A prognostic model for thermal ablation of benign thyroid nodules based on interpretable machine learning.

Introduction: The detection rate of benign thyroid nodules is increasing every year, with some affected patients experiencing symptoms. Ultrasound-guided thermal ablation can reduce the volume of nodules to alleviate symptoms. As the degree and speed of lesion absorption vary greatly between individuals, an effective model to predict curative effect after ablation is lacking. This study aims to predict the efficacy of ultrasound-guided thermal ablation for benign thyroid nodules using machine learning and explain the characteristics affecting the nodule volume reduction ratio (VRR). Design: Prospective study. Patients: The clinical and ultrasonic characteristics of patients who underwent ultrasound-guided thermal ablation of benign thyroid nodules at our hospital between January 2020 and January 2023 were recorded. Measurements: Six machine learning models (logistic regression, support vector machine, decision tree, random forest, eXtreme Gradient Boosting [XGBoost], and Light Gradient Boosting Machine [LGBM]) were constructed to predict efficacy; the effectiveness of each model was evaluated, and the optimal model selected. SHapley Additive exPlanations (SHAP) was used to visualize the decision process of the optimal model and analyze the characteristics affecting the VRR. Results: In total, 518 benign thyroid nodules were included: 356 in the satisfactory group (VRR ≥70% 1 year after operation) and 162 in the unsatisfactory group. The optimal XGBoost model predicted satisfactory efficacy with 78.9% accuracy, 88.8% precision, 79.8% recall rate, an F1 value of 0.84 F1, and an area under the curve of 0.86. The top five characteristics that affected VRRs were the proportion of solid components < 20%, initial nodule volume, blood flow score, peripheral blood flow pattern, and proportion of solid components 50-80%. Conclusions: The models, based on interpretable machine learning, predicted the VRR after thermal ablation for benign thyroid nodules, which provided a reference for preoperative treatment decisions.

Next generation sequence-based targeted somatic mutation analysis in thyroid nodules with pathologically diagnosed as indeterminate cytology.

PURPOSE: The management of indeterminate thyroid nodules remains a topic of ongoing debate, particularly regarding the differentiation of malignancy. Somatic mutation analysis offers crucial insights into tumor characteristics. This study aimed to assist the clinical management of indeterminate nodules with somatic mutation analysis. METHODS: Aspiration samples from 20 indeterminate thyroid nodules were included in the study. A next-generation sequencing panel containing 67 genes was used for molecular profiling. The results were compared with pathology data from surgical material, which is considered the gold standard. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. RESULTS: Variants in six genes (NRAS, BRAF, TP53, TERT, PTEN, PIK3CA) were detected in 10 out of 20 samples. We identified nine Tier 1 or 2 variants in 10 (67 %) out of 15 malignant nodules (NRAS, BRAF, TP53, TERT, PTEN, PIK3CA) and one Tier 2 (PIK3CA) variant in one out of five benign nodules. The study demonstrated an NPV of 40 %, a PPV of 90 %, a specificity of 80 %, and a sensitivity of 60 %. CONCLUSION: Based on the detected molecular markers, at least nine patients (45 %) could be managed correctly without needing a repeat FNAB attempt. This study underscores the clinical practicality of molecular tests in managing nodules with indeterminate cytology. Additionally, this study emphasizes the importance of considering the patient's age when determining the DNA- or RNA-based genetic testing method. Finally, we discussed the significance of the somatic mutation profile and its impact on the current pathological classification.

Primary schwannoma of the thyroid gland: analysis of case characteristics and review of the literature.

BACKGROUND: To improve the characteristics of primary thyroid schwannomas (PTS) and to provide reference basis for clinical diagnosis and treatment. METHODS: PubMed was searched for case reports of PTS up to December 2022 using the search terms "Thyroid nerve sheath tumor" or "Thyroid schwannoma" or "Thyroid Neurilemmoma", respectively. 34 cases were screened. RESULTS: PTS can occur at any age, nodules averaged 3.9 cm. The most common symptoms were voice change and dysphagia. Fine needle aspiration cytology showing spindle-shaped cells should be considered for schwannoma. Most cases underwent thyroid lobectomy or nodule removal with a good prognosis. Tissue types with both Antoni A and Antoni B features are common. Positive immunohistochemical staining for S-100 protein, CD34 and waveform proteins helped confirm the diagnosis. CONCLUSIONS: Positive immunohistochemistry for S-100 and wave proteins helps confirm the diagnosis. Preoperative diagnosis is challenging, but pathology and immunohistochemical staining are the gold standard for diagnosis. The first choice of treatment is surgical resection of the nodules, the prognosis is good.

Parasitic colloid cyst: A diagnostic dilemma.

The pathologies of the neck are varied and at times may cause a diagnostic dilemma for the pathologist. In this report, we present a case of a 32-year-old man with a slow-growing nodular swelling in the right neck region, which was diagnosed as a simple colloid cyst arising in a parasitic thyroid nodule. Simple colloid cysts are cysts that develop due to impaired accumulation of thyroglobulin in inactive follicles. Most thyroid-related pathologies occur as midline swellings. However, the present case was unique due to its location with no connection to the thyroid gland. This case report describes the diagnostic process and adds insight into the pathology of a colloid cyst.

Predictive Value of the Nomogram Model Based on Multimodal Ultrasound Features for Benign and Malignant Thyroid Nodules of C-TIRADS Category 4.

To explore the predictive value of the nomogram model based on multimodal ultrasound features for benign and malignant thyroid nodules of C-TIRADS category 4. A retrospective analysis was conducted on the general conditions and ultrasound features of patients who underwent thyroid ultrasound examination and fine needle aspiration biopsy (FNA) or thyroidectomy at the Affiliated Hospital of Zunyi Medical University from April 2020 to April 2023. Predictive signs for benign and malignant nodules of thyroid C-TIRADS category 4 were screened through LASSO regression and multivariate logistic regression analysis to construct a nomogram prediction model. The predictive efficiency and accuracy of the model were assessed through ROC curves and calibration curves. Seven independent risk factors in the predictive model for benign and malignant thyroid nodules of C-TIRADS category 4 were growth pattern, morphology, microcalcifications, SR, arterial phase enhancement intensity, initial perfusion time, and PE [%]. Based on these features, the area under the curve (AUC) of the constructed prediction model was 0.971 (p ＜ .001, 95% CI: 0.952-0.989), with a prediction accuracy of 93.1%. Internal validation showed that the nomogram calibration curve was consistent with reality, and the decision curve analysis indicated that the model has high clinical application value. The nomogram prediction model constructed based on the multimodal ultrasound features of thyroid nodules of C-TIRADS category 4 has high clinical application value.

Outcomes of Differentiated Thyroid Cancer in Children and Adolescents at King Abdulaziz Medical City, Jeddah.

Objective Differentiated thyroid cancer (DTC) is rare in the pediatric population, with most data from the Western world. We aimed to describe the clinical presentation, treatment intervention, histopathological characteristics, complications, follow-up, and response to treatment in 17 patients with DTC at or below the age of 20 years. Interventions This was a retrospective cohort study at King Abdulaziz Medical City, Jeddah, Saudi Arabia. We included patients aged younger than 20 years with DTC. Total or near-total thyroidectomy was performed in 82% of the patients, central and/or lateral neck dissection in 35% of cases, and radioactive iodine (RAI) ablation in 76% of cases. Results The study included 17 patients (14 females), with a median age of 16 years at the time of diagnosis. Thyroid nodules were the main complaint in 88% of the patients. Thyroid ultrasonography was the main method for the initial evaluation. Papillary cancer was the most common type of tumor, and lymph node spread was found in 82% of the patients. Moreover, 40% of the patients exhibited excellent responses to therapy, with 35% showing indeterminate results. Only 23.5% of the patients developed hypocalcemia postoperatively. Conclusions Classical papillary thyroid carcinoma was the predominant histopathological type, and most patients showed excellent responses to therapy, followed by indeterminate in most of the cases. The most common presentation was a neck nodule, signifying the role of thorough physical neck examinations. Finally, recurrence occurred in a minority of patients. However, none of these patients died.

Combining Image similarity and Predictive AI Models to Decrease Subjectivity in Thyroid Nodule Diagnosis and Improve Malignancy Prediction.

OBJECTIVES: To evaluate the efficacy of combining predictive artificial intelligence (AI) and image similarity model to risk stratify thyroid nodules, using retrospective external validation study. METHODS: Two datasets were used to determine efficacy of the AI application. One was Stanford dataset ultrasound images of 192 nodules between April 2017 to May 2018 and the second was private practice consisting of 118 thyroid nodule images between January 2018 to December 2023. The nodules had definitive diagnosis by cytology or surgical pathology. The AI application was used to predict the diagnosis and American College of Radiology Thyroid Imaging and Data System (ACR TI-RADS) score. RESULTS: In the Stanford dataset, the AI application predicted malignancies with sensitivity of 1.0 and specificity of 0.55. Positive predictive value (PPV) was 0.18 and negative predictive value (NPV) was 1.0. The Area Under the Curve - Receiver Operating Characteristic (AUC-ROC) was 0.78. ACR TI-RADS based clinical recommendation had a polychoric correlation of 0.67. In the private dataset, the AI application predicted malignancies with sensitivity of 0.91 and specificity of 0.95. PPV was 0.8 and NPV was 0.98. AUC-ROC was 0.93 and accuracy was 0.94. ACR TI-RADS based score had a polychoric correlation of 0.94. CONCLUSION: The AI application showed good performance for sensitivity and NPV between the two datasets and demonstrated potential for 61.5% reduction in the need for fine needle aspiration (FNA) and strong correlation to ACR TI-RADS. However, PPV was variable between the datasets possibly from variability in image selection and prevalence of malignancy. If implemented widely and consistently among various clinical settings, this could lead to decreased patient burden associated with an invasive procedure and possibly to decreased health care spending.

Predictive value of the single most suspicious ultrasound feature in subcentimeter thyroid nodules: a retrospective observational cohort study.

PURPOSE: Proper management of subcentimeter thyroid nodules remains challenging for both clinicians and patients. Conducting extensive sonographic research using a safe and inexpensive tool for identifying thyroid nodules is necessary. The aim of this study was to identify whether having the highest-risk ultrasound (US) characteristic suggests that US-guided fine-needle aspiration (FNA) biopsy of subcentimeter nodules is more appropriate for the identification of malignancy than active surveillance (AS) or surgery. METHODS: The data of patients with highly suspicious subcentimeter thyroid nodules and US characteristic data who underwent surgery were retrospectively examined. RESULTS: Among a total of 556 subcentimeter nodules, 223 (40.1%) were benign, and 333 (59.9%) were malignant, with a mean maximal nodule size of 8.1 mm. In addition to age younger than 45 years, several US features were significantly associated with malignancy: irregular margins, the presence of microcalcifications, and taller-than-wide shapes (P < 0.001). Multivariate analysis also revealed that a taller-than-wide shape (OR = 8.988, P = 0.0015) was an independent factor associated with malignancy in subcentimeter thyroid nodules. The diagnostic performance of preoperative FNA was classified as a malignancy, with a sensitivity of 98.4%, specificity of 100%, positive predictive value of 100%, and negative predictive value of 76.9%. CONCLUSIONS: This is one of the few reports based on actual data of the most suspicious US features in subcentimeter thyroid nodules. A taller-than-wide shape US feature is most significantly associated with malignancy. FNA is a simple, accurate, and reliable preoperative method for diagnosing malignant subcentimeter thyroid nodules with highly suspicious US characteristics. AS was less appropriate than FNA for subcentimeter nodules with a taller-than-wide shape, especially in patients ≤ 45 years of age.

Individual Ultrasonographic Characteristics of Thyroid Nodules and Their Cytopathological Correlation to Determine Malignancy Risk.

Background Ultrasonographic evaluation of thyroid nodules is challenging due to their high frequency and low malignancy rate. The risk stratification system developed by the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) focuses on addressing the primary contemporary objectives for these lesions, aiming to decrease unnecessary biopsies while maintaining a similar specificity compared with other risk stratification systems. Generally, when indicative of malignancy by ultrasound findings, the next best step in management is an evaluation by fine needle aspiration biopsy (FNAB) and cytological analysis with The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) results that determine further evaluation requirements, actions that are based on the risk of malignancy (ROM) of the assigned category, which could include surgical intervention. Objectives To validate and analyze the individual impact of each ultrasonographic finding indicative of malignancy in the ACR TI-RADS guidelines based on their respective correlation with results obtained by TBSRTC. Materials and method Reports for 212 thyroid ultrasound-guided FNABs from 2018 to 2020 were assessed. Only 117 had both ACR TI-RADS and TBSRTC reports available and were analyzed. Nodules were divided into two groups: ROM < 5% (Bethesda 1, 2; n = 58), and ROM > 5% (Bethesda 3, 4, 5, 6; n = 59). Statistical analysis was performed using the x2 test and bivariate logistic regression model for each characteristic included in ACR TI-RADS. Results Individual ultrasound characteristics with a more pronounced distribution towards the Bethesda > 5% malignancy group were: solid or almost completely solid composition (n=53, 62.3%), very hypoechoic echogenicity (n=3, 75%), wider-than-tall shape (n=50, 50.5%), lobulated or irregular margin (n=23, 65.7%), punctate echogenic foci (n=18, 72%), and thyroid isthmus location (n=6, 75%). Statistically significant individual ultrasonographic characteristics indicative of malignancy included solid or almost completely solid (p = 0.005), very hypoechoic echogenicity (p = 0.046), margin lobulated or irregular (p = 0.031), and punctate echogenic foci (p = 0.015). No significant association was found in the taller-than-wide shape for differentiating malignant from benign lesions (p = 0.969). Conclusions Specific ultrasound characteristics identified in the ACR TI-RADS system demonstrate a stronger correlation with an increased risk of malignancy when compared with cytologic evaluation results. These characteristics include a solid composition, lobulated or irregular margins, punctate echogenic foci, and very hypoechoic echogenicity. Our findings revealed that the scale points for the taller-than-wide characteristic do not adequately represent its true influence on the risk of malignancy.

Vocal Fold Paralysis Following Benign Thyroid Nodule Laser Thermal Ablation.

Laser thermal ablation (LTA) is an increasingly common procedure to treat benign and malignant thyroid nodules, allowing patients to avoid thyroidectomy. There are few reported postprocedural complications of LTA among patients with benign thyroid nodules. While vocal fold paralysis is a well-known potential complication after thyroidectomy, we present the first case report of vocal fold paralysis following LTA. A female in her 80s presented to an outside endocrinologist with symptoms of hyperthyroidism and benign thyroid nodules. The patient underwent a fine needle aspiration biopsy, radioiodine uptake scan, radioactive thyroid ablation, and LTA at an outside institution. The patient first noticed hoarseness 2days after LTA, and she presented to our office with a weak, breathy voice more than 4months postprocedure. Videostroboscopic examination revealed immobility of the left vocal fold with incomplete glottic closure. After awake injection laryngoplasty in the office, the patient experienced voice improvement. In conclusion, LTA is a relatively new treatment modality with limited literature on adverse outcomes. As minimally invasive techniques such as LTA are becoming more common, it is essential to remain fully aware of risks to recognize and mitigate complications like vocal fold paralysis.

Thyroid Fine-Needle Aspiration: The Current and Future Landscape of Cytopathology.

Thyroid cytology is a rapidly evolving field that has seen significant advances in recent years. Its main goal is to accurately diagnose thyroid nodules, differentiate between benign and malignant lesions, and risk stratify nodules when a definitive diagnosis is not possible. The current landscape of thyroid cytology includes the use of fine-needle aspiration for the diagnosis of thyroid nodules with the use of uniform, tiered reporting systems such as the Bethesda System for Reporting Thyroid Cytopathology. In recent years, molecular testing has emerged as a reliable preoperative diagnostic tool that stratifies patients into different risk categories (low, intermediate, or high) with varying probabilities of malignancy and helps guide patient treatment.

Combing superb microvascular imaging with shear wave elastography for risk stratification of Thyroid Imaging Reporting and Data System (TI-RADS) 4 thyroid nodules.

Background: It is difficult to accurately assess the risk of Thyroid Imaging Reporting and Data System (TI-RADS) 4 thyroid nodules due to the overlap of benign and malignant conventional ultrasound (US) features of nodules. To reduce unnecessary needle biopsies and assist clinical decision-making, this study established a dynamic nomogram incorporating superb microvascular imaging (SMI) and shear wave elastography (SWE) for the risk evaluation of TI-RADS 4 thyroid nodules. Methods: A total of 248 patients who underwent US, SMI, and SWE with cytological or histopathological results were included in this retrospective study, and were randomly divided into training (174 patients) and verification (74 patients) cohorts. The clinical characteristics and US, SMI, and SWE features of patients were analyzed in the training cohort. The least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression were used to screen parameters and construct dynamic nomogram. The receiver operating characteristic (ROC) curves, calibration curve, and decision curve were used to evaluate the performance of the nomogram. Results: A dynamic nomogram was constructed based on age [odds ratio (OR) =0.954; P=0.005] , shape (OR =0.345; P=0.041), SMI (OR =9.511; P<0.001), and SWE (OR =3.670; P=0.001). The nomogram showed excellent discrimination both in the training [area under the curve (AUC): 0.848; 95% confidence interval (CI): 0.784-0.911] and validation (AUC: 0.862; 95% CI: 0.780-0.944) cohorts, and better than US, SMI, and SWE alone in all cohorts (P<0.05). The Nomo-score of each patient was calculated and the cut-off value was 0.607 which can be used to distinguish high-risk and low-risk patients. Conclusions: The SMI and SWE show added predictive value on risk stratification in patients with TI-RADS 4 thyroid nodules and a dynamic nomogram was constructed to screen high-risk individuals and assist the clinical decision-making.

Case Report: Plummer's adenoma in Prader-Willi syndrome.

Thyroid nodules in children are less common than in adults but they are approximately two- to three-fold more likely to be malignant in children. Among thyroid nodular diseases, Plummer's adenoma occurs very rarely in pediatrics, and currently, there is no literature providing evidence of this diagnosis in patients with Prader-Willi syndrome (PWS). We report the case of a 9-year-old Caucasian boy affected by PWS presenting with a rapidly growing palpable mass in the thyroid lodge associated with subclinical hyperthyroidism. Laboratory and other examinations (thyroid ultrasound, fine-needle aspiration of the nodule, and scintigraphy) were strongly suggestive for Plummer's adenoma; therefore, the patient underwent left hemithyroidectomy surgery, and anatomo-pathological examination confirmed the diagnosis. Our case describes the first evidence of an isolated follicular adenoma in children with PWS. Surgery is the only therapeutic option in younger children. Further evidence is needed to assess the possible correlation between these two conditions and the existence of potential risk factors.

Benign Thyroid Nodule Interventions: A Review and Imaging Considerations for the Interventional Radiologist.

Thyroid radiofrequency ablation (RFA) is a minimally invasive procedure that can be used to treat patients with benign thyroid nodules and is a good alternative to thyroidectomy or radioactive iodine. Thyroid RFA is commonly performed with local lidocaine or minimal/moderate sedation and has a minimal risk profile and few side effects. The efficacy of thyroid RFA has been well documented in the literature, with a volume reduction rate of 67 to 75% at 1 year. Another emerging technique for nodule size reduction is thyroid artery embolization which is a minimally invasive procedure that may be performed in patients with nodular goiters, particularly with substernal thyroid nodule extension, and who are either poor surgical candidates or do not want surgery. This article reviews thyroid RFA, focusing on the relevant preprocedural, procedural, and postprocedural imaging, as well as a discussion on the emerging role of thyroid artery embolization.

Comparison of clinical and patient-reported outcomes in patients with benign euthyroid solitary nodules after ultrasound-guided percutaneous microwave ablation and endoscopic thyroidectomy.

BACKGROUND: Percutaneous ultrasound-guided microwave ablation (MWA) for benign solid thyroid nodules is the newest modality for treatment. However, the differences in treatment outcomes between MWA and endoscopic thyroidectomy vestibular approach (TOETVA) for patients with benign euthyroid solitary nodules remain unknown. We are sharing initial results from our prospective study. METHODS: Prospective study between January 2022 and December 2023 was conducted and data were noted at 3 time points in patients planned for treatment (Preoperative, 1 week, and 12 months). Main outcome measures were clinical outcome and comparison of thyroid-related quality of life using the ThyPRO-39hin and swallowing-related quality of life using the SWAL-QoL. RESULTS: Of the 36 included patients, 20 patients underwent TOETVA and 16 underwent MWA. Both the groups were comparable in terms of demographic and clinicopathological profiles. The nodule volume reduction rate of patients at 12 months after MWA was 75.10% and 100% for TOETVA. The mean preoperative ThyPRO-39hin and SWAL-QoL scores were comparable in all domains between the two groups. Mean ThyPRO-39hin and SWAL-QoL scores on postoperative day 7 were significantly better in the MWA group in domains impaired social life (p < 0.0001) and impaired daily life (p = 0.0002). However, at the end of 12 months, mean ThyPRO-39hin and SWAL-QoL scores became significantly better in the TOETVA group as compared to the MWA group. CONCLUSION: Our findings suggest that transoral endoscopic thyroidectomy results in significant superior clinical outcome, thyroid-related quality of life, and swallowing-related quality of life in the long term.

Complications of ultrasound-guided thermal ablation of thyroid nodules and associated risk factors: an experience from 9667 cases.

OBJECTIVES: To evaluate the safety of ultrasound-guided thermal ablation (UGTA) for thyroid nodules (TNs) by analysing complications and related risks. MATERIALS AND METHODS: This retrospective, single-centre study reviewed patients who underwent UGTA (microwave or radiofrequency ablation) between January 2018 and March 2023. The incidence of complications was recorded and assessed during and immediately after ablation,1-3 h later, and at 1 month, 3 months, and 6 months. Univariate and multivariate analyses were performed to identify risk factors for hoarseness and haemorrhagic complications. RESULTS: We reviewed 9667 cases in this study. Overall, 4494 (46.49%) cases underwent microwave ablation, while 5173 (53.51%) cases underwent radiofrequency ablation. The overall complication rate was 4.43%. The incidence of major complications was 1.94% (haemorrhage, 1.32%; hoarseness, 0.54%; and symptomatic aseptic necrosis, 0.08%). The incidence of minor complications was 2.45%. A large nodule volume, radiofrequency ablation, hyper-enhancing nodules, benign nodules, higher preoperative blood pressure, hyperthyroidism, and higher ablation power were independent risk factors for haemorrhage. Dorsal nodules and a higher ablation power were independent risk factors for hoarseness. All complications were resolved. CONCLUSION: This study suggests that UGTA is a safe treatment for TNs. Several risk factors for haemorrhage and hoarseness should be considered before performing UGTA. Different ablation modalities should be considered for patients with different conditions. CLINICAL RELEVANCE STATEMENT: Thermal ablation may be a safe treatment for eligible patients with TNs. KEY POINTS: We analysed the complications and risk factors associated with UGTA in 9667 cases. The complication rate was 4.43%; 1.94% were major complications. Risk factors of haemorrhage and hoarseness should be considered. UGTA was a safe method for the treatment of TNs.

DAC-Net: A light-weight U-shaped network based efficient convolution and attention for thyroid nodule segmentation.

Recently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of increasingly complex modules, such as the Transformer, leading to models with a higher number of parameters and computing requirements. Sophisticated models have difficulties in being implemented in clinical medicine platforms because of limited resources. DAC-Net is a Lightweight U-shaped network created to achieve high performance in segmenting thyroid nodules. Our method consists of three main components: DWSE, which combines depthwise convolution and squeeze-excitation block to enhance feature extraction and connections between samples; ADA, which includes Split Atrous and Dual Attention to extract global and local feature information from various viewpoints; and CSSC, which involves channel- scale and spatial-scale connections. This module enables the fusing of multi-stage features at global and local levels, producing feature maps at different channel and geographical scales, delivering a streamlined integration of multi-scale information. Combining these three components in our U- shaped design allows us to achieve competitive performance while also decreasing the number of parameters and computing complexity. Several experiments were conducted on the DDTI and TN3K datasets. The experimental results demonstrate that our model outperforms state-of-the-art thyroid nodule segmentation architectures in terms of segmentation performance. Our model not only reduces the number of parameters and computing expenses by 73x and 56x, respectively, but also exceeds TransUNet in segmentation performance. The source code is accessible at https://github.com/Phil-y/DAC-Net.

Functional structure of a high resolution thyroid nodule unit. Economic impact and results of its implementation in an Endocrinology department.

BACKGROUND AND OBJECTIVE: The high incidence of nodular thyroid pathology has led to growing concern about the economic impact that this pathology represents on the healthcare system. There are conclusive data about the cost-effectiveness of high-resolution units for nodular thyroid pathology; however, their implementation is not homogeneous in the Endocrinology and Nutrition services of our country. The objective of the present study was to evaluate the economic impact of the implementation of the high-resolution thyroid nodule unit (HRTNU) in our center. PATIENTS AND METHODS: The present work is a prospective, observational and descriptive study carried out in 1314 patients (82% women, mean age 58 years ds = 11) evaluated at the HRTNU during the period of August 2022-August 2023. Demographic data (age and sex) were analyzed, referral center and consultation type, number of total consultations and neck ultrasound performed, number of fine needle aspiration (FNAB) performed, and cytology results were analyzed. RESULTS: In the period from August 2022 to August 2023, a total of 1314 patients were evaluated (neck ultrasound and clinical consultation) and a total of 133 FNAB were performed, of which only 2.26% were non-diagnostic. Compared to the percentage of unsatisfactory FNAB from the previous year August 2021-July 2022 of 25%, a mean saving of 9931.43 euros was estimated. 84.47% of the patients evaluated for the first time by the HRTNU were discharged, estimating a mean saving of 133,200 euros. CONCLUSIONS: The implementation of a HRTNU at the Endocrinology and Nutrition departments, coordinated with primary and specialized care, is a cost-effectiveness alternative, as it reduces the number of medical consultations and is accompanied by a higher rate of diagnostic FNAB.

Serum trace elements show association with thyroperoxidase autoantibodies in Thyroid Imaging Reporting and Data System (TI-RADS) 4 nodules.

Thyroid nodule (TN) has been becoming a great concern worldwide due to its high incidence. Although some studies have reported associations between trace elements exposure and the risk of TNs, the linkage was not inconclusive. The present study aimed to identify the association of selected serum trace elements (Ca, Mg, V, Fe, Co, Cu, Zn, Se, Mn and Mo) with TNs among general adults. A cross-sectional study was conducted in January 2021 in Chengdu, China. 1282 subjects completed the questionnaire and gave at least one human biological material after an overnight fast, venous blood, and urine, including 377 TN participants defined through ultrasound. Various trace elements in serum specimens were determined by inductively coupled plasma mass spectrometry. Thyroid functions were tested by chemiluminescent microparticle immunoassay (CMIA). The associations between trace elements levels and the risk of TNs were examined by restricted cubic splines (RCS) regression and bayesian kernel machine regression (BKMR) models. TNs were more common in females (P < 0.001) and in the elderly (P < 0.001) and that they were also frequently associated with fertility, marital status, annual household income, drinking, anxiety, vitamin supplement, tea consumption, hypertension and hyperlipidemia. After adjusting for confounders by a propensity score matching model, the association between trace elements concentrations and TNs risk was found to be statistically insignificant in the RCS (P for nonlinear > 0.05) and BKMR models. FT3 or T4 (total or free) increased significantly with increasing total trace elements mixture levels. In TI-RADS-4 TN subjects, TPO-Ab level increased significantly with increasing total trace elements mixture levels in the high-dose range. Ca, Zn, Mo at their 75th percentile showed positive individual effects on TPO-Ab, which was examined to be interactive. The detection of trace elements for TNs in general adults may be of no significance, but once individuals classified as TI-RADS-4 TNs are detected with abnormal TPO-Ab, Ca, Zn and Mo level are recommended to measure. The substantive association on it still needs to be continuously explored in the future.

Automatic Classification of Nodules from 2D Ultrasound Images Using Deep Learning Networks.

OBJECTIVE: In clinical practice, thyroid nodules are typically visually evaluated by expert physicians using 2D ultrasound images. Based on their assessment, a fine needle aspiration (FNA) may be recommended. However, visually classifying thyroid nodules from ultrasound images may lead to unnecessary fine needle aspirations for patients. The aim of this study is to develop an automatic thyroid ultrasound image classification system to prevent unnecessary FNAs. METHODS: An automatic computer-aided artificial intelligence system is proposed for classifying thyroid nodules using a fine-tuned deep learning model based on the DenseNet architecture, which incorporates an attention module. The dataset comprises 591 thyroid nodule images categorized based on the Bethesda score. Thyroid nodules are classified as either requiring FNA or not. The challenges encountered in this task include managing variability in image quality, addressing the presence of artifacts in ultrasound image datasets, tackling class imbalance, and ensuring model interpretability. We employed techniques such as data augmentation, class weighting, and gradient-weighted class activation maps (Grad-CAM) to enhance model performance and provide insights into decision making. RESULTS: Our approach achieved excellent results with an average accuracy of 0.94, F1-score of 0.93, and sensitivity of 0.96. The use of Grad-CAM gives insights on the decision making and then reinforce the reliability of the binary classification for the end-user perspective. CONCLUSIONS: We propose a deep learning architecture that effectively classifies thyroid nodules as requiring FNA or not from ultrasound images. Despite challenges related to image variability, class imbalance, and interpretability, our method demonstrated a high classification accuracy with minimal false negatives, showing its potential to reduce unnecessary FNAs in clinical settings.