Correlations of neck ultrasound and pathology in cervical lymph node of papillary thyroid carcinoma

Deep learning-based computer-aided diagnosis system for the automatic detection and classification of lateral cervical lymph nodes on original ultrasound images of papillary thyroid carcinoma: a prospective diagnostic study

PURPOSE

This study aims to develop a deep learning-based computer-aided diagnosis (CAD) system for the automatic detection and classification of lateral cervical lymph nodes (LNs) on original ultrasound images of papillary thyroid carcinoma (PTC) patients.

METHODS

A retrospective data set of 1801 cervical LN ultrasound images from 1675 patients with PTC and a prospective test set including 185 images from 160 patients were collected. Four different deep leaning models were trained and validated in the retrospective data set. The best model was selected for CAD system development and compared with three sonographers in the retrospective and prospective test sets.

RESULTS

The Deformable Detection Transformer (DETR) model showed the highest diagnostic efficacy, with a mean average precision score of 86.3% in the retrospective test set, and was therefore used in constructing the CAD system. The detection performance of the CAD system was superior to the junior sonographer and intermediate sonographer with accuracies of 86.3% and 92.4% in the retrospective and prospective test sets, respectively. The classification performance of the CAD system was better than all sonographers with the areas under the curve (AUCs) of 94.4% and 95.2% in the retrospective and prospective test sets, respectively.

CONCLUSIONS

This study developed a Deformable DETR model-based CAD system for automatically detecting and classifying lateral cervical LNs on original ultrasound images, which showed excellent diagnostic efficacy and clinical utility. It can be an important tool for assisting sonographers in the diagnosis process.

Drawing as a Way of Knowing: How a Mapping Model Assists Preoperative Evaluation of Patients with Thyroid Carcinoma

Background: Effective pre-surgical planning is crucial for achieving successful outcomes in endocrine surgery: it is essential to provide patients with a personalized plan to minimize operative and postoperative risks. Methods: Preoperative lymph node (LN) mapping is a structured high-resolution ultrasonography examination performed in the presence of two endocrinologists and the operating surgeon before intervention to produce a reliable "anatomical guide". Our aim was to propose a preoperative complete model that is non-invasive, avoids overdiagnosis of thyroid microcarcinomas, and reduces medical expenses. Results: The use of 'preoperative echography mapping' has been shown to be successful, particularly in patients with suspected or confirmed neoplastic malignancy. Regarding prognosis, positive outcomes have been observed both post-surgery and in terms of recurrence rates. We collected data on parameters such as biological sex, age, BMI, and results from cytologic tests performed with needle aspiration, and examined whether these parameters predict tumor malignancy or aggressiveness, calculated using a multivariate analysis (MVA). Conclusions: A standard multidisciplinary approach for evaluating neck lymph nodes pre-operation has proven to be an improved diagnostic and preoperative tool.

Central Neck Lymph Node Size Measured by Ultrasound Significantly Predicts Central Neck Lymph Node Metastasis of Papillary Thyroid Carcinoma

Objective: The aim of this study was to investigate whether Central lymph node (CLN) size as measured by an ultrasound can significantly predict CLN metastasis of papillary thyroid carcinoma (PTC). Materials and methods: This retrospective chart review of patients diagnosed with PTC who underwent ultrasound and central neck dissection (CND). We excluded patients who received previous thyroid surgery or radiation. We analyzed the correlation between CLN size and characteristics by ultrasound and histopathologic findings among positive CLN patients. Results: Of the 48 patients who underwent preoperative ultrasound and CND, 34 patients had positive CLN identified by ultrasound. The positive predictive value, negative predictive value, sensitivity, specificity, and accuracy of ultrasound in this diagnostic setting was 88.0%, 21.0%, 73.2%, 42.9%, and 68.7%, respectively. The risk of CLN metastasis of PTC was 67.7% and 85.7% for lymph node size 3.1 to 4 mm and 4.1 to 5 mm, respectively. The risk increased to 100% when the lymph node size was >5 mm. Positive preoperative ultrasound of lateral neck lymph node was found to be a significant risk factor for CLN metastasis (P = .003). Conclusion: Ultrasound was found to be an effective preoperative evaluation in patients with PTC to determine the likelihood of CLN metastasis and whether CND is indicated, especially in the ultrasound-positive central lymph node. A high risk of metastasis was found in CLN size >3 mm by ultrasound, and the risk dramatically increased in CLN size >5 mm. We also found positive lateral neck node from preoperative ultrasound to be a significant risk factor for CLN metastasis.

Ultrasound radiomics models based on multimodal imaging feature fusion of papillary thyroid carcinoma for predicting central lymph node metastasis

Objective

This retrospective study aimed to establish ultrasound radiomics models to predict central lymph node metastasis (CLNM) based on preoperative multimodal ultrasound imaging features fusion of primary papillary thyroid carcinoma (PTC).

Methods

In total, 498 cases of unifocal PTC were randomly divided into two sets which comprised 348 cases (training set) and 150 cases (validition set). In addition, the testing set contained 120 cases of PTC at different times. Post-operative histopathology was the gold standard for CLNM. The following steps were used to build models: the regions of interest were segmented in PTC ultrasound images, multimodal ultrasound image features were then extracted by the deep learning residual neural network with 50-layer network, followed by feature selection and fusion; subsequently, classification was performed using three classical classifiers-adaptive boosting (AB), linear discriminant analysis (LDA), and support vector machine (SVM). The performances of the unimodal models (Unimodal-AB, Unimodal-LDA, and Unimodal-SVM) and the multimodal models (Multimodal-AB, Multimodal-LDA, and Multimodal-SVM) were evaluated and compared.

Results

The Multimodal-SVM model achieved the best predictive performance than the other models (P < 0.05). For the Multimodal-SVM model validation and testing sets, the areas under the receiver operating characteristic curves (AUCs) were 0.910 (95% CI, 0.894-0.926) and 0.851 (95% CI, 0.833-0.869), respectively. The AUCs of the Multimodal-SVM model were 0.920 (95% CI, 0.881-0.959) in the cN0 subgroup-1 cases and 0.828 (95% CI, 0.769-0.887) in the cN0 subgroup-2 cases.

Conclusion

The ultrasound radiomics model only based on the PTC multimodal ultrasound image have high clinical value in predicting CLNM and can provide a reference for treatment decisions.

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.

Ultrasound-based Nomogram for Predicting the Pathological Nodal Negativity of Unilateral Clinical N1a Papillary Thyroid Carcinoma in Adolescents and Young Adults

RATIONALE AND OBJECTIVES

To develop and validate a nomogram incorporating clinical and ultrasound (US) characteristics for predicting the pathological nodal negativity of unilateral clinically N1a (cN1a) papillary thyroid carcinoma (PTC) among adolescents and young adults.

MATERIALS AND METHODS

From December 2016 to August 2021, 278 patients aged ≤ 30 years from two medical centers were enrolled and randomly assigned to the training and validation cohorts at a ratio of 2:1. After performing univariate and multivariate analyses, a nomogram combining all independent predictive factors was constructed and applied to the validation cohort. The performance of the nomogram was evaluated using receiver operating characteristic curves, calibration curves, and decision curve analysis .

RESULTS

Multivariate logistic regression analysis showed that unilateral cN1a PTC in young patients with Hashimoto's thyroiditis, T1 stage, no intra-tumoral microcalcification, and tumors located in the upper third of the thyroid gland was more likely to be free of central lymph node metastases. The nomogram revealed good calibration and discrimination in both cohorts, with areas under the receiver operating characteristic curve of 0.764 (95% confidence interval [CI]: 0.684-0.843) and 0.728 (95% CI: 0.602-0.853) in the training and validation cohorts, respectively. The clinical application of the nomogram was further confirmed using decision curve analysis.

CONCLUSION

This US-based nomogram may assist the assessment of central cervical lymph nodes in young patients with unilateral cN1a PTC, enabling improved risk stratification and optimal treatment management in clinical practice.

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.

Machine learning prediction of prostate cancer from transrectal ultrasound video clips

Objective

To build a machine learning (ML) prediction model for prostate cancer (PCa) from transrectal ultrasound video clips of the whole prostate gland, diagnostic performance was compared with magnetic resonance imaging (MRI).

Methods

We systematically collated data from 501 patients—276 with prostate cancer and 225 with benign lesions. From a final selection of 231 patients (118 with prostate cancer and 113 with benign lesions), we randomly chose 170 for the purpose of training and validating a machine learning model, while using the remaining 61 to test a derived model. We extracted 851 features from ultrasound video clips. After dimensionality reduction with the least absolute shrinkage and selection operator (LASSO) regression, 14 features were finally selected and the support vector machine (SVM) and random forest (RF) algorithms were used to establish radiomics models based on those features. In addition, we creatively proposed a machine learning models aided diagnosis algorithm (MLAD) composed of SVM, RF, and radiologists’ diagnosis based on MRI to evaluate the performance of ML models in computer-aided diagnosis (CAD). We evaluated the area under the curve (AUC) as well as the sensitivity, specificity, and precision of the ML models and radiologists’ diagnosis based on MRI by employing receiver operator characteristic curve (ROC) analysis.

Results

The AUC, sensitivity, specificity, and precision of the SVM in the diagnosis of PCa in the validation set and the test set were 0.78, 63%, 80%; 0.75, 65%, and 67%, respectively. Additionally, the SVM model was found to be superior to senior radiologists’ (SR, more than 10 years of experience) diagnosis based on MRI (AUC, 0.78 vs. 0.75 in the validation set and 0.75 vs. 0.72 in the test set), and the difference was statistically significant (p< 0.05).

Conclusion

The prediction model constructed by the ML algorithm has good diagnostic efficiency for prostate cancer. The SVM model’s diagnostic efficiency is superior to that of MRI, as it has a more focused application value. Overall, these prediction models can aid radiologists in making better diagnoses.

[Risk factors of skip lateral cervical lymph node metastasis in papillary thyroid carcinoma]

Objective:To investigate the incidence and risk factors of skip lateral cervical lymph node metastasis in patients with papillary thyroid carcinoma（PTC）. Methods:The clinical and pathological data of 85 patients with PTC who underwent total thyroidectomy plus central and lateral neck dissection in the Department of Otolaryngology Head and Neck Surgery, the First Affiliated Hospital of Hebei North University from January 2018 to January 2022 were analyzed retrospectively. SPSS 26.0 software was used to process the data, and univariate and multivariate analysis were performed to assess the relationships between skip lateral cervical lymph node metastasis and clinicopathological characteristics. Results:There were 31 cases（36.5%） of skipped lateral cervical lymph node metastasis. Univariate analysis showed that the largest tumor diameter ≤5 mm（P=0.006） and the tumor located in the upper pole of the thyroid（P=0.002） were associated with the occurrence of skip lateral cervical lymph node metastasis in patients with PTC. Most of the skip metastases involved a single area（18/31, 58.1%）, of which area Ⅲ was most likely to be involved（10/31, 32.3%）, followed by area Ⅱ（5/31, 16.1%）. The results of binary logistic analysis showed that tumor diameter less than 5 mm（OR 7.800, 95%CI 1.710-21.394, P=0.005） and tumor at the upper pole of the gland（OR 4.060, 95%CI 1.468-11.235, P=0.007） were independent risk factors of skip lateral cervical lymph node metastasis in PTC patients. Conclusion:PTC patients with tumor diameter ≤5 mm and tumor located in the upper pole of the gland are more prone to skip lateral cervical lymph node metastasis. When the diameter of the tumor is less than 5 mm and the tumor is located at the upper pole of the gland, careful evaluation should be made before operation, even in the absence of central lymph node metastasis, attention should be paid to the possibility of lateral cervical lymph node metastasis.

Nomograms based on preoperative multimodal ultrasound of papillary thyroid carcinoma for predicting central lymph node metastasis

OBJECTIVES

To establish a nomogram for predicting central lymph node metastasis (CLNM) based on the preoperative clinical and multimodal ultrasound (US) features of papillary thyroid carcinoma (PTC) and cervical LNs.

METHODS

Overall, 822 patients with PTC were included in this retrospective study. A thyroid tumor ultrasound model (TTUM) and thyroid tumor and cervical LN ultrasound model (TTCLNUM) were constructed as nomograms to predict the CLNM risk. Areas under the curve (AUCs) evaluated model performance. Calibration and decision curves were applied to assess the accuracy and clinical utility.

RESULTS

For the TTUM training and test sets, the AUCs were 0.786 and 0.789 and bias-corrected AUCs were 0.786 and 0.831, respectively. For the TTCLNUM training and test sets, the AUCs were 0.806 and 0.804 and bias-corrected AUCs were 0.807 and 0.827, respectively. Calibration and decision curves for the TTCLNUM nomogram exhibited higher accuracy and clinical practicability. The AUCs were 0.746 and 0.719 and specificities were 0.942 and 0.905 for the training and test sets, respectively, when the US tumor size was ≤ 8.45 mm, while the AUCs were 0.737 and 0.824 and sensitivity were 0.905 and 0.880, respectively, when the US tumor size was > 8.45 mm.

CONCLUSION

The TTCLNUM nomogram exhibited better predictive performance, especially for the CLNM risk of different PTC tumor sizes. Thus, it serves as a useful clinical tool to supply valuable information for active surveillance and treatment decisions.

KEY POINTS

• Our preoperative noninvasive and intuitive prediction method can improve the accuracy of central lymph node metastasis (CLNM) risk assessment and guide clinical treatment in line with current trends toward personalized treatments. • Preoperative clinical and multimodal ultrasound features of primary papillary thyroid carcinoma (PTC) tumors and cervical LNs were directly used to build an accurate and easy-to-use nomogram for predicting CLNM. • The thyroid tumor and cervical lymph node ultrasound model exhibited better performance for predicting the CLNM of different PTC tumor sizes. It may serve as a useful clinical tool to provide valuable information for active surveillance and treatment decisions.

Diagnostic Test Accuracy of Ultrasonography vs Computed Tomography for Papillary Thyroid Cancer Cervical Lymph Node Metastasis: A Systematic Review and Meta-analysis

Importance

The use of ultrasonography (US) vs cross-sectional imaging for preoperative evaluation of papillary thyroid cancer is debated.

Objective

To compare thyroid US and computed tomography (CT) in the preoperative evaluation of papillary thyroid cancer for cervical lymph node metastasis (CLNM), as well as extrathyroidal disease extension.

Data Sources

MEDLINE and Embase were searched from January 1, 2000, to July 18, 2020.

Study Selection

Studies reporting on the diagnostic accuracy of US and/or CT in individuals with treatment-naive papillary thyroid cancer for CLNM and/or extrathyroidal disease extension were included. The reference standard was defined as histopathology/cytology or imaging follow-up. Independent title and abstract review (2515 studies) followed by full-text review (145 studies) was completed by multiple investigators.

Data Extraction and Synthesis

PRISMA guidelines were followed. Methodologic and diagnostic accuracy data were abstracted independently by multiple investigators. Risk of bias assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool independently and in duplicate. Bivariate random-effects model meta-analysis and multivariable meta-regression modeling was used.

Main Outcomes and Measures

Diagnostic test accuracy of US and CT of the neck for lateral and central compartment CLNM, as well as for extrathyroidal disease extension, determined prior to study commencement.

Results

A total of 47 studies encompassing 31 942 observations for thyroid cancer (12 771 with CLNM; 1747 with extrathyroidal thyroid extension) were included; 21 and 26 studies were at low and high risk for bias, respectively. Based on comparative design studies, US and CT demonstrated no significant difference in sensitivity (73% [95% CI, 64%-80%] and 77% [95% CI, 67%-85%], respectively; P = .11) or specificity (89% [95% CI, 80%-94%] and 88% [95% CI, 79%-94%], respectively; P = .79) for lateral compartment CLNM. For central compartment metastasis, sensitivity was higher in CT (39% [95% CI, 27%-52%]) vs US (28% [95% CI, 21%-36%]; P = .004), while specificity was higher in US (95% [95% CI, 92%-98%]) vs CT (87% [95% CI, 77%-93%]; P < .001). Ultrasonography demonstrated a sensitivity of 91% (95% CI, 81%-96%) and specificity of 47% (95% CI, 35%-60%) for extrathyroidal extension.

Conclusions and Relevance

The findings of this systematic review and meta-analysis suggest that further study is warranted of the role of CT for papillary thyroid cancer staging, possibly as an adjunct to US.

A comparison of the efficiency of diagnostic ultrasound and magnetic resonance imaging of cervical lymph nodes in papillary thyroid carcinoma

OBJECTIVE

To compare and evaluate diagnostic capabilities of preoperative ultrasonography (US) and magnetic resonance imaging (MRI) in the cervical lymph nodes of patients with papillary thyroid cancer.

METHODS

A retrospective dataset involving 156 patients who had undergone thyroidectomy and preoperative US and MRI was assembled. Among these, 69 had cervical lymph node metastasis and 87 did not. At least four radiologists unilaterally and spontaneously investigated the US and MRI attributes of the cervical lymph nodes. The efficiency of diagnostic imaging for cervical lymph nodes, including their true-positive rate or sensitivity, true-negative rate or specificity, positive predictive value, negative predictive value, and predictive accuracy were analysed and assessed.

RESULTS

In the assessment of cervical lymph node metastases of papillary thyroid cancer, the diagnostic sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of diagnostic US vs. MRI were 58.0% vs. 79.7%, 69.0% vs. 83.9%, 59.7% vs. 79.7%, 67.4% vs. 83.9%, and 64.1% vs. 82.1%, respectively. The accuracy consistency of the two imaging modalities was 83.5%.

CONCLUSIONS

MRI is more effective than US in diagnosing and assessing cervical lymph node metastases of papillary thyroid cancer.