups in age, sex, tumor size, calcification, capsule invasion, and strain rates ratio in strain ultrasound elastography (all P < 0.05). In multivariate logistic regression analysis, the independent predictors of occult CCLNM were age (OR = 0.975, 95% CI = 0.959-0.991, P = 0.002), sex (OR = 1.886, 95% CI = 1.220-2.915, P = 0.004), tumor size (OR = 1.054, 95% CI = 1.014-1.097, P = 0.008), and strain rates ratio (OR = 1.178, 95% CI = 1.065-1.304, P = 0.002).

Conclusion

Preoperative strain ultrasound elastography can predict presence of occult CCLNM in papillary thyroid cancer patients and help clinicians select the appropriate treatment strategy.

Radiologist versus Non-Radiologist Detection of Lymph Node Metastasis in Papillary Thyroid Carcinoma by Ultrasound: A Meta-Analysis

Papillary thyroid carcinoma (PTC) is the most common thyroid cancer worldwide and is known to spread to adjacent neck lymphatics. Lymph node metastasis (LNM) is a known predictor of disease recurrence and is an indicator for aggressive resection. Our study aims to determine if ultrasound sonographers’ degree of training influences overall LNM detection. PubMed, Embase, and Scopus articles were searched and screened for relevant articles. Two investigators independently screened and extracted the data. Diagnostic test parameters were determined for all studies, studies reported by radiologists, and studies reported by non-radiologists. The total sample size amounted to 5768 patients and 10,030 lymph nodes. Radiologists performed ultrasounds in 18 studies, while non-radiologists performed ultrasounds in seven studies, corresponding to 4442 and 1326 patients, respectively. The overall sensitivity of LNM detection by US was 59% (95%CI = 58–60%), and the overall specificity was 85% (95%CI = 84–86%). The sensitivity and specificity of US performed by radiologists were 58% and 86%, respectively. The sensitivity and specificity of US performed by non-radiologists were 62% and 78%, respectively. Summary receiver operating curve (sROC) found radiologists and non-radiologists to detect LNM on US with similar accuracy (p = 0.517). Our work suggests that both radiologists and non-radiologists alike detect overall LNM with high accuracy on US.

A Combination of Contrast-Enhanced Ultrasound and Thyroglobulin Level in Fine-Needle Aspirates Improves Diagnostic Accuracy for Metastatic Lymph Nodes of Papillary Thyroid Carcinoma

OBJECTIVE

To evaluate the diagnostic performance of contrast-enhanced ultrasound (CEUS) combined with thyroglobulin (Tg) levels in fine-needle aspirates (FNA) washout fluid (FNA-Tg) in diagnosing cervical lymph node (LN) metastasis in papillary thyroid cancer (PTC) patients.

METHODS

Data from 190 LNs in 167 patients suspected of metastasis from the US between November 2018 and September 2020 were included. All subjects underwent FNA, CEUS, and FNA-Tg examinations. The final outcomes were confirmed by histopathological or cytological examination or follow-up imaging. Data were analyzed using the Wilcoxon rank-sum or chi-squared test. The diagnostic efficacy of FNA, CEUS, and FNA-Tg in diagnosing LNs was compared.

RESULTS

A cutoff value of 6.15 ng/ml (AUC 0.925, 95% confidence interval (CI) 0.885-0.966) successfully identified metastatic LNs. FNA missed 58 LN metastases, of these, 94.8% (55/58) were correctly diagnosed using the combination of CEUS and FNA-Tg. FNA-Tg showed higher sensitivity (90.2%), NPV (86.1%) and accuracy (88.9%) than either FNA (48.2, 57.4 and 69.5%, respectively) or CEUS (82.1, 67.7 and 70.5%, respectively) alone. The combination of CEUS, FNA and FNA-Tg resulted in maximal sensitivity (100%) and NPV (100%) but reduced specificity (51.3%) and overall diagnostic accuracy (80.0%). After adding FNA-Tg to discordant samples between CEUS and FNA, 81.9% of LNs (77/94) were correctly diagnosed.

CONCLUSIONS

The combination of FNA, FNA-Tg and CEUS was found to be a promising imaging tool in detecting metastatic LNs in PTC patients.

Ultrasonographic features of cervical lymph node metastases from medullary thyroid cancer: a retrospective study

Background

To investigate sonographic features of cervical lymph node metastases from medullary thyroid cancer (LNM-MTC), as compared with lymph node metastases from papillary thyroid cancer (LNM-PTC).

Methods

A total of 42 MTC patients with 52 metastatic LNs and 222 PTC patients with 234 metastatic LNs who were confirmed by fine needle aspiration and post-operative pathology, were enrolled in this study. The clinical characteristics and sonographic features of LNs were compared between the two groups. Univariate analysis and multivariate logistic regression analysis were performed on the sonographic features of LNs, including short and long-axis diameter, long-axis diameter/short-axis, shape, border, hilum, echogenicity, calcifications, cystic change and vascularity pattern. The discriminating performance was assessed with the area under the receiver operating characteristic curve (AUC).

Results

The mean age of patients with LNM-MTC was older than that of patients with LNM-PTC (46.81 ± 13.05 vs 39.09 ± 12.05, P < 0.001). No differences were observed in gender, location, long-axis diameter/short-axis, shape, border, echogenicity, cystic change and vascularity pattern between LNM-MTC and LNM-PTC groups (P > 0.05, for all). However, long-axis and short-axis diameter, hilum and calcifications were statistically different between these two groups (P < 0.05, for all). The AUC of discriminate value between LNM-MTC and LNM-PTC was 0.808 (95% confidence interval 0.739–0.877).

Conclusion

Compared with LNM-PTC, LNM-MTC tended to have the sonographic characteristics of larger size, absence of hilum, and less calcifications, and awareness of these features might be helpful to in the diagnosis of LNM-MTC.

Analysis of the Application Value of Ultrasound Imaging Diagnosis in the Clinical Staging of Thyroid Cancer

Thyroid cancer affects 1.3 percent of the population, with rates of occurrence rising in recent years (approximately 2 percent per year). Thyroid cancer is a common endocrine cancer with an annual increase in occurrence. Although the general prognosis for differentiated subtypes is favorable, the rate of mortality linked with thyroid cancer has been steadily progressing. The presence of suspicious thyroid nodules necessitates more diagnostic testing, including laboratory evaluation, additional imaging, and biopsy. For clinical staging and appropriate patient therapy design, accurate diagnosis is necessary. In this paper, we examined the application value of ultrasound imaging diagnosis in the clinical staging of thyroid tumor in this research. The benefit of early diagnosis is determined in this article using ultrasonography reports from Chinese patients. Images of benign and malignant thyroid nodules were collected and annotated in this work, and deep learning-based image recognition and diagnostic system was built utilizing the adaptive wavelet transform-based AdaBoost algorithm (AWT-AA). The system's efficacy in diagnosing thyroid nodules was assessed, and the use of ultrasound imaging in clinical practice was studied. The variables that had a significant impact on malignant nodules were studied using logistic multiple regression analysis. The sensitivity and specificity of ultrasonography thyroid imaging reporting and data system (TI-RADS) categorization outcomes for benign and malignant tumors were also calculated.

A novel tool for predicting the risk of central lymph node metastasis in patients with papillary thyroid microcarcinoma: a retrospective cohort study

Introduction

Central lymph node status in papillary thyroid microcarcinoma (PTMC) plays an important role in treatment decision-making clinically, however, it is not easy to predict central lymph node metastasis (CLNM). The present work focused on finding the more rational alternative for evaluating central lymph node status while identifying influencing factors to construct a model to predict CLNM incidence.

Methods

In this study, we retrospectively analyzed the typical sonographic and clinicopathologic features of 546 PTMC patients who underwent surgery, among which, the data of 382 patients were recruited in the training cohort and that of 164 patients in the validation cohort. Based on the outcome of the training cohort, significant influencing factors were further identified through univariate analysis and were considered as independent variables in multivariable logistic regression analysis and incorporated in and presented with a nomogram.

Results

In total, six independent predictors, including the age, sex, tumor size, multifocality, capsular invasion, Hashimotos thyroiditis were entered into the nomogram. Both internal validation and external validation revealed the favorable discrimination of our as-constructed nomogram. Calibration curves exhibited high consistency. As suggested by decision-curve analyses, the as-constructed nomogram might be applied in clinic. Besides, the model also distinguished patients according to risk stratification.

Conclusions

The novel nomogram containing remarkable influencing factors for CLNM cases was established in the present work. The nomogram can assist clinicians in clinical decision-making.

Development and validation of a nomogram for prediction of cervical lymph node metastasis in middle and lower thoracic esophageal squamous cell carcinoma

Background

Estimates of cervical lymph node (LN) metastasis in patients with middle and lower thoracic esophageal squamous cell carcinoma (ESCC) are important. A nomogram is a useful tool for individualized prediction.

Methods

A total of 235 patients were enrolled in this study. Univariate and multivariate analyses were performed to screen for independent risk factors and construct a nomogram to predict the risk of cervical LN metastasis. The nomogram performance was assessed by discrimination, calibration, and clinical use.

Results

Totally, four independent predictors, including the maximum diameter of tumor, paraesophageal lymph node status, recurrent laryngeal nerve lymph node status, and the CT-reported cervical LN status, were enrolled in the nomogram. The AUC of the nomogram model in the training and validation dataset were 0.833 (95% CI 0.762–0.905), 0.808 (95% CI 0.696–0.920), respectively. The calibration curve demonstrated a strong consistency between nomogram and clinical findings in predicting cervical LN metastasis. Decision curve analysis demonstrated that the nomogram was clinically useful.

Conclusion

We developed a nomogram that could be conveniently used to predict the individualized risk of cervical LN metastasis in patients with middle and lower thoracic ESCC.

Preoperative Prediction of Central Cervical Lymph Node Metastasis in Fine-Needle Aspiration Reporting Suspicious Papillary Thyroid Cancer or Papillary Thyroid Cancer Without Lateral Neck Metastasis

Purpose

No non-invasive method can accurately determine the presence of central cervical lymph node (CCLN) metastasis in papillary thyroid cancer (PTC) until now. This study aimed to investigate factors significantly associated with CCLN metastasis and then develop a model to preoperatively predict CCLN metastasis in fine-needle aspiration (FNA) reporting suspicious papillary thyroid cancer (PTC) or PTC without lateral neck metastasis.

Patients and Methods

Consecutive inpatients who were diagnosed as suspicious PTC or PTC in FNA and underwent partial or total thyroidectomy and CCLN dissection between May 1^st, 2016 and June 30^th, 2018 were included. The total eligible patients were randomly divided into a training set and an internal validation set with the ratio of 7:3. Univariate analysis and multivariate analysis were conducted in the training set to investigate factors associated with CCLN metastasis. The predicting model was built with factors significantly correlated with CCLN metastasis and validated in the validation set.

Results

A total of 770 patients were eligible in this study. Among them, 268 patients had histologically confirmed CCLN metastasis, while the remaining patients did not. Factors including age, BRAF mutation, multifocality, size, and capsule involvement were found to be significantly correlated with the CCLN metastasis in univariate and multivariate analysis. A model used to predict the presence CCLN metastasis based on these factors and US CCLN status yielded AUC, sensitivity, specificity and accuracy of 0.933 (95%CI: 0.905-0.960, p < 0.001), 0.816, 0.966 and 0.914 in the training set and 0.967 (95%CI: 0.943-0.991, p < 0.001), 0.897, 0.959 and 0.936 in the internal validation set.

Conclusion

Age, BRAF mutation, multifocality, size, and capsule involvement were independent predictors of CCLN metastasis in FNA reporting suspicious PTC or PTC without lateral neck metastasis. A simple model was successfully built and showed excellent discrimination to distinguish patients with or without CCLN metastasis.

Cervical lymph node metastases in papillary thyroid cancer: Preoperative staging with ultrasound and/or computed tomography

Preoperative screening of potential risk of lymph node metastasis is necessary for thyroidectomy plus lymph node dissection. The 2015 American thyroid association management guidelines do not recommend prophylactic cervical lymph node resection without clinical evidence of metastasis. Ultrasound is recommended imaging method and routine computed tomography is not recommended by the 2015 American thyroid association management guidelines for screening of lymph node metastasis. The objective of the study was to compare the diagnostic performance of ultrasound against that of computed tomography for screening cervical lymph node metastasis of patients with papillary thyroid cancer before thyroidectomy plus lymph node dissection.Data regarding preoperative neck ultrasound, neck computed tomography, and physical examination of the head and neck and postoperative pathological results of a total of 185 patients (age > 18 years) with a diagnosis of papillary thyroid cancer who had suspicious lymph nodes on preoperative imaging and treated by thyroidectomy plus lymph node dissection for the therapeutic purpose were collected and analyzed.Sensitivity (78.09% vs 75.28%, P < .0001) and accuracy (77.29% vs 75.13%, P = .0004) of neck computed tomography scanning to detect cervical lymph node metastasis were higher than those of neck ultrasound scanning. Sensitivity, accuracy, positive clinical utility, and negative clinical utility for neck ultrasound scanning plus neck computed tomography scanning to detect cervical lymph node metastasis were higher among all index tests (P < .05 for all) and were statistically the same as those of surgical pathology (P > .05 for all). The working areas for decision-making of thyroidectomy plus lymph node dissection of the physical examination, neck ultrasound, the neck computed tomography, and the neck ultrasound scanning plus the neck computed tomography scanning were 0 to 0.691 diagnostic confidence/lesion, 0 to 0.961 diagnostic confidence/lesion, 0 to 0.944 diagnostic confidence/lesion, and 0 to 0.981 diagnostic confidence/lesion, respectively.Besides the neck ultrasound, the neck computed tomography scanning can be used as a complementary imaging method to detect cervical lymph node metastasis of patients with papillary thyroid cancer before thyroidectomy plus lymph node dissection.Level of evidence: III.Technical efficacy stage: 2.

A Proposed Heterogeneous Ensemble Algorithm Model for Predicting Central Lymph Node Metastasis in Papillary Thyroid Cancer

Purpose

To develop a heterogeneous ensemble algorithm model to precisely predict central lymph node metastasis (CLNM), which can provide a reference value on controversial topics of performing prophylactic central lymph node dissection for patients with papillary thyroid cancer (PTC).

Methods

The study included patients with PTC who underwent an initial thyroid resection in a single-center medical institution between January 2014 and December 2018. A total of 18 variables, including clinical features and ultrasound (US) features, were used in the univariate analysis, multivariate analysis, and feature selection and were also used to develop a heterogeneous ensemble model based on five basic machine learning models, including extreme gradient boosting, k-nearest neighbors, random forest, gradient boosting, and AdaBoost. Moreover, a partial dependent plot was used to explain the heterogeneous ensemble model.

Results

The area under the receiver operating characteristic curve of the heterogeneous ensemble algorithm model was 0.67, which is significantly better than that of the basic machine models in predicting CLNM. All machine learning models performed better than US. Based on multivariate analysis and receiver operating characteristic curve analysis, age ≤33 years, tumor size ≥0.8 cm, US-suspected CLNM, and microcalcification were risk factors for CLNM, and anti-thyroid peroxidase antibody and serum thyroglobulin levels were favorable factors for CLNM.

Conclusion

The proposed heterogeneous ensemble algorithm model may be optimal tool to predict CLNM by integrating clinical and US features.

Risk prediction for central lymph node metastasis in isolated isthmic papillary thyroid carcinoma by nomogram: A retrospective study from 2010 to 2021

BACKGROUND

Isthmic papillary thyroid carcinoma (IPTC) is an aggressive thyroid cancer associated with a poor prognosis. Guidelines elaborating on the extent of surgery for IPTC are yet to be developed. This study aims to construct and validate a model to predict central lymph node metastasis (CLNM) in patients with IPTC, which could be used as a risk stratification tool to determine the best surgical approach for patients.

METHODS

Electronic medical records for patients diagnosed with isolated papillary thyroid carcinoma who underwent surgery at Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, from January 2010 to December 2021 were reviewed. All patients who underwent thyroidectomy with central neck dissection (CND) for isolated IPTC were included. We conducted univariate and multivariate logistic regression analyses to assess risk factors for ipsilateral and contralateral CLNM and the number of CLNM in IPTC patients. Based on the analysis, the nomogram construction and internal validations were performed.

RESULTS

A total of 147 patients with isolated IPTC were included. The occurrence of CLNM was 53.7% in the patients. We identified three predictors of ipsilateral CLNM, including age, gender, and size. For contralateral CLNM, three identified predictors were age, gender, and capsular invasion. Predictors for the number of CLNM included age, gender, capsular invasion, tumor size, and chronic lymphocytic thyroiditis (CLT). The concordance index(C-index) of the models predicting ipsilateral CLNM, contralateral CLNM, 1-4 CLNM, and ≥5 CLNM was 0.779 (95%CI, 0.704, to 0.854), 0.779 (95%CI, 0.703 to 0.855), 0.724 (95%CI, 0.629 to 0.818), and 0.932 (95%CI, 0.884 to 0.980), respectively. The corresponding indices for the internal validation were 0.756 (95%CI, 0.753 to 0.758), 0.753 (95%CI, 0.750 to 0.756), 0.706 (95%CI, 0.702 to 0.708), and 0.920 (95%CI, 0.918 to 0.922). Receiver operating characteristic (ROC) curves, calibration, and decision curve analysis (DCA) results confirmed that the three nomograms could precisely predict CLNM in patients with isolated IPTC.

CONCLUSION

We constructed predictive nomograms for CLNM in IPTC patients. A risk stratification scheme and corresponding surgical treatment recommendations were provided accordingly. Our predictive models can be used as a risk stratification tool to help clinicians make individualized surgical plans for their patients.

A comparative analysis of eight machine learning models for the prediction of lateral lymph node metastasis in patients with papillary thyroid carcinoma

BACKGROUND

Lateral lymph node metastasis (LLNM) is a contributor for poor prognosis in papillary thyroid cancer (PTC). We aimed to develop and validate machine learning (ML) algorithms-based models for predicting the risk of LLNM in these patients.

METHODS

This is retrospective study comprising 1236 patients who underwent initial thyroid resection at our institution between January 2019 and March 2022. All patients were randomly split into the training dataset (70%) and the validation dataset (30%). Eight ML algorithms, including the Logistic Regression, Gradient Boosting Machine, Extreme Gradient Boosting, Random Forest (RF), Decision Tree, Neural Network, Support Vector Machine and Bayesian Network were used to evaluate the risk of LLNM. The performance of ML models was evaluated by the area under curve (AUC), sensitivity, specificity, and decision curve analysis.

RESULTS

Among the eight ML algorithms, RF had the highest AUC (0.975), with sensitivity and specificity of 0.903 and 0.959, respectively. It was therefore used to develop as prediction model. The diagnostic performance of RF algorithm was dependent on the following nine top-rank variables: central lymph node ratio, size, central lymph node metastasis, number of foci, location, body mass index, aspect ratio, sex and extrathyroidal extension.

CONCLUSION

By combining clinical and sonographic characteristics, ML algorithms can achieve acceptable prediction of LLNM, of which the RF model performs best. ML algorithms can help clinicians to identify the risk probability of LLNM in PTC patients.

Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer

OBJECTIVE

To develop a web-based machine learning server to predict lateral lymph node metastasis (LLNM) in papillary thyroid cancer (PTC) patients.

METHODS

Clinical data for PTC patients who underwent primary thyroidectomy at our hospital between January 2015 and December 2020, with pathologically confirmed presence or absence of any LLNM finding, were retrospectively reviewed. We built all models from a training set (80%) and assessed them in a test set (20%), using algorithms including decision tree, XGBoost, random forest, support vector machine, neural network, and K-nearest neighbor algorithm. Their performance was measured against a previously established nomogram using area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), precision, recall, accuracy, F1 score, specificity, and sensitivity. Interpretable machine learning was used for identifying potential relationships between variables and LLNM, and a web-based tool was created for use by clinicians.

RESULTS

A total of 1135 (62.53%) out of 1815 PTC patients enrolled in this study experienced LLNM episodes. In predicting LLNM, the best algorithm was random forest. In determining feature importance, the AUC reached 0.80, with an accuracy of 0.74, sensitivity of 0.89, and F1 score of 0.81. In addition, DCA showed that random forest held a higher clinical net benefit. Random forest identified tumor size, lymph node microcalcification, age, lymph node size, and tumor location as the most influentials in predicting LLNM. And the website tool is freely accessible at http://43.138.62.202/.

CONCLUSION

The results showed that machine learning can be used to enable accurate prediction for LLNM in PTC patients, and that the web tool allowed for LLNM risk assessment at the individual level.

A Preoperative Nomogram for the Prediction of High-Volume Central Lymph Node Metastasis in Papillary Thyroid Carcinoma

Background

High-volume lymph node metastasis (HVLNM, equal to or more than 5 lymph nodes) is one of the adverse features indicating high recurrence risk in papillary thyroid carcinoma (PTC) and is recommended as one of the indications of completion thyroidectomy for patients undergoing thyroid lobectomy at first. In this study, we aim to develop a preoperative nomogram for the prediction of HVLNMs in the central compartment in PTC (cT1-2N0M0), where preoperative imaging techniques perform poor.

Methods

From October 2016 to April 2021, 423 patients were included, who were diagnosed as PTC (cT1-2N0M0) and underwent total thyroidectomy and prophylactic central compartment neck dissection in our center. Demographic and clinicopathological features were recorded and analyzed using univariate and multivariate logistic regression analysis. A nomogram was developed based on multivariate logistic regression analysis.

Results

Among the included patients, 13.4% (57 cases) were found to have HVLNMs in the central compartment. Univariate and multivariate logistic regression analysis showed that age (35 years), BRAF with V600E mutated, nodule diameter, and calcification independently predicted HVLNMs in the central compartment. The nomogram showed good discrimination with an AUC of 0.821 (95% CI, 0.768-0.875).

Conclusion

The preoperative nomogram can be used to quantify the probability of HVLNMs in the central compartment and may reduce the reoperation rate after thyroid lobectomy.

[Establishment of a predictive model for central cervical lymph node metastasis of papillary thyroid carcinoma based on ACR TI-RADS score and evaluation of its diagnostic efficacy]

Objective:To establish a predictive model for central lymph node metastasis（CLNM） of papillary thyroid carcinoma（PTC） based on ACR TI-RADS grades（ATR model） and evaluate its diagnostic efficacy. Methods:A total of 319 patients with PTC diagnosed from January 2019 to May 2020 were included, including 366 nodules were used as the modeling cohort to construct the risk prediction model. A total of 105 PTC patients with 121 nodules from June to August 2020 were included as the external validation cohort. The C-index of the model was calculated and the Hosmer-Lemeshow goodness-of-fit test was performed to compare the diagnostic efficiency of ACR model and those conventional imaging models. Results:The ATR model, Y=-3.719+0.765×gender+1.094×multifocality+0.08×maximum diameter+0.266×ACR TI-RADS score. In the training set, validation set and external validation cohort, the model C-index was 0.758（95%CI: 0.699-0.817）, 0.717（95%CI: 0.619-0.815） and 0.756（95%CI: 0.671-0.840）, respectively. The Hosmer-Lemeshow goodness of fit test showed that the prediction rate of the model was consistent with the actual incidence rate（P=0.918; P=0.581; P=0.366）. With ≥0.434 as the diagnostic threshold, the model had the highest diagnostic efficacy （sensitivity: 86.0%, specificity: 56.3%, Youden index: 0.423）. In the external validation cohort, there was no significant difference between C-US and CT（P>0.05）. Compared with C-US and CT, the sensitivity（66.1% vs 16.1%, P<0.001; 66.1% vs 9.7%, P<0.001） and accuracy（68.6% vs 55.4%, P=0.041; 68.6% vs 52.9%, P=0.012） of ATR model were higher, and the negative predictive value was higher than that of CT（66.7% vs 50.9%, P=0.042）, but there was no difference between ATR model and C-US（66.7% vs 52.3%, P=0.066）; There was no significant difference among the three positive predictive values（70.7% vs 83.3%, P=0.211; 70.7% vs 85.7%, P=0.319）, but the specificity of the model was low （71.2% vs 96.6%, P=0.001; 71.2% vs 98.3%, P<0.001）. Conclusion:The predictive model based on ACR TI-RADS grades can predict CLNM of PTC more accurately and sensitively than traditional imaging examination.

The Prediction of Metastases of Lateral Cervical Lymph Node in Medullary Thyroid Carcinoma

PURPOSE

Development and validation of a nomogram for the prediction of lateral lymph node metastasis (LLNM) in medullary thyroid carcinoma (MTC).

METHODS

We retrospectively reviewed the clinical features of patients with MTC in the Surveillance, Epidemiology, and End Results (SEER) database between 2010 and 2017 and in our Department of Surgical Oncology, Hangzhou First People's Hospital between 2009 and 2019. The log-rank test was used to compare the difference in the Kaplan-Meier (K-M) curves in recurrence and survival. The nomogram was developed to predict the risk of LLNM in MTC patients. The prediction efficiency of the predictive model was assessed by area under the curve (AUC) and concordance index (C-index) and calibration curves. Decision curve analysis (DCA) was performed to determine the clinic value of the predictive model.

RESULT

A total of 714 patients in the SEER database and 35 patients in our department were enrolled in our study. Patients with LLNM had worse recurrence rate and cancer-specific survival (CSS) compared with patients without LLNM. Five clinical characteristics including sex, tumor size, multifocality, extrathyroidal extension, and distant metastasis were identified to be associated with LLNM in MTC patients, which were used to develop a nomogram. Our prediction model had satisfied discrimination with a C-index of 0.825, supported by both training set and internal testing set with a C-index of 0.825, and 0.816, respectively. DCA was further made to evaluate the clinical utility of this nomogram for predicting LLNM.

CONCLUSIONS

Male sex, tumor size >38mm, multifocality, extrathyroidal extension, and distant metastasis in MTC patients were significant risk factors for predicting LLNM.