History of Thyroid Ultrasound

Prediction of lymph node metastasis in papillary thyroid carcinoma using non-contrast CT-based radiomics and deep learning with thyroid lobe segmentation: A dual-center study

Objectives

This study aimed to develop a predictive model for lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) patients by deep learning radiomic (DLRad) and clinical features.

Methods

This study included 271 thyroid lobes from 228 PTC patients who underwent preoperative neck non-contrast CT at Center 1 (May 2021-April 2024). LNM status was confirmed via postoperative pathology, with each thyroid lobe labeled accordingly. The cohort was divided into training (n = 189) and validation (n = 82) cohorts, with additional temporal (n = 59 lobes, Center 1, May-August 2024) and external (n = 66 lobes, Center 2) test cohorts. Thyroid lobes were manually segmented from the isthmus midline, ensuring interobserver consistency (ICC ≥ 0.8). Deep learning and radiomics features were selected using LASSO algorithms to compute DLRad scores. Logistic regression identified independent predictors, forming DLRad, clinical, and combined models. Model performance was evaluated using AUC, calibration, decision curves, and the DeLong test, compared against radiologists' assessments.

Results

Independent predictors of LNM included age, gender, multiple nodules, tumor size group, and DLRad. The combined model demonstrated superior diagnostic performance with AUCs of 0.830 (training), 0.799 (validation), 0.819 (temporal test), and 0.756 (external test), outperforming the DLRad model (AUCs: 0.786, 0.730, 0.753, 0.642), clinical model (AUCs: 0.723, 0.745, 0.671, 0.660), and radiologist evaluations (AUCs: 0.529, 0.606, 0.620, 0.503). It also achieved the lowest Brier scores (0.167, 0.184, 0.175, 0.201) and the highest net benefit in decision-curve analysis at threshold probabilities > 20 %.

Conclusions

The combined model integrating DLRad and clinical features exhibits good performance in predicting LNM in PTC patients.

Thyroid Cancer Staging: Historical Evolution and Analysis From Macrocarcinoma to Microcarcinoma

The classification of thyroid cancer diagnosis and treatment has evolved dramatically since the Union for International Cancer Control (UICC) published the first staging system in 1968. A careful review of the eight published editions of well-differentiated thyroid cancer (WDTC) staging by the UICC and the American Joint Committee on Cancer (AJCC) was performed. Each edition was analyzed to clearly understand which development published and accepted by specialists treating thyroid cancer justified considering a new updated edition. This study presents a comprehensive review of the remarkable evolution of thyroid cancer staging, highlighting the various changes in several areas throughout the years and editions. There were surprising changes within the eight publications: the tumor size was progressively reduced from 4 cm in the first AJCC volume to less than 1 cm in the seventh and eighth UICC and AJCC editions, classifying these small, WDTCs known up to now as "microcarcinomas." Extrathyroidal extension was accepted after the third edition; this description certainly plays a key role in today's decisions to manage this tumor as a prognostic factor. The age specification of 45 years prevailed for seven consecutive publications until it was raised to 55 years in the eighth thyroid cancer staging system. Without a doubt, this iconic change allowed physicians around the world to give their 45-year-old thyroid cancer patients a more encouraging panorama of the disease with the new classification. Over the course of nearly 57 years, thyroid cancer staging has undergone remarkable changes, reaching a level of certainty that not only provides recommendations for safer treatments with less surgery and adjunctive measures but also improves survival rates and patient safety.

A model based on Chinese thyroid imaging reporting and data systems for predicting Bethesda III/IV thyroid nodules

Objectives

This study aimed to explore the performance of a model based on Chinese Thyroid Imaging Reporting and Data Systems (C-TIRADS), clinical characteristics, and other ultrasound characteristics for the prediction of Bethesda III/IV thyroid nodules before fine needle aspiration (FNA).

Materials and methods

A total of 855 thyroid nodules from 810 patients were included. All nodules underwent ultrasound examination before FNA. All nodules were categorized according to the C-TIRADS criteria and classified into two groups, Bethesda III/IV and non-III/IV thyroid nodules, using cytologic diagnosis as the gold standard. The clinical and ultrasonographic characteristics of the nodules in the two groups were compared, and independent predictors of Bethesda III/IV nodules were determined by univariate and multivariate logistic regression analyses, based on which a prediction model was constructed. The predictive efficacy of the model was compared with that of C-TIRADS alone by sensitivity, specificity, and area under the curve (AUC).

Results

Our study found that the C-TIRADS category, homogeneous echotexture, blood flow signal present, and posterior echo unchanged were independent predictors for Bethesda III/IV thyroid nodules. Based on multiple logistic regression, a predictive model was established: Logit (p)= - 4.213 + 0.965 × homogeneous echotexture+ 1.050 × blood flow signal present + 0.473 × posterior echo unchanged+ 2.859 × C-TIRADS 3 + 2.804 × C-TIRADS 4A + 1.824 × C-TIRADS 4B + 0.919 × C-TIRADS 4C. The AUC of the model among all nodules was 0.746 (95%CI: 0.710-0.782), 0.779 (95%CI: 0.730-0.829) among nodules with a diameter (D) > 10mm, and 0.718 (95%CI: 0.667-0.769) among nodules with D ≤ 10mm, which were significantly higher than that of the C-TIRADS alone.

Conclusion

We developed a predictive model for Bethesda III/IV thyroid nodules that is better for nodules with D > 10mm FNA operators can choose the optimal puncture strategy based on the prediction results to improve the rate of definitive diagnosis of the first FNA of Bethesda III/IV nodules and thus reduce repeat FNA.

An unsupervised automatic texture classification method for ultrasound images of thyroid nodules

Objective.Ultrasound is the predominant modality in medical practice for evaluating thyroid nodules. Currently, diagnosis is typically based on textural information. This study aims to develop an automated texture classification approach to aid physicians in interpreting ultrasound images of thyroid nodules. However, there is currently a scarcity of pixel-level labeled datasets for the texture classes of thyroid nodules. The labeling of such datasets relies on professional and experienced doctors, requiring a significant amount of manpower. Therefore, the objective of this study is to develop an unsupervised method for classifying nodule textures.Approach.Firstly, we develop a spatial mapping network to transform the one-dimensional pixel value space into a high-dimensional space to extract comprehensive feature information. Subsequently, we outline the principles of feature selection that are suitable for clustering. Then we propose a pixel-level clustering algorithm with a region growth pattern, and a distance evaluation method for texture sets among different nodules is established.Main results.Our algorithm achieves a pixel-level classification accuracy of 0.931 for the cystic and solid region, 0.870 for the hypoechoic region, 0.959 for the isoechoic region, and 0.961 for the hyperechoic region. The efficacy of our algorithm and its concordance with human observation have been demonstrated. Furthermore, we conduct calculations and visualize the distribution of different textures in benign and malignant nodules.Significance.This method can be used for the automatic generation of pixel-level labels of thyroid nodule texture, aiding in the construction of texture datasets, and offering image analysis information for medical professionals.

Observational cohort study on safety and efficacy of robotic thyroidectomy with super-meticulous capsular dissection versus open surgery for thyroid cancer: postoperative dynamic risk assessment of radioactive iodine therapy

OBJECTIVE

To assess the efficacy and safety of robotic thyroidectomy (RT) with super-meticulous capsular dissection (SMCD) versus open thyroidectomy (OT), the authors used a dynamic risk assessment system incorporating 131 I-WBS along with radioactive iodine (RAI) efficacy evaluation.

BACKGROUND

Currently, the therapeutic efficacy of robotic surgery remains controversial. The 131 I whole-body scan ( 131 I-WBS) dynamic risk assessment system can detect small residual thyroid tissues and lesions, which may be used as indicators for the surgical efficacy of RT or OT thyroidectomy in differentiated thyroid cancer (DTC).

METHODS

This retrospective cohort study included 2349 patients who underwent total thyroidectomy followed by RAI therapy in our department between August 2017 and June 2023. Propensity score matching was performed at a ratio of 1:3 based on surgical type and mean follow-up duration to minimize selection bias after excluding those lost to follow-up. The primary outcome was surgical completeness, assessed using a dynamic risk system incorporating 131 I-WBS along with RAI efficacy evaluation.

RESULTS

There was no significant difference in the number of metastatic lymph nodes removed between the two groups ( P =0.45). The incidence rate of parathyroid gland transplantation was 395 (68.7%) in the OT group and 8 (3.8%) in the RT group ( P <0.001). There were no differences in the thyroidectomy completeness based on the 3 h iodine uptake rate and 99m TcO 4- thyroid imaging between the two groups. The dynamic risk assessment with and without 131 I-WBS showed significant differences ( P <0.001). The postoperative and post-RAI dynamic risk scores, evaluated at the time of RAI and 6 months after RAI, did not differ significantly between the two groups ( P >0.05). The rates of transient and permanent hypoparathyroidism were higher in the OT group than in the RT group ( P <0.05). The local recurrence rates showed no significant difference between the groups.

CONCLUSIONS

This study demonstrates that RT with SMCD can achieve outcomes equivalent to those of traditional open surgery when integrating the 131 I-WBS dynamic evaluation system and the therapeutic effects of RAI. Additionally, robot surgery demonstrated a notable advantage in protecting parathyroid function.

Deep learning model for diagnosis of thyroid nodules with size less than 1 cm: A multicenter, retrospective study

Objective

To develop a ultrasound images based dual-channel deep learning model to achieve accurate early diagnosis of thyroid nodules less than 1 cm.

Methods

A dual-channel deep learning model called thyroid nodule transformer network (TNT-Net) was proposed. The model has two input channels for transverse and longitudinal ultrasound images of thyroid nodules, respectively. A total of 9649 nodules from 8455 patients across five hospitals were retrospectively collected. The data were divided into a training set (8453 nodules, 7369 patients), an internal test set (565 nodules, 512 patients), and an external test set (631 nodules, 574 patients).

Results

TNT-Net achieved an area under the curve (AUC) of 0.953 (95 % confidence interval (CI): 0.934, 0.969) on the internal test set and 0.941 (95 % CI: 0.921, 0.957) on the external test set, significantly outperforming traditional deep convolutional neural network models and single-channel swin transformer model, whose AUCs ranged from 0.800 (95 % CI: 0.759, 0.837) to 0.856 (95 % CI: 0.819, 0.881). Furthermore, feature heatmap visualization showed that TNT-Net could extract richer and more energetic malignant nodule patterns.

Conclusion

The proposed TNT-Net model significantly improved the recognition capability for thyroid nodules with size less than 1 cm. This model has the potential to reduce overdiagnosis and overtreatment of such nodules, providing essential support for precise management of thyroid nodules while complementing fine-needle aspiration biopsy.

Application of shear wave elastography in the management of thyroid nodules in children and adolescents: our experience and a review of the literature

Introduction

Shear wave elastography (SWE) is an ultrasound diagnostic method used to measure tissue stiffness. Since the mechanical properties of tissue involved in the pathological process change, SWE might indicate regions of the examined tissue covered by the disease. It is well documented that SWE helps to differentiate benign and malignant nodules in thyroid glands in adults, however, there are few studies on the application of SWE in thyroid diagnosis in children. The purpose of the study was to assess the application of SWE based on Young's modulus expressed in kPa in the management of thyroid nodules in children and adolescents.

Methods

In total, 116 pediatric patients (81 girls and 35 boys) with 168 thyroid nodules were enrolled in the study and qualified for SWE followed by fine needle aspiration biopsy.

Results

According to the result of the cytological examination presented in the Bethesda System, nodules were classified as benign (147 nodules classified as category II according to the Bethesda System) or indeterminate or suspicious (21 nodules classified as categories III, IV, and V according to the Bethesda System). Benign cytological diagnoses were nodular goiter, parenchymal goiter, nodular colloid goiter, or lymphocytic inflammation. Among the indeterminate or suspicious nodules, 15 were diagnosed as category III according to the Bethesda System (atypia of undetermined significance (AUS) or follicular lesion of undetermined significance (FLUS) in cytology), 1 nodule was diagnosed as category IV according to the Bethesda System (suspicious for follicular neoplasm - oxyphilic cell tumor), and 5 as category V according to the Bethesda System (suspicious for malignancy). There were no significant differences in thyrotropin (TSH) and free thyroxine (fT4) concentrations between the benign and suspicious groups. Patients with benign and indeterminate or suspicious thyroid nodules were of comparable age. Mean SWE in benign nodules was statistically significantly lower than in nodules with indeterminate or suspicious cytology (42.22 ± 16.69 vs. 57.4 ± 24.0 kPa, p=0.0004). Six patients from the indeterminate or suspicious group were revealed to be malignant in the final histopathological examination.

Conclusion

Our results suggest that SWE is a viable diagnostic method, however, it still seems to need some adjustment for pediatric patients.

Development and validation of a prognostic nomogram for predicting liver metastasis in thyroid cancer: a study based on the surveillance, epidemiology, and end results database

This study aimed to create a prognostic nomogram to predict the risk of liver metastasis (LM) in thyroid cancer (TC) patients and assess survival outcomes for those with LM. Data were collected from the SEER database, covering TC patients from 2010 to 2020, totaling 110,039 individuals, including 142 with LM. Logistic regression and stepwise regression based on the Akaike information criterion (AIC) identified significant factors influencing LM occurrence: age, histological type, tumor size, bone metastasis, lung metastasis, and T stage (p < 0.05). A nomogram was constructed using these factors, achieving a Cindex of 0.977, with ROC curve analysis showing an area under the curve (AUC) of 0.977. For patients with TCLM, follicular TC, medullary TC, papillary TC, and examined regional nodes were associated with better prognosis (p < 0.001, HR < 1), while concurrent brain metastasis indicated poorer outcomes (HR = 2.747, p = 0.037). In conclusion, this nomogram effectively predicts LM risk and evaluates prognosis for TCLM patients, aiding clinicians in personalized treatment decisions.

Long-term efficacy of lobectomy for stage T1 papillary thyroid carcinoma with varying degrees of lymph node metastasis

Background

The presence of lymph node metastasis (LNM) is frequently observed in papillary thyroid carcinoma (PTC), and most clinical guidelines recommend total thyroidectomy. However, the impact of LNM on specific types of locoregional recurrence remains uncertain, particularly for stage T1 PTC.

Methods

The present retrospective cohort study enrolled patients diagnosed with stage T1 PTC between 2008 and 2015. Propensity score matching was performed in patients with lobectomy accompanied by varying degrees of LNM. Logistic regression analysis was performed to compare the effect of LNM on relapse types, and Kaplan-Meier method was utilized to calculate recurrence-free survival.

Results

The study cohort comprised 2,785 patients who were followed up for an average duration of 69 months. After controlling follow-up time and potential prognostic factors, we include a total of 362 patients in each group. Recurrence rates in the N0, N1a, and N1b groups were found to be 2.5%, 9.7%, and 10.2% respectively. Notably, group N1a versus group N0 (P=0.803), N1b group versus N0 group (P=0.465), and group N1b versus group N1a (P=0.344) had no difference in residual thyroid recurrence. However, when considering lymph node recurrence, both N1a(P=0.003) and N1b(P=0.009) groups showed a higher risk than N0 group. In addition, there was no difference in lymph node recurrence between N1b group and N1a group (P=0.364), but positive lymph node (PLN) and lymph node positive rate (LNPR) demonstrated a strong discriminatory effect (P<0.001).

Conclusion

Lobectomy may be more appropriate for patients with unilateral stage T1 PTC in the low LNPR group.

Association of autoimmune thyroid disease with type 1 diabetes mellitus and its ultrasonic diagnosis and management

As a common hyperglycemic disease, type 1 diabetes mellitus (T1DM) is a complicated disorder that requires a lifelong insulin supply due to the immune-mediated destruction of pancreatic β cells. Although it is an organ-specific autoimmune disorder, T1DM is often associated with multiple other autoimmune disorders. The most prevalent concomitant autoimmune disorder occurring in T1DM is autoimmune thyroid disease (AITD), which mainly exhibits two extremes of phenotypes: hyperthyroidism [Graves' disease (GD)] and hypo-thyroidism [Hashimoto's thyroiditis, (HT)]. However, the presence of comorbid AITD may negatively affect metabolic management in T1DM patients and thereby may increase the risk for potential diabetes-related complications. Thus, routine screening of thyroid function has been recommended when T1DM is diagnosed. Here, first, we summarize current knowledge regarding the etiology and pathogenesis mechanisms of both diseases. Subsequently, an updated review of the association between T1DM and AITD is offered. Finally, we provide a relatively detailed review focusing on the application of thyroid ultrasonography in diagnosing and managing HT and GD, suggesting its critical role in the timely and accurate diagnosis of AITD in T1DM.

A Comprehensive Approach to the Thyroid Bethesda Category III (AUS) in the Transition Zone Between 2nd Edition and 3rd Edition of The Bethesda System for Reporting Thyroid Cytopathology: Subcategorization, Nuclear Scoring, and More

Significant interobserver variabilities exist for Bethesda category III: atypia of undetermined significance (AUS) of The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC). Thus, subcategorization of AUS including AUS "nuclear" and AUS "other" is proposed in the recent 3rd edition of TBSRTC. This study investigated the impact of the nuclear features/architectural features/nuclear score (NS) (3-tiered)/subcategories and subgroups on risk of malignancy (ROM) in thyroid fine-needle aspirations (FNA). 6940 FNAs were evaluated. 1224 (17.6%) cases diagnosed as AUS were reviewed, and 240 patients (initial FNAs of 260 nodules and 240 thyroidectomies) were included. Subcategories and subgroups were defined according to TBSRTC 2nd and 3rd editions. Histological diagnostic groups included nonneoplastic disease, benign neoplasm, low-risk neoplasm, and malignant neoplasm. Overall, ROM was 30.7%. ROM was significantly higher in FNAs with nuclear overlapping (35.5%), nuclear molding (56.9%), irregular contours (42.1%), nuclear grooves (74.1%), chromatin clearing (49.4%), and chromatin margination (57.7%), and these features were independent significant predictors for malignancy. FNAs with NS3 had significantly higher ROM (64.2%). Three-dimensional groups were significantly more frequent in malignant neoplasms (35.7%). ROM was significantly higher in AUS-nuclear subcategory (48.2%) and in AUS-nuclear and architectural subcategory (38.3%). The highest ROM was detected in AUS-nuclear1 subgroup (65.2%). ROM was significantly higher in the group including AUS-nuclear and AUS-nuclear and architectural subcategories, namely "high-risk group" than the group including other subcategories, namely "low-risk group" (42.0%vs 13.9%). In conclusion, subcategorization may not be the end point, and nuclear scoring and evaluation of architectural patterns according to strict criteria may provide data for remodeling of TBSRTC categories.

Uni- and Multivariate Analyses of Cancer Risk in Cytologically Indeterminate Thyroid Nodules: A Single-Center Experience

Every year in Italy, about 60,000 new cases of nodular thyroid pathology are diagnosed, of which almost 30% are cytologically indeterminate (TIR3A/3B). The risk of malignancy reported in the literature on thyroid nodules ranges from 5% to 15% for TIR3A and from 15% to 30% for TIR3B. It is suspected that these percentages are higher in practice. We performed univariate and multivariate analyses of clinical risk factors. The medical records of 291 patients who underwent surgery for cytologically indeterminate nodular thyroid disease were retrospectively reviewed. Clinical parameters and preoperative serum markers were then compared between the benign nodular thyroid disease and thyroid cancer groups. For each patient, clinical characteristics, comorbidities, neck ultrasonographic features, and histological reports were statistically analyzed using Chi-squared and Fisher's exact tests. A total of 134 malignant neoplasms were found (46%), divided into 55 cases (35%) in the TIR3A group and 79 cases (59%) in the TIR3B group. Statistical analysis was not significant in both populations for both sex and age (TIR3A p-value = 0.5097 and p-value = 0.1430, TIR3B p-value = 0.5191 p-value = 0.3384), while it was statistically significant in patients with TIR3A nodules associated with thyroiditis (p-value = 0.0009). In addition, the patients with TIR3A and 3B nodules were stratified by ultrasound risk for the prediction of malignancy and it was significant (p = 0.0004 and p < 0.0001). In light of these results, it emerges that surgical treatment of nodular thyroid pathology with indeterminate cytology TIR3A should always be considered, and surgery for TIR3B is mandatory.