Dataset Information

Ultrasound-based radiomics nomogram combined with clinical features for the prediction of central lymph node metastasis in papillary thyroid carcinoma patients with Hashimoto's thyroiditis.

ABSTRACT:

Background

Hashimoto thyroiditis (HT) is the most common autoimmune thyroid disease and is considered an independent risk factor for papillary thyroid carcinoma (PTC), with a higher incidence of PTC in patients with HT.

Objective

To build an integrated nomogram using clinical information and ultrasound-based radiomics features in patients with papillary thyroid carcinoma (PTC) with Hashimoto thyroiditis (HT) to predict central lymph node metastasis (CLNM).

Methods

In total, 235 patients with PTC with HT were enrolled in this study, including 101 with CLNM and 134 without CLNM. They were divided randomly into training and validation datasets with a 7:3 ratio for developing and evaluating clinical features plus conventional ultrasound features (Clin-CUS) model and clinical features plus radiomics scores (Clin-RS) model, respectively. In the Clin-RS model, the Pyradiomics package (V1.3.0) was used to extract radiomics variables, and LASSO regression was used to select features and construct radiomics scores (RS). The Clin-CUS and Clin-RS nomogram models were built using logistic regression analysis.

Results

Twenty-seven CLNM-associated radiomics features were selected using univariate analysis and LASSO regression from 1488 radiomics features and were calculated to construct the RS. The integrated model (Clin-RS) had better diagnostic performance than the Clin-CUS model for differentiating CLNM in the training dataset (AUC: 0.845 vs. 0.778) and the validation dataset (AUC: 0.808 vs. 0.751), respectively.

Conclusion

Our findings suggest that applying an ultrasound-based radiomics approach can effectively predict CLNM in patients with PTC with HT. By incorporating clinical information and RS, the Clin-RS model can achieve a high diagnostic performance in diagnosing CLNM in patients with PTC with HT.

SUBMITTER: Jin P

PROVIDER: S-EPMC9439618 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Ultrasound-based radiomics nomogram combined with clinical features for the prediction of central lymph node metastasis in papillary thyroid carcinoma patients with Hashimoto's thyroiditis.

Jin Peile P Chen Jifan J Dong Yiping Y Zhang Chengyue C Chen Yajun Y Zhang Cong C Qiu Fuqiang F Zhang Chao C Huang Pintong P

Frontiers in endocrinology 20220819

<h4>Background</h4>Hashimoto thyroiditis (HT) is the most common autoimmune thyroid disease and is considered an independent risk factor for papillary thyroid carcinoma (PTC), with a higher incidence of PTC in patients with HT.<h4>Objective</h4>To build an integrated nomogram using clinical information and ultrasound-based radiomics features in patients with papillary thyroid carcinoma (PTC) with Hashimoto thyroiditis (HT) to predict central lymph node metastasis (CLNM).<h4>Methods</h4>In total, ...[more]

PMID: 36060946

Similar Datasets

Project description:BackgroundCurrent studies have reported a high association between the Hashimoto's thyroiditis (HT) and papillary thyroid cancer (PTC). However, studies on the characteristics of central lymph node metastasis (CLNM) in PTC patients with HT are scarce. Therefore, this study aims to evaluate the risk factors of CLNM in PTC and HT patients.MethodsWe retrospectively collected clinical data from 933 PTC patients with HT who underwent thyroid surgery. Of these, 653 patients were categorized into a training cohort for constructing the nomogram, and 280 patients formed a validation cohort to verify the performance of the model. Least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression analyses were used to select risk factors. A nomogram model for predicting CLNM was developed and internally validated. We subsequently evaluated thyroid function within 3 years after surgery and estimated the prevalence and incidence of postoperative complications between the CLNM ( +) and CLNM (-) groups.ResultsLASSO regression revealed that 19 nonzero variables were associated with CLNM. Multivariate logistic regression analysis revealed that younger, patients of low body mass index (BMI), drinking, intranodular hyperechoic (IH) status, diameter ≥ 1 cm, multifocality, extrathyroidal extension (ETE), enlarged central lymph nodes (ECLNs) and lateral lymph node metastasis (LLNM) were at higher risk of CLNM (P < 0.05). A nomogram to predict CLNM in PTC patients with HT was constructed and internally validated on the basis of risk factors. The areas under the ROC curve (AUCs) of nomogram were 0.768 (95% CI, 0.723-0.812) and 0.773 (95% CI, 0.705-0.841) in training and validation groups, respectively. Moreover, the nomogram data showed a good discrimination and calibration ability to training and validation groups. Postoperative follow-up revealed that TGAb levels and the incidence of hypothyroidism were significantly greater in CLNM ( +) group than CLNM (-) group, respectively.ConclusionsOur nomogram schedule developed and validated with a comprehensive set of preoperative risk factors showed a high benefit in predicting CLNM in PTC patients with HT. Postoperative follow-up of thyroid function allow to clarify the trend, as well as prevalence and incidence of common thyroid complications.

Project description:BackgroundHashimoto's thyroiditis (HT) is the most prevalent inflammatory disorder of the thyroid gland. Current studies have reported the coexistence rate between HT and papillary thyroid carcinoma (PTC) is quite high. The objective of this study was to evaluate the impact of HT on the predictive factors of central compartment lymph node metastasis (CLNM) in PTC.MethodsA retrospective investigation was performed on PTC patients. They were subclassified into HT and non-HT groups. The results of preoperative neck ultrasound (US) examinations were reviewed. The clinical characteristics and the predictive value for CLNM were explored and compared between the two groups.ResultsA total of 756 patients were included in this study. There were more female patients (86.1%) in the PTC coexistent with the HT group than non-HT group. The patients with HT group had higher preoperative serum level of TSH. There was statistically significant difference between the HT patients and non-HT patients in nodular vascularization. Univariate and multivariate analyses showed that male, age ≤45 years old, tumor diameter >1 cm, and presence of suspicious central compartment lymph node on US, irregular nodular shape, multifocal carcinoma were independent predictive factors of CLNM in PTC patients. It was showed that male, age ≤45 years old, tumor diameter >1 cm, multifocality, and presence of suspicious central lymph node on US were risk factors for CLNM in non-HT patients. Only tumor diameter >1 cm and presence of suspicious central lymph node on US were independently correlated with CLNM in HT patients. The sensitivity of the multivariate model was 63.5%, and specificity was 88.9% for prediction CLNM in HT patients. For non-HT patients, the AUC was 80.6%, the sensitivity of the multivariate model was 64.5%, and specificity was 85.2.ConclusionPTC combined with HT is more common in women, and TSH level in HT group is higher than that in patients with PTC alone. Regardless of that HT is not a related risk factor of CLNM in PTC, our result suggested that different predictive systems should be used for HT and non-HT patients respectively to have a more accurate evaluation of CLNM in clinic.

Project description:PurposeThis study investigates the clinicopathological characteristics of papillary thyroid carcinoma (PTC) with coexisting Hashimoto's thyroiditis (HT) and further explores the risk factors for central lymph node metastasis (CLNM) in PTC.MethodA retrospective analysis was conducted on 415 PTC patients who underwent surgical treatment for thyroid cancer at the First Affiliated Hospital of Anhui University of Chinese Medicine from 2016 to 2022. Clinicopathological features were compared between PTC patients with and without HT. Univariate and multivariate logistic regression were used to analyze the risk factors of CLNM.ResultThe PTC+HT group had a higher proportion of female patients (85.5%) than the PTC group (P<0.05). Univariate analysis revealed no statistically significant difference between the two groups in eight aspects (all P>0.05). Multivariate analysis showed that HT was positively associated with the total number of central lymph node (CLN) dissected, Thyroid-stimulating hormone (TSH), Thyroid peroxidase antibody (TPOAb), and Thyroglobulin antibodies (TgAb), while identified as a protective factor against invasion with an odds ratio of 0.422 (95%CI 0.209-0.853, P=0.016). Through univariate and multivariate logistic regression, we proved that tumor position, Capsule + Extrathyroidal extension (ETE), multifocal tumors, and the total number of CLN dissected were independent risk factors for CLNM. Multiple linear regression analysis told us that invasion (β= 0.093, p=0.048) had a positively predictive impact on CLN positive rate.ConclusionFemale PTC patients are more prone to concurrent HT, which elevates the levels of TSH, TPOAb, and TgAb. HT not only promotes the longitudinal growth of nodules and PTC development, but also reduces the risk of invasion and CLNM. Therefore, we posit that the impact of HT on PTC patients is a "double-edged sword". Isthmus, Capsule + ETE, multifocality, age < 55 years old, and male are high-risk factors for CLNM in PTC, while HT is regarded as a protective factor. Capsule + ETE is the primary risk factor affecting the CLN positive rate.

Project description:BackgroundPrevious models for differentiating benign and malignant thyroid nodules(TN) have predominantly focused on the characteristics of the nodules themselves, without considering the specific features of the thyroid gland(TG) in patients with Hashimoto's thyroiditis(HT). In this study, we analyzed the clinical and ultrasound radiomics(USR) features of TN in patients with HT and constructed a model for differentiating benign and malignant nodules specifically in this population.MethodsWe retrospectively collected clinical and ultrasound data from 227 patients with TN and concomitant HT(161 for training, 66 for testing). Two experienced sonographers delineated the TG and TN regions, and USR features were extracted using Python. Lasso regression and logistic analysis were employed to select relevant USR features and clinical data to construct the model for differentiating benign and malignant TN. The performance of the model was evaluated using area under the curve(AUC), calibration curves, and decision curve analysis(DCA).ResultsA total of 1,162 USR features were extracted from TN and the TG in the 227 patients with HT. Lasso regression identified 14 features, which were used to construct the TN score, TG score, and TN+TG score. Univariate analysis identified six clinical predictors: TI-RADS, echoic type, aspect ratio, boundary, calcification, and thyroid function. Multivariable analysis revealed that incorporating USR scores improved the performance of the model for differentiating benign and malignant TN in patients with HT. Specifically, the TN+TG score resulted in the highest increase in AUC(from 0.83 to 0.94) in the clinical prediction model. Calibration curves and DCA demonstrated higher accuracy and net benefit for the TN+TG+clinical model.ConclusionUSR features of both the TG and TN can be utilized for differentiating benign and malignant TN in patients with HT. These findings highlight the importance of considering the entire TG in the evaluation of TN in HT patients, providing valuable insights for clinical decision-making in this population.

Project description:PurposePapillary thyroid carcinoma (PTC) frequently coexists with Hashimoto's thyroiditis (HT), which poses challenges in detecting central lymph node metastasis (CLNM) and determining optimal surgical management. Our study aimed to identify the independent predictors for CLNM in PTC patients with HT and develop a comprehensive prediction model for individualized clinical decision-making.Patients and methodsIn this retrospective study, a total of 242 consecutive PTC patients who underwent thyroid surgery and central lymph node dissection between February 2019 and December 2021 were included. 129 patients with HT were enrolled as the case group and 113 patients without HT as control. The results of patients' general information, laboratory examination, ultrasound features, pathological evaluation, and BRAF mutation were collected. Multivariate logistic regression analysis was used to identify independent predictors, and the prediction model and nomogram were developed for PTC patients with HT. The performance of the model was assessed using the receiver operating characteristic curve, calibration curve, decision curve analysis, and clinical impact curve. In addition, the impact of the factor BRAF mutation was further evaluated.ResultsMultivariate analysis revealed that gender (OR = 8.341, P = 0.013, 95% CI: 1.572, 44.266), maximum diameter (OR = 0.316, P = 0.029, 95% CI: 0.113, 0.888), multifocality (OR = 3.238, P = 0.010, 95% CI: 1.319, 7.948), margin (OR = 2.750, P = 0.046, 95% CI: 1.020, 7.416), and thyrotropin receptor antibody (TR-Ab) (OR = 0.054, P = 0.003, 95% CI: 0.008, 0.374) were identified as independent predictors for CLNM in PTC patients with HT. The area under the curve of the model was 0.82, with accuracy, sensitivity, and specificity of 77.5%, 80.3% and 75.0%, respectively. Meanwhile, the model showed satisfactory performance in the internal validation. Moreover, the results revealed that BRAF mutation cannot further improve the efficacy of the prediction model.ConclusionMale, maximum diameter > 10mm, multifocal tumors, irregular margin, and lower TR-Ab level have significant predictive value for CLNM in PTC patients with HT. Meanwhile, BRAF mutation may not have a valuable predictive role for CLNM in these cases. The nomogram constructed offers a convenient and valuable tool for clinicians to determine surgical decision and prognostication for patients.

Dataset Information

Ultrasound-based radiomics nomogram combined with clinical features for the prediction of central lymph node metastasis in papillary thyroid carcinoma patients with Hashimoto's thyroiditis.

Background

Objective

Methods

Results

Conclusion

Publications

Ultrasound-based radiomics nomogram combined with clinical features for the prediction of central lymph node metastasis in papillary thyroid carcinoma patients with Hashimoto's thyroiditis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets