A Comparative Analysis of Six Machine Learning Models Based on Ultrasound to Distinguish the Possibility of Central Cervical Lymph Node Metastasis in Patients With Papillary Thyroid Carcinoma

Zou, Ying; Shi, Yan; Liu, Jihua; Cui, Guanghe; Liu, Yang; Liu, Meiling; Sun, Fang

doi:10.3389/fonc.2021.656127

Cited by 19 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ultrasound is very sensitive in the evaluation of primary PTC lesions, and clinicians can obtain PTC ultrasound features preoperatively ( 7 ). It has been reported that the ultrasound signs of PTC can be used to predict cervical lymph node metastasis in patients with PTC and provide a basis for the selection of surgical methods ( 10 ), but no similar study has been conducted in LN-prRLN. Therefore, this study aims to provide a theoretical basis for the preoperative clinical evaluation of LN-prRLN metastases by assessing the preoperative ultrasound features of PTC and postoperative pathological data in 482 PTC patients and analyzing the relationship between them to establish a new scoring system for LN-prRLN in patients with PTC.…”

Section: Introductionmentioning

confidence: 99%

A Novel Scoring System for Predicting the Metastases of Posterior Right Recurrent Laryngeal Nerve Lymph Node Involvement in Patients With Papillary Thyroid Carcinoma by Preoperative Ultrasound

Zhou

et al. 2021

Front. Endocrinol.

View full text Add to dashboard Cite

ObjectiveOur goal was to investigate the correlation between papillary thyroid carcinoma (PTC) characteristics on ultrasonography and metastases of lymph nodes posterior to the right recurrent laryngeal nerve (LN-prRLN). There is still no good method for clinicians to judge whether a patient needs LN-prRLN resection before surgery, and we also wanted to establish a new scoring system to determine whether patients with papillary thyroid carcinoma require LN-prRLN resection before surgery.Patients and MethodsThere were 482 patients with right or bilateral PTC who underwent thyroid gland resection from December 2015 to December 2017 recruited as study subjects. The relationship between the PTC characteristics on ultrasonography and the metastases of LN-prRLN was analyzed by univariate and logistic regression analyses. Based on the risk factors identified in univariate and logistic regression analysis, a nomogram-based LN-prRLN prediction model was established.ResultLN-prRLN were removed from all patients, of which 79 had LN-prRLN metastasis, with a metastasis rate of 16.39%. Multivariate logistic regression analysis revealed that LN-prRLN metastasis was closely related to sex, age, blood supply, larger tumors (> 1 cm) and capsular invasion. A risk prediction model has been established and fully verified. The calibration curve used to evaluate the nomogram shows that the consistency index was 0.75 ± 0.065.ConclusionPreoperative clinical data, such as sex, age, abundant blood supply, larger tumor (> 1 cm) and capsular invasion, are positively correlated with LN-prRLN metastasis. Our scoring system can help surgeons non-invasively determine which patients should undergo LN-prRLN resection before surgery. We recommend that LN-prRLN resection should be performed when the score is above 103.1.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Scoring System for Predicting the Metastases of Posterior Right Recurrent Laryngeal Nerve Lymph Node Involvement in Patients With Papillary Thyroid Carcinoma by Preoperative Ultrasound

Zhou

et al. 2021

Front. Endocrinol.

View full text Add to dashboard Cite

show abstract

“…It takes full advantage of high-throughput image features by extracting crucial features out of complex clinical contexts to assist diagnosis and individualized treatment [34]. As for methods to predict CLNM of thyroid cancer, the AUC varied between 0.73 to 0.83 in the previous ML algorithms by clinical and conventional US features [17,18,35]. However, multimodal US information was not enrolled before.…”

Section: Discussionmentioning

confidence: 99%

Application of decision tree algorithms to predict central lymph node metastasis in well-differentiated papillary thyroid carcinoma based on multimodal ultrasound parameters: a retrospective study

Wan

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Prophylactic central neck dissection (pCND) in well-differentiated primary papillary thyroid carcinoma (PTC) patients have become controversial. Several attempts have been made to predict central compartment lymph node metastasis (CLNM) based on clinical and conventional ultrasonic parameters. This study seeks to develop a decision tree (DT) model for predicting the risk of CLNM in these patients based on clinical and preoperative multimodal ultrasound (US) characteristics.Methods: A total of 148 PTC nodules confirmed by surgical pathology at Beijing Tiantan Hospital were retrospectively analyzed. All nodules underwent multimodal US examinations from January 2020 to September 2021 before surgery. Correlation analysis of CLNM with clinical characteristics, multimodal US parameters of PTC lesions based on grayscale US, color Doppler flow imaging, superb microvascular imaging, contrast-enhanced US and shear wave elastography technology was carried out. Finally, the Chi-squared automatic interaction detector with a ten-fold cross test was used to establish DT models based on multimodal US parameters to predict CLNM. The area under the curve (AUC) was calculated for comparing prediction performance.Results: Univariate analysis indicated that CLNM was positively correlated with Tg level, maximum size, tall than wide, the number of microcalcifications greater than or equal to 5, contact capsule, US reported abnormal cervical lymph nodes, non-centripetal perfusion, delayed clearance, SWV mean and SWV ratio (p<0.05). The multimodal US algorithm based on tall than wide, contact the capsule, US reported abnormal cervical lymph nodes, centripetal enhancement as independent variables showed good discrimination: the sensitivity, specificity, accuracy and AUC were 80.0%, 76.7%, 78.4%, and 0.837 (95% CI: 0.771-0.902). There was a significant difference between multimodal US DT with conventional ultrasound DT (p<0.001). Conclusions: This study implies that the DT model based on preoperative multimodal US characteristics of PTCs has reasonable prediction ability for CLNM, which can be conveniently used for clinical decision-making of individualized treatment in well-differentiated PTC patients.

show abstract

“…The AUC of their model for the diagnosis of CLNM in the validation cohort was slightly lower than that of the current study (0.70 vs. 71). Zou et al [ 37 ] used machine learning models based on US data to determine the probability of CLNM. The AUC of their model for the diagnosis of CLNM was slightly higher in the validation cohort compared with the current study (0.73 vs. 0.71).…”

Section: Discussionmentioning

confidence: 99%

Evaluation of Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma Using Clinical-Ultrasound Radiomic Machine Learning-Based Model

Agyekum

Ren

Wang

et al. 2022

Cancers

View full text Add to dashboard Cite

We aim to develop a clinical-ultrasound radiomic (USR) model based on USR features and clinical factors for the evaluation of cervical lymph node metastasis (CLNM) in patients with papillary thyroid carcinoma (PTC). This retrospective study used routine clinical and US data from 205 PTC patients. According to the pathology results, the enrolled patients were divided into a non-CLNM group and a CLNM group. All patients were randomly divided into a training cohort (n = 143) and a validation cohort (n = 62). A total of 1046 USR features of lesion areas were extracted. The features were reduced using Pearson’s Correlation Coefficient (PCC) and Recursive Feature Elimination (RFE) with stratified 15-fold cross-validation. Several machine learning classifiers were employed to build a Clinical model based on clinical variables, a USR model based solely on extracted USR features, and a Clinical-USR model based on the combination of clinical variables and USR features. The Clinical-USR model could discriminate between PTC patients with CLNM and PTC patients without CLNM in the training (AUC, 0.78) and validation cohorts (AUC, 0.71). When compared to the Clinical model, the USR model had higher AUCs in the validation (0.74 vs. 0.63) cohorts. The Clinical-USR model demonstrated higher AUC values in the validation cohort (0.71 vs. 0.63) compared to the Clinical model. The newly developed Clinical-USR model is feasible for predicting CLNM in patients with PTC.

show abstract

A Comparative Analysis of Six Machine Learning Models Based on Ultrasound to Distinguish the Possibility of Central Cervical Lymph Node Metastasis in Patients With Papillary Thyroid Carcinoma

Cited by 19 publications

References 37 publications

A Novel Scoring System for Predicting the Metastases of Posterior Right Recurrent Laryngeal Nerve Lymph Node Involvement in Patients With Papillary Thyroid Carcinoma by Preoperative Ultrasound

A Novel Scoring System for Predicting the Metastases of Posterior Right Recurrent Laryngeal Nerve Lymph Node Involvement in Patients With Papillary Thyroid Carcinoma by Preoperative Ultrasound

Application of decision tree algorithms to predict central lymph node metastasis in well-differentiated papillary thyroid carcinoma based on multimodal ultrasound parameters: a retrospective study

Evaluation of Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma Using Clinical-Ultrasound Radiomic Machine Learning-Based Model

Contact Info

Product

Resources

About