Our objective is to develop and validate a deep learning radiomics nomogram (DLRN) based on preoperative ultrasound images and clinical features, for predicting the malignancy of thyroid nodules with indeterminate cytology (Bethesda III).

Between June 2017 and June 2022, we conducted a retrospective study on 194 patients with surgically confirmed indeterminate cytology (Bethesda III) in our hospital. The training and internal validation cohorts were comprised of 155 and 39 patients, in a 7:3 ratio. To facilitate external validation, we selected an additional 80 patients from each of the remaining two medical centers. Utilizing preoperative ultrasound data, we obtained imaging markers that encompass both deep learning and manually radiomic features. After feature selection, we developed a comprehensive diagnostic model to evaluate the predictive value for Bethesda III benign and malignant cases. The model's diagnostic accuracy, calibration, and clinical applicability were systematically assessed.

The results showed that the prediction model, which integrated 512 DTL features extracted from the pre-trained Resnet34 network, ultrasound radiomics, and clinical features, exhibited superior stability in distinguishing between benign and malignant indeterminate thyroid nodules (Bethesda Class III). In the validation set, the AUC was 0.92 (95% CI: 0.831-1.000), and the accuracy, sensitivity, specificity, precision, and recall were 0.897, 0.882, 0.909, 0.882, and 0.882, respectively.

The comprehensive multidimensional data model based on deep transfer learning, ultrasound radiomics features, and clinical characteristics can effectively distinguish the benign and malignant indeterminate thyroid nodules (Bethesda Class III), providing valuable guidance for treatment selection in patients with indeterminate thyroid nodules (Bethesda Class III).

This study aims to compare the diagnostic efficiency of the American College of Radiology-Thyroid Imaging, Reporting, and Data System (ACR-TIRADS), fine-needle aspiration (FNA) cytopathology alone, and the dynamic artificial intelligence (AI) diagnostic system.

A total of 1035 patients from three hospitals were included in the study. Of these, 590 were from the retrospective dataset and 445 cases were from the prospective dataset. The diagnostic accuracy of the dynamic AI system in the thyroid nodules was evaluated in comparison to the gold standard of postoperative pathology. The sensitivity, specificity, ROC, and diagnostic differences in the κ-factor relative to the gold standard were analyzed for the AI system and the FNA.

The dynamic AI diagnostic system showed good diagnostic stability in different ages and sexes and nodules of different sizes. The diagnostic AUC of the dynamic AI system showed a significant improvement from 0.89 to 0.93 compared to ACR TI-RADS. Compared to that of FNA cytopathology, the diagnostic efficacy of the dynamic AI system was found to be no statistical difference in both the retrospective cohort and the prospective cohort.

The dynamic AI diagnostic system enhances the accuracy of ACR TI-RADS-based diagnoses and has the potential to replace biopsies, thus reducing the necessity for invasive procedures in patients.

The diagnostic care pathway of thyroid nodules spans multiple institutions. Collaborative networks are important to deal with such pathways that result from centralization and differentiation of care. Despite the high prevalence of thyroid nodules and the increase in cancer diagnoses, most nodules are benign and attributable to overdiagnosis, leading to an increase in fine-needle aspirations (FNAs). This study assessed the effectiveness of a multi-hospital network that implemented a unified thyroid care pathway in reducing the number of FNAs without compromising malignancy detection. In this nationwide population-based cohort study, Bethesda scores were extracted from all thyroid FNA reports from 2010 to 2021 in the Netherlands using text mining. Trends in the number of FNAs and Bethesda scores were visualized for the network and the rest of the country. Joinpoint analyses with the Davies test determined the statistical significance of observed trend changes. Nationwide, FNAs increased by an average of 5.7% annually from 2010 to 2018. In the network, FNAs started to decrease in 2016-2017, coinciding with the care pathway implementation (p < 0.001). In contrast, in the rest of the Netherlands, a decline was observed in 2020, potentially attributable to the COVID-19 pandemic. In both cases, the reduction mainly involved Bethesda categories 1 and 2, without compromising malignancy detection. High-volume surgical centers seemed to initiate a decline more rapidly compared to non-high-volume surgical centers. This study indicates that a unified care pathway within a multi-hospital network can reduce the number of FNAs without compromising malignancy detection, which could alleviate the burden on both patients and the healthcare system.

Castleman disease (CD) is a rare lymphoproliferative disorder of unknown etiology characterized by lymph node enlargement. CD cannot be confirmed by preoperative puncture cytology, and definitive diagnosis depends on postoperative histopathology. Due to the lack of characteristic clinical manifestations and imaging features, in clinical practice, CD is often easily missed or misdiagnosed, and it is frequently mistaken for lymphoma or autoimmune diseases. Cases of CD that coexist with papillary thyroid carcinoma (PTC) are particularly rare and are often misdiagnosed as PTC with lymph node metastasis. The present study discusses the diagnosis, treatment process and prognosis of a case involving PTC that is complicated with unilateral, single-center CD. This patient was diagnosed with a right lobe nodal gland of the thyroid gland combined with a mass in the left supraclavicular fossa. The postoperative pathological examination revealed a right lobe papillary carcinoma of the thyroid gland with metastasis of the right cervical lymph node combined with CD in the left supraclavicular fossa. The immunohistochemical results of the right cervical lymph node were thyroglobulin (+), thyroid transcription factor-1(+). Immunohistochemical results of left supraclavicular fossa mass: Bcl-2 (low expression in the germinal center, high expression outside), Bcl-6 (germinal center +), Cyclin D1 (-), cluster of differentiation 38 (focally+). In future clinical practice, when encountering PTC with mediastinal masses, clinicians should consider not only common lymph node metastases but also the possibility of CD. Overall, this study aims to provide valuable insights and experience for clinicians regarding CD and PTC.

Objective: Indeterminate cytology (Bethesda III and IV) represents 15-30% of biopsied thyroid nodules and require additional diagnostic testing. Molecular testing (MT) is a commonly used diagnostic tool that evaluatesmalignancy risk through next generation sequencing of fine needle aspiration (FNA) samples. While MT achieves high sensitivity (97-100%) in ruling out malignancy, its specificity and positive predictive value (PPV) remain relatively low. This study proposes a multimodal deep learning model that integrates ultrasound (US) imaging with MT to improve risk stratification by enhancing PPV while maintaining high sensitivity. Combining these modalities leverages complementary information from both molecular and imaging data, addressing limitations in current approaches and offering a robust framework for evaluating indeterminate nodules. Methods: We retrospectively analyzed 333 patients with indeterminate thyroid nodules (259 benign, 74 malignant) at UCLA Medical Center between 2016 and 2022. We evaluated four configurations: whole frame US images, 256 × 256 patches, 128 × 128 patches, and an ensemble model combining the first three configurations. The clinical baseline consisted of Bethesda cytology and MT results. Models were assessed using five fold cross validation stratified by surgical outcomes. Results: The clinical baseline (Bethesda + MT) achieved an AUROC of 0.728 [0.68, 0.78] with sensitivity of 0.946 [0.88, 1.00], specificity of 0.664 [0.60, 0.73], and PPV of 0.448 [0.41, 0.48]. The proposed ensemble model demonstrated improved performance, achieving an AUROC of 0.831 [0.77, 0.89] with a sensitivity of 0.946 [0.88, 1.00], specificity of 0.703 [0.66, 0.75], and PPV of 0.477 [0.46, 0.50]. These improvements were statistically significant (p = 0.0008). Conclusion: Our multimodal model enhances MT performance by providing statistically significant improvements in PPV and specificity while maintaining high sensitivity. Our framework could be leveraged to reduce the number of benign thyroid resections in patients with indeterminate nodules. However, this study is limited by its single center dataset, lack of external validation, and the use of binarized MT outputs rather than granular malignancy risk probabilities. Future work should validate these findings across diverse populations and larger external datasets for more comprehensive risk stratification.

In recent decades, the diagnosis of thyroid cancer, especially the papillary type, has increased significantly due to the use of imaging techniques such as ultrasound. For this reason, it is essential to rationalize diagnosis and treatment, since the behavior of thyroid cancer varies from slow-progressing tumors to highly aggressive ones. The application of risk assessment systems for ultrasound images and the optimization of cytology incorporating molecular studies allows cases to be stratified in order to select therapy on an individual basis. Currently, attempts are being made to avoid overtreatment in low-risk tumors, with active surveillance or minimally invasive techniques. The administration of radioiodine is indicated according to risk, with lower doses, and in advanced cases, oncospecific systemic treatments are being incorporated. The management of thyroid cancer requires a multidisciplinary team and population studies and quality clinical trials are necessary to update treatment guidelines.

Identifying aggressive variants of throid papillary carcinoma correctly is paramount, as their diagnosis requires more extensive surgical interventions. Numerous cytologic scoring systems have been proposed to distinguish non-aggressive from aggressive variants. Oncocytic morphology is characterised by cells with abundant granular cytoplasm resulting from mitochondrial accumulation. This feature is particularly prominent in specific PTC variants. Tall cell and hobnail variants are aggressive variants with oncocytic morphology. The present study aims to evaluate the cytomorphological features of 51 histologically confirmed papillary thyroid carcinoma (PTC) cases with oncocytic morphology and to identify cytological features that could facilitate the distinction between aggressive (tall cell and hobnail) and non-aggressive (oncocytic and Warthin-like) variants during the FNA stage, thereby enabling early detection of aggressive variants.

We retrospectively examined the cytological features of cases diagnosed with histologically confirmed aggressive variants with poor prognosis (tall cell and hobnail) and non-aggressive variants with good prognosis (oncocytic and Warthin-like), obtained from the pathology department of our hospital between 2014 and 2020.

39 cases (76.5%) classified into the good prognosis group, which included oncocytic variant (O-PTC) (33 cases) and Warthin-like variant (WL-PTC) (6 cases). The poor prognosis group included 12 cases (23.5%), comprising hobnail variant (HN-PTC) (2 cases) and tall cell variant (TC-PTC) (10 cases). The swirl pattern was significantly more frequent in the poor prognosis group (83.3% vs. 43.6%, p = 0.022), with a sensitivity of 83.3% and specificity of 56.4%. The presence of nuclear grooves was observed in all cases of the poor prognosis group (100%) while in 61.5% of the good prognosis group (p = 0.011). This feature exhibited 100% sensitivity and 38.4% specificity. Concerning cytoplasmic volume, scant-medium amount cytoplasmic volume was significantly more common in the poor prognosis group (66.7% vs. 20.5%, p = 0.005), showing 66.7% sensitivity and 79.4% specificity, and yielding the highest accuracy rate (76.4%) among all characteristics.

Oncocytic morphology-based approaches may help identify poor prognosis variants and guide clinical decisions. In our study, cellular swirls, grooves and scant-medium cytoplasmic volume were the most significant cytological indicators for identifying poor prognosis variants. Despite previous emphasis on cell width/height ratio and foamy INCIs for TC-PTC diagnosis, no significant differences were found between the two groups in our study.

To determine the malignancy risk of thyroid nodules with Isolated Macrocalcifications (IMC) based on surgical results and evaluate the postoperative risk of malignant nodules with IMC.

A total of 46 thyroid nodules with IMC were enrolled from 3680 consecutive patients who underwent thyroidectomy between August 2018 and September 2023. The malignancy risk of IMC nodules, postoperative risk of malignant nodules, and whether the ultrasonic features of IMC (smooth, lobulated, or focal disruption of the anterior margin) were associated with malignancy were investigated. The nodules were further divided into three groups (group A, maximum diameter < 10 mm; group B, maximum diameter of 10‒14 mm and group C, maximum diameter ≥ 15 mm). Differences in malignancy and Lymph Node Metastasis (LNM) risks were also evaluated among the three groups.

The malignancy risk of the IMC nodules was 30.43% (14/46). Four patients developed LNM. Eight nodules were staged as T1aN0M0 and low-risk, whereas six nodules were staged as T1bN1aM0 and intermediate-risk. Focal disruption of the anterior margin of IMC was significantly associated with malignancy. Malignant and LNM risk showed no differences among nodules with different sizes.

IMC nodules with different sizes had a lower intermediate risk of malignancy and exhibited the same aggressive behavior. The cutoff value of these nodules for further Fine Needle Aspiration (FNA) warranted further investigation. Interruption of IMC was more often seen in malignant nodules, and more attention should be paid to these nodules.

The 2023 revision of the Bethesda System for Reporting Thyroid Cytopathology (BSRTC) simplified the subcategorization of category III into two groups: "AUS-nuclear" and "AUS-other". The aim of this study was to investigate the risk of malignancy (ROM) of individual BSRTC categories with a particular emphasis on the "AUS-nuclear" and "AUS-other" subcategories and to check whether the low-risk follicular-cell-derived thyroid neoplasm (LRTN) interpretation or EU-TIRADS class of the nodule modify ROM.

The analysis covered the FNA results of 18,225 nodules in 12,470 patients. The rate of malignancy (the upper limit of ROM) was established on the basis of the assessment of 1660 nodules treated surgically in 978 patients.

In the broadest variant, with all LRTNs regarded as malignant, the ROM for subsequent categories was as follows: I: 0.4-3.5%, II: 0.1-1.3%, III: 3.8-17.7%, IV: 23.3-27.8%, V: 79.6-90.1%, and VI: 86.3-100.0%. In AUS-nuclear nodules, the ROM was 10.5-28.9%, while in AUS-other nodules, it was 2.2-12.2%. The exclusion of NIFTP or all LRTNs from cancers mainly affected the ROM of AUS-nuclear nodules: 9.4-25.9% or 8.6-23.7%, respectively. EU-TIRADS 5 class increases the ROM in AUS-nuclear nodules to 78.3%, OR: 15.7 and in AUS-other to 40.7%, OR: 6.6.

The 2023 BSRTC is a welcome step towards simplification of the way nodules are classified within category III. The AUS-nuclear subcategory is associated with a two-times-higher incidence of malignancy than the AUS-other regardless of LRTN interpretation and EU-TIRADS class of the nodule. The EU-TIRADS 5 class of the nodule is helpful in the identification of category III nodules with a high risk of malignancy.

To compare the diagnostic outcomes of core needle biopsy (CNB) and fine-needle aspiration (FNA) using Bethesda IV as a test-positive criterion for diagnosing follicular-patterned neoplasms in a large multicenter cohort.

This retrospective study included 5463 thyroid nodules ≥1 cm from 4883 patients (4019 females, 864 males; mean age 53.8 years) that underwent FNA or CNB across 26 hospitals in Korea between June and September 2015. The final diagnosis in cases diagnosed as Bethesda IV (follicular neoplasm) in biopsies were confirmed by surgical pathology. The primary study outcome was the diagnostic yield, defined as the proportion of nodules with follicular-patterned neoplasms confirmed at surgery after receiving Bethesda IV results on biopsy (FNA or CNB), among all that underwent biopsy. Secondary outcomes included false referral rate (FRR) and positive predictive value (PPV). All nodules were analyzed before matching (823 and 4640 nodules for CNB and FNA, respectively) and after nodule matching in a 1:2 ratio (799 and 1571 nodules, respectively) according to age, sex, nodule size, and Korean Thyroid Imaging Reporting and Data System (K-TIRADS) category. Additionally, the diagnostic yields of various histological subtypes of follicular-patterned neoplasms and nodule subgroups were analyzed.

CNB demonstrated a significantly higher diagnostic yield than FNA both before (9.0% vs. 0.5%; P < 0.001) and after matching (9.0% vs. 0.6%; P < 0.001). CNB consistently had higher diagnostic yields than FNA for most histological subtypes and all subgroups. FRR was not significantly different between the CNB and FNA groups after matching (0.4% vs. 0.1%; P = 0.337). The PPV was consistently greater than 90% for both methods, with no significant difference.

CNB had a higher diagnostic yield than FNA for follicular-patterned neoplasms, with no significant difference in FRR using Bethesda IV as the test-positive criterion.

Value-Based Health Care (VBHC) implementation motivates providers to reduce unnecessary procedures to improve outcomes and costs, i.e.

In thyroid cancer care, adequate use of Fine Needle Aspiration (FNA) may prevent downstream diagnostics, costs, and delays in the care process. This study aims to evaluate the impact of needle selection in FNA on Bethesda I classifications, duration of FNA appointments, and care utilization.

In October 2021, a Modified Menghini-type needle needle replaced the regular syringe needle used for FNA. An interrupted time series (ITS) analysis using generalized linear models was conducted with data from radiology and pathology reports coupled with care utilization data at the patient level. Outcomes included frequency of Bethesda I classifications per month, appointment time, and health care utilization in the first patient year (in 2024€).

Between July 2020 and May 2022, 345 FNA in 224 patients were included. Implementation of the Modified Menghini-type needle needle was associated with a 78% level decrease in the odds of Bethesda I classification during FNA (OR (95% CI) 0.22 (0.06;0.71)), and, on average, a 4% (1.25 min) reduction in FNA appointment time. Despite a higher FNA unit cost postintervention (additional cost of €17.56 per FNA), there were no changes in the diagnostic and overall costs.

VBHC implementation provides the tools to identify and monitor improvement projects that enhance the value of thyroid nodule diagnostics and management. Implementing a Modified Menghini-type needle needle in FNA resulted in increased adequate diagnostic results, time savings, and no changes in diagnostic and care costs.

Not applicable.

Pelvic and peritoneal washings (PW) are often taken during gynecologic resections when the presence of a neoplastic process is known or suspected. A positive PW may upstage a patient and/or impact a patient's prognosis and treatment. Two surveys were created to inform The International System for Serous Fluid Cytology, a standardized reporting system, regarding the practice and utilization of PW cytology.

Pathologists and cytotechnologists (n = 475) responded to a survey which examined their reporting preferences. Gynecologic oncologists (GONC) (n = 168) answered a separate survey which examined how they utilized PW specimens.

Most pathologists/cytotechnologists felt that bland-appearing epithelial cells of unknown origin should be classified as benign. Most favored reporting psammomatous calcification without associated epithelial cells as benign (64.1%), whereas 8.6% did not report this finding at all, 20.5% would report as atypical, and 6.8% would report as suspicious of a neoplasm. Most GONCs (63.9%) routinely obtained PW specimens during endometrial cancer staging; of those, 53% reported that a positive cytology result could change their management. Sixty-six percent of GONCs indicated that they treat indeterminate PW results as negative. Others indicated that an indeterminate PW may result in review of slides with the pathologist, counseling the patient, and/or closer observation. Most GONCs did not find utility in the reporting of psammomatous calcifications, presence of mucin, atypical cells favored to be benign, endometrial cells, or iatrogenic material.

Substantial variability exists among pathologists in how PW specimens are reported, as well as how gynecologic oncologists utilize these specimens.

The number of thyroid cancer diagnoses has been increasing for several decades, with a significant part of cases being detected incidentally (thyroid incidentaloma, TI) by imaging studies performed for reasons other than thyroid disease, including PET/CT with [18F]FDG. The chacteristics of the detected TI cannot be determined solely on the basis of conventional parameters used in everyday clinical practice, such as SUVmax. In recent years, there has been a growing interest in radiomics, which is a quantitative method of analyzing radiological images based on the analysis of image texture. Textural analysis may be helpful, as it allows to characterize features invisible to the physician with the naked eye.

Of the 54 patients who presented focal [18F]FDG-avid TI and had subsequent fine needle aspiration biopsy, 4 patients were excluded from the analysis due to the unavailability of the final diagnostic information. Hence, in the final analysis, data from 50 patients were used (39 females and 11 males) with a mean age of 58.5 ± 11.26. Of these 50 patients, 11 (22.0%) [18F]FDG-avid nodules were diagnosed as malignant. The performance of the XGBoost model in assessing [18F]FDG-avid TI was similar (0.846 [confidence interval, CI, 95% 0.737-0.956]) to SUVmax (0.797 [CI 95%: 0.622-0.973]; p = 0.60).

With an AI-based algorithm using radiomics features it is possible to detect the malignancy of thyroid nodule. However, no statistically significant differences were observed between the AI and radiomics approach, and when using a conventional measure, i.e., SUVmax.

To compare the diagnostic value of ACR Thyroid Imaging Reporting and Data System (TI-RADS), K-TIRADS, and C-TIRADS in Bethesda III/IV thyroid nodules.

This single-center retrospective study classified 80 Bethesda stage III/IV thyroid nodules from 80 patients between January 2020 and July 2023 according to three different systems. Diagnostic performance was evaluated using receiver operating characteristic curves, with histopathological diagnosis serving as the reference standard.

Overall, 41/80 (51.2%) nodules were malignant and 39/80 (48.8%) were benign. The malignancy rates for Bethesda type III and IV nodules were 50.7% and 55.6%, respectively. The malignancy risk in thyroid nodules increased with higher TI-RADS categories (P<0.001). Optimal cutoff values for ACR-, K-, and C-TIRADS were categories 5, 5, and 4C, respectively. Area under the curve (AUC) for ACR-, K-, and C-TIRADS was 0.782, 0.767, and 0.842, respectively, with C-TIRADS showing a significantly higher AUC than ACR-TIRADS and K-TIRADS (all P<0.05). C-TIRADS demonstrated the highest sensitivity, accuracy, and positive predictive value, whereas ACR TI-RADS showed the highest specificity and negative predictive value. Furthermore, the AUC, sensitivity, specificity, and accuracy of ACR TI-RADS, K-TIRADS, and C-TIRADS were higher in nodules >1 cm than in those ≤ 1 cm."

All three TI-RADS systems have diagnostic value in differentiating benign from malignant Bethesda III/IV nodules, With C-TIRADS showing the highest area under the curve(AUC), suggesting its potential utility in clinical evaluation and management of such nodules, particularly in Chinese populations.

Variations in hue and contrast are common in H&E-stained pathology images due to differences in slide preparation across various institutions. Such stain variations, while not affecting pathologists much in diagnosing the biopsy, pose significant challenges for computer-assisted diagnostic systems, leading to potential underdiagnosis or misdiagnosis, especially when stain differentiation introduces substantial heterogeneity across datasets from different sources. Traditional stain normalization methods, aimed at mitigating these issues, often require labor-intensive selection of appropriate templates, limiting their practicality and automation. Innovatively, we propose a Learnable Stain Normalization layer, i.e. LStainNorm, designed as an easily integrable component for pathology image analysis. It minimizes the need for manual template selection by autonomously learning the optimal stain characteristics. Moreover, the learned optimal stain template provides the interpretability to enhance the understanding of the normalization process. Additionally, we demonstrate that fusing pathology images normalized in multiple color spaces can improve performance. Therefore, we extend LStainNorm with a novel self-attention mechanism to facilitate the fusion of features across different attributes and color spaces. Experimentally, LStainNorm outperforms the state-of-the-art methods including conventional ones and GANs on two classification datasets and three nuclei segmentation datasets by an average increase of 4.78% in accuracy, 3.53% in Dice coefficient, and 6.59% in IoU. Additionally, by enabling an end-to-end training and inference process, LStainNorm eliminates the need for intermediate steps between normalization and analysis, resulting in more efficient use of hardware resources and significantly faster inference time, i.e up to hundreds of times quicker than traditional methods. The code is publicly available at https://github.com/yjzscode/Optimal-Normalisation-in-Color-Spaces.

To propose a simplified histological classification for core-needle biopsy (CNB) of thyroid nodules with four diagnostic categories (DC) and provide the risk of malignancy (ROM) and the expected incidence for each DC. There is no uniform scheme for categorizing CNB specimens, except for a Korean diagnostic classification similar to the Bethesda system for FNAC.

Data from a single institution using CNB as a routine diagnostic tool for thyroid nodules. Biopsies were classified as non-diagnostic, benign, follicular tumour (FT) or malignant. The frequency of each DC and the correlation with surgical pathology of nodules undergoing surgery after CNB were evaluated.

Of 6284 CNBs on 5782 nodules [195 (3.1%) non-diagnostic, 5043 (80.3%) benign, 435 (6.9%) FT and 611 (9.7%) malignant], 1914 nodules (33.1%) underwent surgery after 2016 CNBs: 48 non-diagnostic, 1035 benign, 355 FT and 578 malignant. Malignancy was diagnosed after surgery in 11 non-diagnostic (ROM: 22.9%), 23 benign (ROM: 2.2%), 44 FT (ROM: 12.4%, 11.5% excluding low-grade malignancy) and 568 malignant CNBs (ROM: 98.3%, 93.8% excluding low-grade malignancy). Sensitivity and positive predictive value for malignancy of FT or malignant CNB were 94.7% and 65.6%, and for thyroid neoplasm (adenoma or carcinoma) were 93.2% and 92.6%.

Our diagnostic classification for CNB of thyroid nodules has a high diagnostic accuracy with a low rate of indeterminate categories. This classification, applied in a Western practice, shows a low ROM for nodules classified as follicular tumours, which could be improved with immunohistochemical studies.

There has been remarkable growth in our understanding of the biologic behavior and molecular signature of thyroid malignancies, which has led to the introduction, application, and evolution of molecular testing of thyroid nodule FNA cytology. Next-generation sequencing molecular testing is an important, well-validated diagnostic tool for management of cytologically indeterminate thyroid nodules. It reduces unnecessary thyroid surgery for benign disease, avoiding associated surgical risks for the patient and reducing healthcare expenses. This article reviews the development and implementation of thyroid nodule cytologic classification and subsequent testing and how it has improved the diagnostic considerations in thyroid nodule and thyroid cancer management algorithms. The use of molecular testing as a prognostic tool is evolving and although the data are limited, they suggest a promising role in prognostication for oncologic outcomes. However, future studies are needed to further evaluate this.

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.

To assess the efficacy and safety of thermal ablation (TA) in managing follicular thyroid neoplasms (FN).

This multicenter retrospective study involved participants diagnosed with FN across nine hospitals, undergoing microwave ablation or radiofrequency ablation from January 2014 to January 2024. Primary outcomes assessed were technical success and disease progression, with secondary outcomes including tumor size and volume changes, complete tumor disappearance, complications, and side effects. Subgroup analyses aimed to identify factors influencing tumor progression and complete disappearance.

The study enrolled 375 patients (mean age: 43.2 years ± 14.9 [standard deviation]; 298 women) with 482 FNs, tracked over an average of 23.6 months, achieving a 100% technical success rate. Disease progression was observed in 4.8% (18/375) of patients, with a local recurrence rate of 3.7% (14/375) and new neoplasm occurrence of 1.1% (4/375). Multifocal neoplasms emerged as an independent risk factor for disease progression (hazard ratio [HR], 3.48; 95% CI, 1.16-10.45; P = 0.026). Tumor volume significantly reduced (P < 0.001), particularly within 1-3 months post-ablation, with complete tumor disappearance observed in 10.4% (39/375) of cases, more likely in tumors smaller than 2 cm (HR, 0.11; 95% CI, 0.06-0.23; P < 0.001). Complications occurred in 2.9% of patients, with major events in 2.1% and minor in 0.8%.

TA is a safe and efficacious method for treating FN, showing low rates of disease progression and complications. Optimal outcomes may be achieved in patients with unifocal FN and neoplasms under 2 cm.

The authors sought to assess whether the age of 18 reflects a true pathological inflection point that justifies transitioning between pediatric and adult paradigms of care with differentiated thyroid cancer (DTC).

A retrospective chart review was conducted for patients aged 12-24 undergoing hemithyroidectomy or total thyroidectomy for papillary or follicular thyroid carcinoma from 2010 to 2020.

A total of 153 patients receiving surgery for DTC were assessed for pathological stage, nodal metastasis, and thyroid neoplasm characteristics. When comparing pathologic tumor staging of patients <18 vs. ≥18 years old, there was a significant relationship between age and pT stage (p=0.009), but not between age and pN stage (p=0.319). However, when comparing patients ≤15 vs. >15 years, there was a significant relationship between age and pT stage (p=0.015) and age and pN stage (p=0.016). Patients ≤15 years of age most commonly had stage pT2 tumors (48.9 %, n=22), whereas most >15 years had stage pT1 tumors (37.9 %, n=41). Of patients whose lymph nodes were analyzed, patients ≤15 years were most likely to have pN1b disease (31.1 %, n=14), while patients >15 years were most likely to have pN0 disease (33.3 %, n=36).

In this sample, separating children and adults at an age of 15, rather than 18, yielded more significant differences in risk of nodal involvement. Markers of invasive histology were more common in patients older than 15, while nodal involvement was more common in patients 15 and under.

Thyroid disease continues to be one of the most prevalent disease groups worldwide, with its frequency and distribution being impacted by numerous factors. Significant progress has been achieved in recent years in thyroid nodules, largely due to the advent of novel detection and diagnostic techniques. This study aims to scrutinize the top 100 most frequently cited articles in thyroid nodule research, utilizing bibliometric analysis to identify trends, highlight critical focal points, and lay a groundwork for forthcoming investigations.

A comprehensive literature search was carried out using the SCI-E database, and all the recorded results were downloaded in plain text format for detailed analysis. The key terms analyzed with VOSviewer 1.6.18, CiteSpace 6.3r1, bibliometrix in R Studio (v.4.4.1), and Microsoft Excel 2021 software include country, institution, author, journal, and keywords.

The publication timeframe extends from 1 January 2003 to 31 December 2021, reaching a peak citation count of 9,100. Notably, the United States leads in the number of published articles, with Harvard University standing out as a prestigious institution. These articles were featured in 45 diverse journals, with THYROID leading in publication volume. Nikiforov Yuri E. was the most prolific first author, appearing 10 times. Keyword analysis highlighted traditional research themes such as "fine needle aspiration," "carcinogens," and "management." However, "deep learning" has surfaced as a significant area of focus in recent studies.

This study has extracted the bibliometric characteristics of the top 100 most-cited articles pertaining to TNs, providing an invaluable reference for upcoming studies. Through meticulous analysis, it has been determined that the primary research concentrations encompass the diagnosis of benign or malignant TNs, the management of TNs, and the subsequent monitoring of TNs, with deep learning emerging as a pivotal area of exploration.

Indeterminate thyroid nodules (ITNs) lead to diagnostic surgeries in many countries. The use of molecular testing (MT) is endorsed by several guidelines, but costs are limitative, especially in public health care systems like in Canada.

The primary objective of this work was to evaluate the clinical value of ThyroSeq v3 (TSv3) using benign call rate (BCR) in a real-world practice. The secondary objective was to assess the cost-effectiveness of MT.

This multicentric prospective study was conducted in 5 academic centers in Quebec, Canada. A total of 500 consecutive patients with Bethesda III (on 2 consecutive cytopathologies) or IV and TIRADS 3 or 4 nodules measuring 1 to 4 cm were included. MT was performed between November 2021 and November 2022. Patients with a positive TSv3 were referred for surgery. Patients with a negative TSv3 were planned for follow-up by ultrasonography for a minimum of 2 years. The BCR, corresponding to the proportion of ITNs with negative TSv3 results, was assessed.

A total of 500 patients underwent TSv3 testing, with a BCR of 72.6% (95% CI, 68.5%-76.5%; P < .001). Ultimately, 99.7% of patients with a negative result avoided surgery. The positive predictive value of TSv3 was 68.2% (95% CI, 58.5%-76.9%). The cost-benefit analysis identified that the implementation of MT would yield a cost savings of $6.1 million over the next 10 years.

The use of MT (TSv3) in a well-selected population with ITNs led to a BCR of 72.6%. It is cost-effective and prevents unnecessary surgeries in a public health care setting.

We address the application of artificial intelligence (AI) techniques in thyroid cytopathology, specifically for diagnosing papillary thyroid carcinoma (PTC), the most common type of thyroid cancer.

Our research introduces deep learning frameworks that analyze cytological images from fine-needle aspiration cytology (FNAC), a key preoperative diagnostic method for PTC. The first framework is a patch-level classifier referred as "TCS-CNN", based on a convolutional neural network (CNN) architecture, to predict thyroid cancer based on the Bethesda System (TBS) category. The second framework is an attention-based deep multiple instance learning (AD-MIL) model, which employs a feature extractor using TCS-CNN and an attention mechanism to aggregate features from smaller-patch-level regions into predictions for larger-patch-level regions, referred to as bag-level predictions in this context.

The proposed TCS-CNN framework achieves an accuracy of 97% and a recall of 96% for small-patch-level classification, accurately capturing local malignancy information. Additionally, the AD-MIL framework also achieves approximately 96% accuracy and recall, demonstrating that this framework can maintain comparable performance while expanding the diagnostic coverage to larger regions through patch aggregation.

This study provides a feasibility analysis for thyroid cytopathology classification and visual interpretability for AI diagnosis, suggesting potential improvements in patient outcomes and reductions in healthcare costs.

Voice related complications are a major cause of morbidity in patients undergoing thyroidectomy in the postoperative period in the modern world. EBSLN being a primary tensor of vocal cords via cricothyroid muscle is important to produce high pitched sound above 150 Hz and it is essential for professional voice users. This nerve is prone to injury during surgery because of its proximity to the upper pole of the thyroid and complex anatomical relationship with the superior thyroid vessels. We aimed to study the occurrence of injury to EBSLN during surgery via acoustic voice analysis and comparing it with the pre-operative values. Patients of benign thyroid swelling with Bethesda type I to III and normal thyroid function tests were taken up for surgery. Pre- and post-operatively acoustic voice analysis was done in a soundproof room. Fundamental frequency (F0), amplitude perturbation (shimmer), fundamental frequency perturbation (jitter), and harmonic/noise ratio (HNR) were calculated and analysed. Intraoperatively, EBSLN was identified in Joll's triangle and preserved. The acoustic voice analysis was performed on the postoperative day one and seven, and compared with the pre-operative values. The mean age of patients was 35.73 ± 9.13 years. Most common age group 36-45 with male to female ratio being 1:9. Cystic colloid goitre was seen in 85% patients. F0 decreased from the preoperative value (221.447 ± 45.981 Hz) on postoperative day one (217.283 ± 46.323 Hz), p-value < 0.01 and on day 7, F0 (219.872 ± 45.096 Hz) p = 0.46. Pitch sigma increase (p < 0.01) from pre-operative (16.791 ± 14.716 Hz) to postoperative day 1 (18.454 ± 15.088 Hz) and on day 7 (17.79 ± 15.315 Hz), p = 0.09. Jitter (%) pre-operatively (0.46%±0.17%), post-operative day 1 (0.45%±0.21%, p = 0.05) and postoperative day 7 (0.44%±0.19%, p = 0.11). Shimmer (dB) the pre-operative (0.582 ± 0.317 dB), post-operative day 1 (0.552 ± 0.301 dB), p = 0.08 and postoperative day 7 (0.566 ± 0.302 dB) p = 0.90 on day 7. HNR pre-operatively (19.009 ± 3.939 dB), postoperative day 1 (18.803 ± 4.14 dB, p = 0.58) and postoperative day 7 (18.740 ± 3.630 dB, p = 0.46). Acoustic voice analysis showed decreased pitch and increase in pitch sigma on postoperative day one which improved on day seven, and it shows that there was no permanent injury to ESBLN during surgery. Acoustic voice analysis being a non-invasive objective procedure, can be used to diagnose EBSLN injury post-thyroidectomy. However, research with large sample size is required to conclusively study the diagnostic efficacy of acoustic voice analysis to diagnose injury to EBSLN.

The current requirement is to establish the preoperative diagnosis accurately as possible and to achieve an adequate extent of surgery. The aim of this study was to define the preoperative clinical and molecular genetic risks of malignancy in indeterminate thyroid nodules (Bethesda III and IV) and to determine their impact on the surgical strategy.

Prospectively retrospective analysis of 287 patients provided the basis of preoperative laboratory examination, sonographic stratification of malignancy risks and cytological findings. Molecular tests focused on pathogenic variants of genes associated with thyroid oncogenesis in cytologically indeterminate nodules (Bethesda III and IV). The evaluation included clinical risk factors: positive family history, radiation exposure and growth in size and/or number of nodules.

Preoperative FNAB detected 52 cytologically indeterminate nodules (28.7%) out of 181 patients. Postoperative histopathological examination revealed malignancy in 12 cases (23.7%) and there was no significant difference between Bethesda III and IV categories (P=0.517). Clinical risk factors for malignancy were found in 32 patients (61.5%) and the presence of at least one of them resulted in a clearly higher incidence of malignancy than their absence (31.3% vs. 10.0%, respectively). Pathogenic variants of genes were detected in 12/49 patients in Bethesda III and IV, and in 4 cases (33.3%) thyroid carcinoma was revealed. The rate of malignancies was substantially higher in patients with pathogenic variants than in those without (33.3% vs. 16.2%, respectively).

Our experience implies that molecular genetic testing is one of several decision factors. We will continue to monitor and enlarge our patient cohort to obtain long-term follow-up data.

Chronic lymphocytic thyroiditis is an autoimmune thyroid disorder and the most common cause of hypothyroidism in women. Many studies suggest that chronic lymphocytic thyroiditis contributes to a diagnostic challenge in thyroid nodules and may increase the risk of developing papillary thyroid cancer. This study examines preoperative clinical factors and tumor characteristics associated with papillary thyroid cancer among patients with chronic lymphocytic thyroiditis.

A retrospective review of prospectively collected data of patients who underwent total thyroidectomy between 2009 and 2020 at a tertiary institution was performed. Sociodemographic factors, comorbidities, surgeon-performed ultrasound, fine needle aspiration, tumor characteristics, and final histopathology were studied. Patients were subdivided into 2 groups based on final histopathology: chronic lymphocytic thyroiditis alone and chronic lymphocytic thyroiditis with papillary thyroid cancer. χ2 tests were used for independence among categorical variables, and comparisons were based on t tests.

Of 2,200 total thyroidectomy patients, the majority of 250 patients with chronic lymphocytic thyroiditis were women (90.4%) and had a mean age of 50 (±13) years. All patients with chronic lymphocytic thyroiditis underwent preoperative ultrasound, 89.2% (n = 223) underwent fine needle aspiration preoperatively, and 25.2% (n = 63) presented with obstructive symptoms, whereas 53.6% (n = 134) had papillary thyroid cancer on final histopathology and 74.8% (n = 187) underwent central neck lymph node removal. When comparing patients with chronic lymphocytic thyroiditis alone with those with chronic lymphocytic thyroiditis and papillary thyroid cancer, no differences for sex, race, nodule density, nodule size, echogenicity, irregular borders, and number of nodules were identified, but there was a statistically significant difference for obstructive symptoms (37.1% vs 14.9%), multinodular goiter (55.8% vs 32.3%), microcalcifications (18.4% vs 36.6%), Bethesda III fine needle aspiration results (41.4% vs 27.4%), and central neck lymph node removal (58.6% vs 88.8%), respectively (P < .05). Preoperative fine needle aspiration in patients with chronic lymphocytic thyroiditis for papillary thyroid cancer had a positive predictive value of 92.9%, negative predictive value of 83.3%, false positive rate of 13.8%, and false negative rate of 8.8%.

Although thyroid ultrasound features may have limited utility for malignancy, fine needle aspiration of index thyroid nodules still demonstrates a high positive predictive value in stratifying patients with chronic lymphocytic thyroiditis with papillary thyroid cancer. A higher level of suspicion preoperatively may be needed to avoid unnecessary lymph node removal for patients with chronic lymphocytic thyroiditis.

Papillary thyroid carcinoma (PTC) is the most common malignant thyroid neoplasm, accounting for approximately 85% of all follicular cell-derived thyroid nodules. This study aimed to assess the diagnostic potential of circulating microRNA-146a-5p and microRNA-221-3p as biomarkers for PTC and their usefulness in monitoring disease progression during patient follow-up.

An observational study was conducted on two cohorts of PTC patients and healthy controls (HCs) using digital PCR. We collected patients' clinical, biochemical, and imaging data during the post-surgery surveillance. We analyzed the levels of circulating miRNAs in serum samples of patients before surgery and during the follow-up, including those with indeterminate/biochemical incomplete response (IndR/BIR) and residual thyroid tissues (Thy Residue).

Both miR-146a-5p and miR-221-3p were confirmed as effective biomarkers for PTC diagnosis. They enabled differentiation between pre-surgery PTC patients and HCs with an area under the curve (AUC) of 92% and 87.3%, respectively, using a threshold level of 768,545 copies/uL for miR-146a-5p and 389,331 copies/uL for miR-221-3p. It was found that miRNA fold change levels, rather than absolute levels, can be useful during patient follow-up. In particular, we found that a fold change of 2 for miR-146a-5p and 2.2 for miR-221-3p can identify a progressive disease, regardless of the presence of TgAbs or remnant thyroid.

MiRNA-146a-5p and miRNA-221-3p, particularly the former, could be valuable diagnostic biomarkers for PTCs. They also seem to be effective in monitoring disease progression during patient follow-up by evaluating their fold change, even when thyroglobulin is uninformative.

The efficacy of radiofrequency ablation (RFA) in treating thyroid nodules with indeterminate cytology remains less studied. The objective of this study was to determine the efficacy of RFA in treating nodules with Bethesda III that have been molecularly profiled benign (BIII-MPN).

We included prospectively enrolled patients who underwent RFA for benign and BIII-MPN thyroid nodules. Primary outcome measures were volume reduction ratio (VRR), symptom score (range 0-10), and cosmetic score (range 0-3) at 1, 3, 6, and 12 months after RFA, as well as complication rates.

A total of 258 nodules in 192 patients were included (benign: 238 in 174; BIII-MPN: 20 in 18). The median VRR differed insignificantly, whereas symptom and cosmetic score improvements were similar between two cohorts. BIII-MPN thyroid nodules were associated with lower rates of infection and temporary voice change.

Our preliminary findings suggest that RFA may be a feasible management option for BIII-MPN thyroid nodules. However, appropriate will be important to address the important risk of potentially missed malignancies.

Increasing numbers of cytologically indeterminate thyroid nodules (ITNs) present challenges for preoperative diagnosis, often leading to unnecessary diagnostic surgical procedures for nodules that prove benign. Research in ultrasound radiomics and genomic testing leverages high-throughput data and image or sequence algorithms to establish assisted models or testing panels for ITN diagnosis. Many radiomics models now demonstrate diagnostic accuracy above 80% and sensitivity over 90%, surpassing the performance of less experienced radiologists and, in some cases, matching the accuracy of experienced radiologists. Molecular testing panels have helped clinicians achieve accurate diagnoses of ITNs, preventing unnecessary diagnostic surgical procedures in 42%-61% of patients with benign nodules.

In this review, we examined studies on ultrasound radiomics and genomic molecular testing for cytological ITNs conducted over the past 5 years, aiming to provide insights for researchers focused on improving ITN diagnosis.

Radiomics models and molecular testing have enhanced diagnostic accuracy before surgery and reduced unnecessary diagnostic surgical procedures for ITN patients.

Molecular assays serve as a potential risk stratification tool for cytologically indeterminate thyroid nodules (ITNs). BRAF V600E mutations are nearly always associated with thyroid cancer. However, the malignancy risk for ITNs with other less common BRAF alterations is less well understood. In this retrospective cohort study, we examine the risk of malignancy (ROM), histopathologic diagnoses, and clinical outcomes for non-V600E BRAF-altered ITNs.

Genomic profiling data obtained from 1034 pre-operative fine-needle aspiration samples from 955 patients were reviewed. Nodules harboring BRAF V600E were excluded. Clinical, radiographic, and histopathologic data were analyzed retrospectively from BRAF-altered ITNs managed surgically at one comprehensive cancer center (2014-2024). Diagnoses were subdivided based on American Thyroid Association (ATA) risk categories.

Thirty-seven patients (3.9%) with non-V600E BRAF-altered ITNs were identified (isolated BRAF mutation: n = 29 [78.4%], BRAF + other mutation: n = 3 [8.1%], BRAF fusion: n = 4 [10.8%], BRAF-like gene expression: n = 1 [2.7%]). All BRAF mutations identified in the cohort were class II (RAS-independent, intermediate to high kinase activity). Nodules had a median pre-operative diameter of 1.8 cm (interquartile range [IQR] 1.4-2.5). Patients presented with nodal metastases in 2.7% (n = 1) of cases, and local invasion was not identified in any patients in the cohort. Approximately half of patients (54.1%) were initially treated with a partial thyroidectomy (lobectomy: n = 17 [45.9%], isthmusectomy: n = 3 [8.1%]), and the remaining patients underwent total thyroidectomy (n = 17 [45.9%]). Median post-operative follow-up was 28 months (IQR 17.8-45.5). ROM for BRAF alterations was 73% (95%CI 59-87%; ATA low risk: 64.9%/ATA int risk: 5.4%/ATA high risk: 2.7%). There were no high-risk cancers identified in patients with isolated BRAF mutation (benign: n = 10 [34.5%], ATA low risk: n = 19 [65.5%]), and the most common isolated mutation was K601E (n = 17, 45.9%) which had a 58.8% ROM (all ATA low risk). Patients with isolated BRAF mutations had a significantly lower rate of ATA intermediate or high risk pathology when compared to all other BRAF alterations (0% vs. 37.5%, p = 0.0072). Only three patients were treated with radioactive iodine post-operatively (8.1%), and no completion thyroidectomy procedures were performed in those who did not initially undergo total thyroidectomy. No patients in the cohort were found to have distant metastatic disease or recurrence, and there were no deaths during the follow-up interval.

ITNs harboring non-V600E BRAF alterations were rare (3.9% of patients) and typically malignant (73%). Nearly all nodules were benign or ATA low-risk cancers. Only 8% of such nodules were ATA intermediate or high risk cancers. In ITNs with isolated non-V600E BRAF and no other genetic alterations, one-third were non-malignant, and all cancers were ATA low risk. In the appropriate clinical context, thyroid lobectomy or active surveillance can be considered for initial management of non-V600E BRAF-altered ITNs.

Tyrosine kinase inhibitors (TKIs) are crucial for improving the survival rates of individuals with metastatic thyroid cancer. Moreover, systemic inflammation and malnutrition are known to negatively affect metastatic thyroid cancer prognosis. Evaluating nutritional status at the start of treatment can improve survival rates. Purpose: This study investigated the correlation between the hemoglobin, albumin, lymphocyte count, and platelet (HALP) score and prognosis of patients with metastatic thyroid cancer undergoing first-line TKI therapy. Methods: We retrospectively analyzed data from 44 patients between January 2010 and June 2024. The primary outcomes evaluated in the study were time to treatment failure (TTF) and overall survival (OS); HALP scores were categorized as low (≤29.21) and high (>29.21) based on receiver operating characteristic analysis. Results: The 1-year survival rate was significantly lower in the low HALP score group compared to the high HALP score group (50% vs. 96.3%). Multivariate Cox regression analysis revealed that low HALP scores, elevated leukocyte counts, and lymphopenia were independent predictors of shorter TTF (HR = 0.272, p = 0.011) and OS (HR = 0.208, p = 0.028). Conclusions: The results obtained in the present study demonstrate that the HALP score has prognostic significance for patients with metastatic thyroid cancer who are undergoing first-line TKI treatment. In metastatic thyroid cancer patients, interventions focused on improving nutritional status at the start, during initiation, and throughout the TKI treatment may enhance treatment effectiveness. However, further prospective studies involving larger patient cohorts are necessary to validate our results.

Preoperative ultrasound examination of thyroid nodules is the most economical and effective screening method for diagnosing thyroid nodules. Fine-needle aspiration biopsy (FNAB) cytology guided by ultrasound has high sensitivity and specificity in distinguishing benign and malignant thyroid nodules. However, approximately 25% of thyroid nodules cannot be determined by FNAB, and accurate differentiation of benign and malignant thyroid nodules is critical for patient prognosis. Here, we report the diagnosis and surgical treatment process of a rare patient with bilateral thyroid malignant tumor of independent origin. This patient had significantly elevated levels of calcitonin (Ctn: 130.00 pg/mL) and carcinoembryonic antigen (CEA: 16.13 ng/mL). Ultrasound shows a solid nodule on the left side of the thyroid gland, measuring 1.2*0.8*0.9cm, TI-RADS 4A; right solid nodule, 1.3*0.7*0.9 cm, TI-RADS 3. A fine needle biopsy of the left nodule showed little glandular epithelium and no evidence of malignancy. Multi-gene joint analysis of RET C634R in the left nodule and BRAF V600E in the right nodule indicated a potential diagnosis of left medullary thyroid carcinoma (MTC) and right papillary thyroid carcinoma (PTC). Postoperative pathology revealed the left thyroid nodule was MTC and the right nodule was PTC. The patient's bilateral thyroid nodules are independent primary malignant lesions. This case emphasizes the important significance of combined analysis of ultrasound, serum biomarkers, cellular pathology, molecular detection, and paraffin pathology in the differential diagnosis of benign and malignant multiple thyroid nodules. It provides a reference for future diagnosis and treatment decisions of multiple thyroid nodules.

Objectives: Cytologically indeterminate thyroid nodules (Bethesda class III or IV) carry a 10-40% risk of malignancy. Diagnostic lobectomies are frequently performed but negative surgeries incur unnecessary costs on the healthcare system, potential complications, and negative impacts on quality of life. Molecular tests (MTs) have been developed to reduce unnecessary surgeries. However, well-validated, high-performance MTs are often expensive, and their cost-effectiveness has not been studied in the Asian population. This study evaluates the rate of unnecessary surgery in the setting without MT (our current practice) and the cost-effectiveness of introducing a commercially available MT for the management of cytologically indeterminate thyroid nodules in a modernized city in Asia. Methods: Management decisions and outcomes of consecutive Bethesda III or IV thyroid nodules in a tertiary endocrine surgery center in Hong Kong were evaluated. Costs of health service provided by the public health system, which covers >90% of healthcare service in the city, were retrieved. A decision tree model was developed to compare the cost-effectiveness in avoiding unnecessary surgeries of current practice versus routine MT from a public healthcare provider's perspective. In our current practice, MT was not available, and patients with indeterminate nodules received either upfront lobectomy, repeat fine needle aspiration cytology (FNAC), or active surveillance. Results: Over a 4-year period, 2157 FNACs were performed. After exclusion, 1957 FNACs were analyzed, and 18.6% were Bethesda III or IV. Thirty-six percent of these cytologically indeterminate nodules received upfront surgery, with 28% having malignancy in final pathology, that is, 72% of surgeries were unnecessary. Routine MT could reduce 82 unnecessary surgeries/year, 26% more than current practice. Routine MT resulted in an incremental cost-effectiveness ratio of Hong Kong dollar (HKD) 49,102 (US dollar [USD] 6314) per unnecessary surgery. Sensitivity analysis showed test cost of MT contributed significantly to incremental cost-effectiveness ratio. Lowering the commercial price of MT to below HKD 8044 (USD 1031) would render routine MT cost-saving. Conclusion: Currently, a high rate of unnecessary surgeries is being performed for cytologically indeterminate thyroid nodules. MT was more effective in reducing unnecessary surgeries than current practice, but at a higher cost. MT will become cost-saving if the test cost could be lowered.

This study assessed CLDN16 as a potential replacement or improvement biomarker for papillary thyroid cancer (PTC), addressing the limitations associated with the prevalently used BRAF-V600E mutation.

Database analyses, tissue validation, RNA sequencing, and functional assays were conducted to evaluate CLDN16 as a PTC biomarker and its clinical application.

CLDN16 expression was examined in PTC and normal thyroid/para-tumor tissues and compared across various cancer types. We evaluated diagnostic accuracy, stability in primary and metastatic sites, and associations with aggressive features. Knockdown experiments were performed to investigate the impact on PTC cell behavior. Additionally, we developed a support vector machine model for diagnosing malignant and high-risk PTCs.

CLDN16 demonstrated high specificity for PTC, with positive detection rates (88.0% in The Cancer Genome Atlas [TCGA] and 88.3% in our center) significantly surpassing BRAF-V600E (47.5% in TCGA and 74.3% in our center). This resulted in superior diagnostic accuracy (ROC-CLDN16 = 0.922 vs ROC-BRAF-V600E = 0.742 in TCGA). CLDN16 exhibited stable expression across primary and metastatic sites and was associated with aggressive features, including extrathyroidal extension and lymph node metastasis. CLDN16 knockdown inhibited migration, invasion, and iodine uptake in PTC cells. Clinically, CLDN16 effectively identified malignancy in BRAF wild patients (94.2%), and combined with BRAF-V600E, achieved 96.9% accuracy. The incorporation of CLDN16 into PTC molecular typing facilitated precise high-risk identification (92.0% accuracy in the training set and 100% in the validation set).

CLDN16 presents a promising biomarker that could surpass BRAF-V600E, offering effective clinical utility and revolutionizing PTC molecular typing for precise high-risk identification.

Thyroid nodules are common, and ultrasound-based risk stratification using ACR's TIRADS classification is a key step in predicting nodule pathology. Determining thyroid nodule contours is necessary for the calculation of TIRADS scores and can also be used in the development of machine learning nodule diagnosis systems. This paper presents the development, validation, and multi-institutional independent testing of a machine learning system for the automatic segmentation of thyroid nodules on ultrasound.

The datasets, containing a total of 1595 thyroid ultrasound images from 520 patients with thyroid nodules, were retrospectively collected under IRB approval from University of Chicago Medicine (UCM) and Weill Cornell Medical Center (WCMC). Nodules were manually contoured by a team of UCM and WCMC physicians for ground truth. An AttU-Net, a U-Net architecture with additional attention weighting functions, was trained for the segmentations. The algorithm was validated through fivefold cross-validation by nodule and was tested on two independent test sets: one from UCM and one from WCMC. Dice similarity coefficient (DSC) and percent Hausdorff distance (%HD), Hausdorff distance reported as a percent of the nodule's effective diameter, served as the performance metrics.

On multi-institutional independent testing, the AttU-Net yielded average DSCs (std. deviation) of 0.915 (0.04) and 0.922 (0.03) and %HDs (std. deviation) of 12.9% (4.6) and 13.4% (6.3) on the UCM and WCMC test sets, respectively. Similarity testing showed the algorithm's performance on the two institutional test sets was equivalent up to margins of Δ DSC ≤ 0.013 and Δ %HD ≤ 1.73%.

This work presents a robust automatic thyroid nodule segmentation algorithm that could be implemented for risk stratification systems. Future work is merited to incorporate this segmentation method within an automatic thyroid classification system.

The risk of malignancy in thyroid nodules is higher in children than in adults, often necessitating a more aggressive endocrine and surgical approach. However, given that not all solid thyroid nodules are malignant, a more conservative approach may also be appropriate in certain cases.

This study aims to present an illustrative analysis of the pathological foundations underlying the sonographic appearance of benign, borderline, and malignant thyroid nodules in the pediatric population at a single tertiary thyroid center.

A total of 47 well-documented pediatric patients referred for thyroid surgery between 2010 and 2023 were analyzed. This retrospective assessment included an examination of demographic data, hormonal profiles, ultrasound findings, and histopathology reports.

Ultrasound and histopathology of thyroid nodules provided insights into subgroup differentiation. Benign nodules like dyshormonogenetic goiter showed solid hypoechoic features on ultrasound and dense fibrosis on histopathology, while thyroid follicular nodular disease exhibited isoechoic nodules with halos, histologically revealing dilated follicles. In borderline tumors, well-differentiated tumor of uncertain malignant potential (WDT-UMP) nodules were hypo/hyperechoic with occasional capsular invasion, resembling papillary thyroid carcinoma (PTC) features histologically. Non-invasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP) appeared as well-defined hypoechoic nodules with a hypoechoic rim, with histology showing follicular architecture and PTC nuclear features, but no invasion. Follicular tumor of uncertain malignant potential (FT-UMP) displayed hypo/hyperechoic patterns and indistinct borders, with uncertain capsular invasion and no PTC nuclear features. Malignant lesions showed distinct patterns: PTC as hypoechoic, irregular nodules with mixed vascularization, follicular thyroid carcinoma as large, hyperechoic nodules with invasive features, and poorly differentiated thyroid carcinoma (PDTC) as heterogeneous hypoechoic masses.

Because of the significant overlap in sonographic features among benign, borderline, and certain malignant thyroid lesions in pediatric patients, ultrasonography alone is insufficient for accurate risk stratification. This overlap necessitates referrals for fine-needle aspiration biopsy (FNAB) in children more frequently than in adults. Future studies utilizing artificial intelligence (AI) to predict clinical outcomes in thyroid nodule diagnostics may offer new advancements, particularly given the increasing number of pediatric patients with solid thyroid lesions.

This study aimed to develop a multimodal radiopathomics model utilising preoperative ultrasound (US) and fine-needle aspiration cytology (FNAC) to predict large-number cervical lymph node metastasis (CLNM) in patients with clinically lymph node-negative (cN0) papillary thyroid carcinoma (PTC).

This multicentre retrospective study included patients with PTC between October 2017 and June 2024 across seven institutions. Patients were categorised based on the presence or absence of large-number CLNM in training, validation, and external testing cohorts. A clinical model was developed based on the maximum diameter of thyroid nodules. Radiomics features were extracted from US images and pathomics features were extracted from FNAC images. Feature selection was performed using univariate analysis, correlation analysis, and least absolute shrinkage and selection operator regression. Six machine learning (ML) algorithms were employed to construct radiomics, pathomics, and radiopathomics models. Predictive performance was assessed using the area under the curve (AUC), and decision curve analysis (DCA).

A total of 426 patients with PTC (41.65 ± 12.47 years; 124 men) were included in this study, with 213 (50%) exhibiting large-number CLNM. The multimodal radiopathomics model demonstrated excellent predictive capabilities with AUCs 0.921, 0.873, 0.903; accuracies (ACCs) 0.852, 0.800, 0.833; sensitivities (SENs) 0.876, 0.867, 0.857; specificities (SPEs) 0.829, 0.733, 0.810, for the training, validation, and testing cohorts, respectively. It significantly outperformed the clinical model (AUCs 0.730, 0.698, 0.630; ACCs 0.690, 0.656, 0.627; SENs 0.686, 0.378, 0.556; SPEs 0.695, 0.933, 0.698), the radiomics model (AUCs 0.819, 0.762, 0.783; ACCs 0.752, 0.722, 0.738; SENs 0.657, 0.844, 0.937; SPEs 0.848, 0.600, 0.540), and the pathomics model (AUCs 0.882, 0.786, 0.800; ACCs 0.829, 0.756, 0.786; SENs 0.819, 0.889, 0.857; SPEs 0.838, 0.633, 0.714).

The multimodal radiopathomics model demonstrated significant advantages in the preoperative prediction of large-number CLNM in patients with cN0 PTC.

Question Accurate preoperative prediction of large-number CLNM in PTC patients can guide treatment plans, but single-modality diagnostic performance remains limited. Findings The radiopathomics model utilising preoperative US and FNAC images effectively predicted large-number CLNM in both validation and testing cohorts, outperforming single predictive models. Clinical relevance Our study proposes a multimodal radiopathomics model based on preoperative US and FNAC images, which can effectively predict large-number CLNM in PTC preoperatively and guide clinicians in treatment planning.

Noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP) can be differentiated from invasive encapsulated follicular variant of papillary thyroid carcinoma (eFV-PTC) by the presence of a tumor capsule or blood vessel invasion in histological examination. The objective of this study was to investigate whether it is possible to distinguish between NIFTP and invasive eFV-PTC before surgery. Patients diagnosed with NIFTP and invasive eFV-PTC from 2017 to 2023 were analyzed for biochemical, ultrasonographic, and cytological features. No differences were found in thyroid function tests, thyroid autoantibody levels, tumor size, or ultrasonographic characteristics. However, patients with invasive eFV-PTC had higher preoperative neutrophil-to-lymphocyte ratio (NLR) values and a higher Bethesda cytology category compared to those with NIFTP. In the multivariable analysis, NLR was the only significant predictor of invasive eFV-PTC. Nevertheless, there was no reliable NLR cutoff for distinguishing between the two entities. Overall, this study substantiates considerable overlap in demographic and clinical data between NIFTP and invasive eFV-PTC. Although the higher NLR observed in thyroid cancer does not provide strong discrimination, it suggests that the invasive nature of tumor cells might elicit a more profound systemic inflammatory or immune response.

The conflicting results of the Bethesda system for reporting thyroid cytopathology (BSRTC) and B-Raf proto-oncogene (BRAF) mutation status during pre-operative fine-needle aspiration cytology (FNAC) of thyroid nodules create a dilemma for clinicians in devising appropriate treatment strategies for patients. This study provides a report on the histopathological findings of 687 thyroid nodules with an indeterminate cytological diagnosis after the combination of the BSRTC and BRAF mutation status.

The clinical data of patients with thyroid nodules, suspicious of malignancy at ultrasound (US), who underwent US-guided FNAC between December 2020 and March 2023 at our cancer center were reviewed. Patients with an indeterminate diagnosis, that is, conflicting results of the BSRTC and BRAF mutation status after FNAC, were enrolled. The following four combinations of BSRTC and BRAF mutation status were considered indeterminate: (1) Group 1, BSRTC I and positive for a BRAF mutation; (2) Group 2, BSRTC II and positive for a BRAF mutation; (3) Group 3, BSRTC III and positive for a BRAF mutation; and (4) Group 4, BSRTC V and negative for a BRAF mutation. Finally, only patients who underwent surgical treatment at our center were included in the data analysis.

Among the 1,044 eligible patients, 687 underwent surgical treatment. Of the 687 patients, 117 were in Group 1, 14 in Group 2, 394 in Group 3, and 162 in Group 4. Histopathological examination showed that 677 (98.5%) patients had papillary thyroid cancer, including 585 with papillary thyroid microcarcinoma, whereas only 10 (1.5%) had benign nodules. The malignancy rates were 98.3%, 100%, 98.7%, and 98.1% for Groups 1 to 4, respectively. Among the 387 patients in category 4A by the thyroid imaging reporting and data system (TI-RADS 4A) through the US, the malignancy rate was 98.4%, and for the 116 nodules <5 mm in diameter in the US, the malignancy rate was 99.1%. When combining TI-RADS 4A and a nodule diameter <5 mm, the malignancy rate was 98.9% (88/89). A total of 179 patients (26.1%) had histopathologically confirmed central cervical lymph node metastasis, and 46 (6.8%) had lateral cervical lymph node metastasis. Two nodules in Group 1, five nodules in Group 3, and three nodules in Group 4 were determined to be benign post-surgery. The benign thyroid nodules included seven dysplastic, one adenomatous, one fibrotic, and one hyperplastic.

Thyroid nodules, suspicious of malignancy on US, after the combined interpretation of BSRTC and BRAF mutation status following pre-operative FNAC had a high risk of malignancy. Repeat US-guided FNAC for indeterminate thyroid nodules is highly recommended in clinical practice.