Diagnosis Of Thyroid Nodules Research Articles

Description of a New miRNA Signature for the Surgical Management of Thyroid Nodules

Background: The diagnosis of malignant thyroid nodules is mainly based on the fine-needle aspiration biopsy (FNAB). To improve the detection of malignant nodules, different molecular tests have been developed. We present a new molecular signature based on altered miRNA expressions and specific mutations. Methods: This is a prospective non-interventional study, including all Bethesda categories, carried out on an FNAB sampled in suspicious nodule(s) during thyroidectomy. miRNA quantification and mutations detection were performed. The reference diagnosis was the pathological assessment of the surgical specimen. Different classification algorithms were trained with molecular data to correctly classify the samples. Results: A total of 294 samples were recorded and randomly divided in two equal groups. The random forest algorithm showed the highest accuracy and used mostly miRNAs to classify the nodules. The sensitivity and the specificity of our signature were, respectively, 76% and 96%, and the positive and negative predictive values were both 90% (disease prevalence of 30%). Conclusions: We have identified a molecular classifier that combines miRNA expressions with mutations detection. This signature could potentially help clinicians, as complementary to the Bethesda classification, to discriminate indeterminate FNABs.

Efficacy of Ultrasound Findings in Diagnosing Thyroid Nodules Correlating with Histopathology and Surgical Outcomes

Efficacy of Ultrasound Findings in Diagnosing Thyroid Nodules Correlating with Histopathology and Surgical Outcomes

The ability of virtual noncontrast images to remove intrinsic and external iodine from the thyroid via dual-layer spectral detector computed tomography.

Virtual noncontrast (VNC) images generated by dual-layer spectral computed tomography (DLCT) remove iodine influence from enhanced images to simulate true noncontrast (TNC) images. Previous research has demonstrated the high comparability of abdominal VNC images with TNC images, suggesting their potential as substitutes. Given the thyroid's significant iodine content, this study evaluated the efficacy of VNC images for removing both intrinsic and extrinsic iodine through an analysis of computed tomography (CT) attenuation and iodine density in TNC and enhanced VNC thyroid images. A total of 115 thyroid nodules were classified into papillary thyroid carcinoma (PTC) and nodular goiter (NG) groups based on pathology. Patients underwent both noncontrast and enhanced neck scans, with attenuation values of CT and iodine density measured for nodules, normal thyroid, and the carotid artery on conventional and VNC images. The study calculated CT attenuation and iodine density for both intrinsic and external iodine content. The Wilcoxon rank-sum test was used to compare intrinsic and external iodine differences between the PTC and NG groups. The Spearman test was used for correlation assessment within each group, and Bland-Altman analysis was conducted to evaluate CT attenuation consistency between VNC images from nonenhanced scans (VNCn) and VNC images from enhanced scans (VNCe) within the groups. The CT attenuation values of intrinsic iodine showed no differences between nodules, normal thyroid, and carotid artery in the PTC and NG groups (P>0.05). However, there was a difference in the CT attenuation values of external iodine for nodules between the two groups (P<0.05), while no difference was found for normal thyroid or the carotid artery between the groups (P>0.05). The correlation between CT attenuation values of the nodules, normal thyroid, and carotid artery for intrinsic iodine and iodine density was high in both the PTC group (r=0.919, r=0.951, r=0.592, respectively; P<0.001) and the NG group (r=0.925, r=0.973, r=0.721, respectively; P<0.001). Similarly, there was a strong correlation between the CT attenuation values of the nodules, normal thyroid, and carotid artery for extrinsic iodine and iodine density in the PTC group (r=0.960, r=0.965, r=0.904, respectively; P<0.001) and the NG group (r=0.979, r=0.967, r=0.963, respectively; P<0.001). There was no statistically significant difference in the CT attenuation values of the normal thyroid in VNCn and VNCe images (P>0.05), while the CT attenuation values of nodules and the carotid artery in VNCn and VNCe images in the two groups were significantly different (P<0.05). Bland-Altman scatter plots showed that, apart from the normal thyroid in the NG group, the consistency of CT attenuation values on VNCn and VNCe images was generally poor (more than 5% of data points outside the consistency limit). VNC images show certain ability to remove intrinsic and external iodine from the thyroid. In the diagnosis of thyroid nodules, enhanced VNC images of the thyroid cannot replace conventional nonenhanced images.

The value and sensitivity of contrast-enhanced ultrasonography combined with fine-needle aspiration biopsy in the diagnosis of thyroid nodules

To investigate the value and sensitivity of contrast-enhanced ultrasonography (CEUS) combined with fine-needle aspiration biopsy (FNAB) in the diagnosis of thyroid nodules. This study enrolled 120 patients with thyroid nodules who visited our hospital between July 2018 and January 2021. All patients underwent CEU and CEUS-guided FNAB. The sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of CEUS-guided FNAB for the qualitative diagnosis of thyroid nodules were significantly higher compared with CEUS only (P < 0.05). The consistency in the diagnostic results was high between CEU-guided FNAB and surgical pathology and moderate between CEU and surgical pathology. The diagnostic coincidence rates of CEUS-guided FNAB were significantly higher than those of CEU only for papillary thyroid carcinoma, follicular carcinoma, undifferentiated carcinoma, and medullary carcinoma (P < 0.05). The diagnostic coincidence rates of CEUS-guided FNAB for stages I, II, and III thyroid cancer were significantly higher compared with CEU only (P < 0.05). Contrast-enhanced ultrasonography combined with FNAB improved the sensitivity and accuracy of making a qualitative diagnosis for thyroid nodules. This outcome will not only help to distinguish thyroid cancer from benign ones but can also assist in determining the pathological type and tumor stage of thyroid cancer, thereby presenting good diagnostic value.

Retrospective Study of Fine Needle Aspiration Cytology of Patients with Thyroid Nodule in Benghazi in the Period of (2021-2023)

Background: Thyroid nodules constitute a common endocrine disorder, these nodules could be solitary, multiple, cystic, or solid. Increasing age, female gender, iodine deficiency, and history of thyroid radiation all are high risk for thyroid nodules. FNAC representing the most cost-effective diagnostic tool used in the assessment of nodules of the thyroid. Objective of the study: The aim of this study is to evaluate the result of fine needle aspiration cytology (FNAC) and assess thyroid status using of thyroid hormone obtained from patients with thyroid nodules. Materials and methods: this is a retrospective study, includes collection of data from available cases of thyroid nodules underwent fine needle aspiration between 2021 to 2023, data regarding age, sex, TFT, USS, FNAC was collected from the archive of endocrine out patients clinic of Benghazi Medical Center and from endocrine clinic of Benghazi diabetic center. The analysis was done using the SPSS program. Result: A total of 60 cases were studied, Data was collected from 60 patient’s files for years between 2021 and 2023. The mean age of the patients with FNAC selected for this study was 49.65, and ranged from 21-80 years. The gender distribution shows female predominance in which female cases were 53 (98.33%) while only one case (1.67%) was reported among men. The size of nodules in our cases range from 1cm to 4.5 cm. The mean size of nodules is 1.89cm. In this study the largest group of nodules located in right lobe (21) cases then left lobe (20) cases then both (17) cases and in isthmus only 2 cases. Most of the cases thyroid function test result shows an euthyroid status (38) cases. FNAC of thyroid nodule showed that most of patient’s result diagnosed as benign nodules (47) cases. Conclusion: FNAC is a key tool in diagnosis of thyroid nodule as it has safe, minimally invasive and cost effective diagnostic role.

The study on ultrasound image classification using a dual-branch model based on Resnet50 guided by U-net segmentation results

In recent years, the incidence of nodular thyroid diseases has been increasing annually. Ultrasonography has become a routine diagnostic tool for thyroid nodules due to its high real-time capabilities and low invasiveness. However, thyroid images obtained from current ultrasound tests often have low resolution and are plagued by significant noise interference. Regional differences in medical conditions and varying levels of physician experience can impact the accuracy and efficiency of diagnostic results. With the advancement of deep learning technology, deep learning models are used to identify whether a nodule in a thyroid ultrasound image is benign or malignant. This helps to close the gap between doctors’ experience and equipment differences, improving the accuracy of the initial diagnosis of thyroid nodules. To cope with the problem that thyroid ultrasound images contain complex background and noise as well as poorly defined local features. in this paper, we first construct an improved ResNet50 classification model that uses a two-branch input and incorporates a global attention lightening module. This model is used to improve the accuracy of benign and malignant nodule classification in thyroid ultrasound images and to reduce the computational effort due to the two-branch structure.We constructed a U-net segmentation model incorporating our proposed ACR module, which uses hollow convolution with different dilation rates to capture multi-scale contextual information for feature extraction of nodules in thyroid ultrasound images and uses the results of the segmentation task as an auxiliary branch for the classification task to guide the classification model to focus on the lesion region more efficiently in the case of weak local features. The classification model is guided to focus on the lesion region more efficiently, and the classification and segmentation sub-networks are respectively improved specifically for this study, which is used to improve the accuracy of classifying the benign and malignant nature of the nodules in thyroid ultrasound images. The experimental results show that the four evaluation metrics of accuracy, precision, recall, and f1 of the improved model are 96.01%, 93.3%, 98.8%, and 96.0%, respectively. The improvements were 5.7%, 1.6%, 13.1%, and 7.4%, respectively, compared with the baseline classification model.

Contrast-Enhanced Ultrasound for Diagnosing Thyroid Nodules With Indeterminate Cytology: A Retrospective Study.

A small number of thyroid nodules cannot be clearly diagnosed using ultrasound-guided fine needle aspiration biopsy. Contrast-enhanced ultrasound (CEUS) has high diagnostic performance for thyroid nodules. We explored the value of CEUS for diagnosing thyroid nodules with indeterminate cytology. Between September 2019 and July 2022, 27,646 patients with thyroid nodule(s) underwent conventional ultrasound (CUS) in our hospital. From these patients, 597 nodules were subjected to CEUS and ultrasound-guided fine needle aspiration biopsy and 116 thyroid nodules with indeterminate cytology diagnose were enrolled in this study. The independent risk factors for predicting malignancy were determined using univariate and multivariate logistic regression analyses. Receiver operating characteristic (ROC) curves were drawn for CUS, CEUS, and CEUS combined with CUS. The area under the curve (AUC) was calculated and compared. Of the 116 thyroid nodules, 40 (34.5%) were benign and 76 (65.5%) were malignant. Univariate analysis showed that the shape, echogenicity, margin, microcalcification, enhancement intensity, enhancement homogeneity, wash in, and wash out were significantly different between benign and malignant thyroid nodules (all p < 0.05). Multivariate logistic regression analysis showed that taller-than-wide, irregular margin, microcalcification, hypo-enhancement, heterogeneity enhancement, synchronous/slower wash in, and synchronous/slower wash out were independent risk factors for malignancy (all p < 0.05). ROC curve analysis showed that the AUC of CUS and CEUS were 0.769 and 0.848, respectively. No significant difference was observed in the AUC between the two modalities (p > 0.05). However, the AUC (0.934) of the CUS combined with CEUS was significantly higher than that of CEUS or CUS alone (both p < 0.05). CEUS is helpful in diagnosing thyroid nodules with indeterminate cytology. CUS combined with CEUS is highly valuable for predicting malignancy.

Optimizing thyroid AUS nodules malignancy prediction: a comprehensive study of logistic regression and machine learning models.

The accurate diagnosis of thyroid nodules with indeterminate cytology, particularly in the atypia of undetermined significance (AUS) category, remains challenging. This study aims to predict the risk of malignancy in AUS nodules by comparing two machine learning (ML) and three conventional logistic regression (LR) models. A retrospective study on 356 AUS nodules in 342 individuals from 6728 patients who underwent thyroid surgery in 2021. All the clinical, ultrasonographic, and molecular data were collected and randomly separated into training and validation cohorts at a ratio of 7: 3. ML (random forest and XGBoost) and LR (lasso regression, best subset selection, and backward stepwise regression) models were constructed and evaluated using area under the curve (AUC), calibration, and clinical utility metrics. Approximately 90% (321/356) of the AUS nodules were malignant, predominantly papillary thyroid carcinoma with 68.6% BRAF V600E mutations. The final LR prediction model based on backward stepwise regression exhibited superior discrimination with AUC values of 0.83 (95% CI: 0.73-0.92) and 0.80 (95% CI: 0.67-0.94) in training and validation, respectively. Well calibration, and clinical utility were also confirmed. The ML models showed moderate performance. A nomogram was developed on the final LR model. The LR model developed using the backward stepwise regression, outperformed ML models in predicting malignancy in AUS thyroid nodules. The corresponding nomogram based on this model provides a valuable and practical tool for personalized risk assessment, potentially reducing unnecessary surgeries and enhancing clinical decision-making.

Do as Sonographers Think: Contrast-Enhanced Ultrasound for Thyroid Nodules Diagnosis via Microvascular Infiltrative Awareness.

Dynamic contrast-enhanced ultrasound (CEUS) imaging can reflect the microvascular distribution and blood flow perfusion, thereby holding clinical significance in distinguishing between malignant and benign thyroid nodules. Notably, CEUS offers a meticulous visualization of the microvascular distribution surrounding the nodule, leading to an apparent increase in tumor size compared to gray-scale ultrasound (US). In the dual-image obtained, the lesion size enlarged from gray-scale US to CEUS, as the microvascular appeared to be continuously infiltrating the surrounding tissue. Although the infiltrative dilatation of microvasculature remains ambiguous, sonographers believe it may promote the diagnosis of thyroid nodules. We propose a deep learning model designed to emulate the diagnostic reasoning process employed by sonographers. This model integrates the observation of microvascular infiltration on dynamic CEUS, leveraging the additional insights provided by gray-scale US for enhanced diagnostic support. Specifically, temporal projection attention is implemented on time dimension of dynamic CEUS to represent the microvascular perfusion. Additionally, we employ a group of confidence maps with flexible Sigmoid Alpha Functions to aware and describe the infiltrative dilatation process. Moreover, a self-adaptive integration mechanism is introduced to dynamically integrate the assisted gray-scale US and the confidence maps of CEUS for individual patients, ensuring a trustworthy diagnosis of thyroid nodules. In this retrospective study, we collected a thyroid nodule dataset of 282 CEUS videos. The method achieves a superior diagnostic accuracy and sensitivity of 89.52% and 94.75%, respectively. These results suggest that imitating the diagnostic thinking of sonographers, encompassing dynamic microvascular perfusion and infiltrative expansion, proves beneficial for CEUS-based thyroid nodule diagnosis.

Diagnostic Accuracy of Ultrasound Elastography Versus Fine-Needle Aspiration Cytology in Predicting Benign and Malignant Thyroid Nodules in Solitary and Multinodular Thyroid Glands: A Comparative Analysis.

Background The diagnosis of thyroid nodules requires accurate techniques; fine-needle aspiration cytology (FNAC) is the gold standard, while ultrasonography elastography has potential but is not well supported by data, particularly when it comes to differentiating benign from malignant nodules in single and multiple noduled glands. Objective This study's main goal was to assess the diagnostic accuracy of ultrasound elastography in predicting benign versus malignant thyroid nodules, both in solitary and multinodular thyroid glands, compared with FNAC. Methodology This prospective observational study evaluated thyroid nodules using ultrasound elastography and FNAC. Patients who were 18 years of age or older and had visible thyroid nodules met the inclusion criteria; those who had undergone thyroid surgery in the past, had cancer, or refused both tests were excluded. Data on demographics, clinical conditions, and imaging were gathered from 360 enrolled patients. Statistical analysis included calculating sensitivity, specificity, and diagnostic accuracy of ultrasound elastography using FNAC as a reference, alongside receiver operating characteristic curve analysis to determine the optimal cutoff for benign versus malignant nodules. Results There were 360 individuals in the trial, 250 of whom had benign thyroid nodules and 110 of whom had malignant ones. When compared to ultrasound elastography, FNAC showed somewhat better sensitivity (92.00%) and specificity (85.33%) for benign nodules. On the other hand, for malignant nodules, FNAC showed better specificity (80.95%) and sensitivity (91.82%) than ultrasonic elastography. In all age categories, FNAC consistently performed better than ultrasound elastography. The total accuracy obtained by ultrasound elastography was 81.94%, but the accuracy obtained by FNAC was higher at 85.47%. Ultrasound elastography's ideal cutoff value was found to be 4.2, with a sensitivity of 87.25% and a specificity of 78.40%. Conclusion Ultrasound elastography shows significant promise as a non-invasive, real-time complementary tool to FNAC for diagnosing thyroid nodules.

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

ObjectiveTo develop a ultrasound images based dual-channel deep learning model to achieve accurate early diagnosis of thyroid nodules less than 1 cm. MethodsA dual-channel deep learning model called thyroid nodule transformer network (TNT-Net) was proposed. The model has two input channels for transverse and longitudinal ultrasound images of thyroid nodules, respectively. A total of 9649 nodules from 8455 patients across five hospitals were retrospectively collected. The data were divided into a training set (8453 nodules, 7369 patients), an internal test set (565 nodules, 512 patients), and an external test set (631 nodules, 574 patients). ResultsTNT-Net achieved an area under the curve (AUC) of 0.953 (95 % confidence interval (CI): 0.934, 0.969) on the internal test set and 0.941 (95 % CI: 0.921, 0.957) on the external test set, significantly outperforming traditional deep convolutional neural network models and single-channel swin transformer model, whose AUCs ranged from 0.800 (95 % CI: 0.759, 0.837) to 0.856 (95 % CI: 0.819, 0.881). Furthermore, feature heatmap visualization showed that TNT-Net could extract richer and more energetic malignant nodule patterns. ConclusionThe proposed TNT-Net model significantly improved the recognition capability for thyroid nodules with size less than 1 cm. This model has the potential to reduce overdiagnosis and overtreatment of such nodules, providing essential support for precise management of thyroid nodules while complementing fine-needle aspiration biopsy.

The Horizon of Thyroid Imaging Reporting and Data System in the Diagnostic Performance of Thyroid Nodules: Clinical Application and Future Perspectives.

The widespread occurrence of thyroid nodules and the typically slow progression of thyroid cancer have led to the development of the thyroid imaging reporting and data system (TI-RADS). The primary objectives behind the development of TI-RADS were to minimize unnecessary biopsies of non-cancerous nodules, enhance the overall precision of diagnosis and establish a uniform risk-stratification framework based on the lexicon to notify healthcare professionals of nodules that require a biopsy. The identification and precise diagnosis of thyroid nodules have led to improved clinical practice examination reports within the general population. TI-RADS is a risk-stratification system related to thyroid lesions and based on ultrasound characteristics and is similar to the structure of the breast imaging reporting and data system. There are various versions of TI-RADS, with some being widely used and adequately validated, while others lacking thorough evaluation. TI-RADS uses a numerical scoring system for characteristics, and its categories are determined by the cumulative score of a thyroid nodule, indicating the likelihood of it being benign or malignant. In this article, the various TI-RADS systems were examined as a successful method for producing precise and comprehensive documentation, with a particular emphasis on their functionality, similarities, distinctions and potential future developments.

The accuracy of fine-needle aspiration cytology and ultrasonography in assessing thyroid nodules in correlation with histopathology: a retrospective study.

Accurately diagnosing thyroid nodules is vital for preventing unnecessary surgeries and providing prompt therapy. Although fine-needle aspiration cytology (FNAC) and ultrasonography (US) are widely used diagnostic methods, their reliability is questioned. This study investigates the effectiveness of US and FNAC in thyroid nodule diagnosis and differentiates benign from malignant nodules in relation to final histopathological diagnosis. A retrospective study including 307 adult patients with thyroid diseases who underwent neck US and FNAC before surgery was conducted between April 2019 and May 2023. The diagnostic efficacy of US, FNAC, and their combination usage was compared to histopathological results. Histopathological findings revealed that 187 (61%) cases were benign, while 120 (39%) were malignant. The US features of 'taller-than-wider' forms and hypoechoic appearance had the highest diagnostic accuracy in characterizing malignant thyroid nodules, with 83 and 73% accuracy, respectively. The combination of US parameters demonstrated high sensitivity, specificity, positive predictive value, and negative predictive value (NPV) of 88.33, 63.10, 60.6, and 89.4%, with a statistically significant area under the ROC curve (AUC: 0.828, P<0.001) than individual parameters. FNAC's sensitivity, specificity, PPV NPV, and accuracy in detecting malignant lesions were 50, 95, 86, 75, and 77%, respectively, with acceptable discrimination and statistical significance (AUC: 0.723, P<0.0001). The combination of US parameters and FNAC significantly improved the AUC value (AUC: 0.878, P<0.0001), sensitivity (83.33%), and specificity (79.14%). Univariate analysis showed that hypoechoic appearance, heterogenicity, large mass size (>4cm), 'taller-than-wider', infiltrative margins, and microcalcifications were risk factors for malignancy in thyroid nodules and were statistically significant (all P-values <0.05). Combining US characteristics with FNAC results can afford the maximum analytical accuracy in distinguishing benign from malignant thyroid nodules. This strategy is practical due to its simplicity, minimal invasiveness, and cost-effectiveness, enabling robust management regimens and avoiding additional surgical procedures.

Ring-Enhancement on CEUS: Is it Useful in the Differential Diagnosis of Solid Thyroid Nodules?

To investigate the efficiency of contrast-enhanced ultrasound (CEUS) features, particularly ring-enhancement patterns, in the differential diagnosis of thyroid nodules. 302 nodules with CEUS ring-enhancement were retrospectively enrolled, including 135 benign and 167 malignant ones. The ring-enhancement patterns were classified into regular and irregular hyper- or hypo-ring enhancement. Comparative analyses of ultrasound (US) and CEUS features between benign and malignant nodules were performed. The diagnostic performances of the ring-enhancement patterns and Chinese Thyroid Imaging Reporting and Data System (C-TIRADS) were compared in nodules with different sizes. Irregular hypo-ring enhancement was much more common in malignancies than that in benign ones, and it was an independent predictor for thyroid malignant nodules. With irregular hypo-ring enhancement as the diagnostic criteria for malignant nodules, the specificity was higher than that of C-TIRADS (85.2% vs. 75.6%, p = .037) while the AUC was comparable (0.845 vs. 0.803, p = .136) in all nodules. When the nodule size was taken into account, the specificity and AUC were both significantly higher than those of C-TIRADS (92.8% vs. 81.1%, p = .021; 0.907 vs. 0.823, p = .026) in nodules ≥10 mm, which can decrease the unnecessary FNA rate. Irregular hypo-ring enhancement was a valuable CEUS feature for the differential diagnosis of thyroid nodules, especially in nodules ≥10 mm.

ThyFusion: A lightweight attribute enhancement module for thyroid nodule diagnosis using gradient and frequency-domain awareness

Accurate classification of thyroid nodules is a critical step in clinical diagnosis and plays a crucial role in guiding subsequent treatment planning. However, current deep learning methods lack the ability to effectively perceive the attributes of thyroid nodules. Specifically, convolutional neural network-based methods struggle to capture fine-grained attributes, such as echogenic foci, due to repeated downsampling operations. On the other hand, Transformer-based methods partition the image into blocks, which hinders the capture of continuous attributes such as margins, and require a large number of parameters. To overcome these limitations, this paper proposes a novel lightweight attribute enhancement module called ThyFusion. Firstly, a multi-scale Gaussian filtering attention module is developed to accurately capture fine-grained information. Secondly, a frequency-domain global regulation module is proposed to regulate global features and capture coarse-grained attributes. Finally, a cross domain mutual learning module is presented to fuse fine-grained and coarse-grained attributes. Extensive experiments were conducted to demonstrate the effectiveness of ThyFusion, and it was compared against 15 benchmark methods. ThyFusion achieves higher accuracy, F1 score, recall, and precision (87.18%, 87.12%, 87.36% and 87.10%). ThyFusion is a plug-and-play lightweight module that can be embedded behind any layer of a backbone network to enhance the accuracy of thyroid nodule classification. The advantages of ThyFusion in thyroid nodule classification can greatly streamline the process of automated diagnosis and improve the accuracy of thyroid diagnosis.

The Current Progress of Artificial Intelligence in Approach to Thyroid Nodules: A Narrative Review

Background: Artificial intelligence (AI) can play a significant role in the future of thyroidology. Thyroid nodules are common conditions that may benefit from AI through more accurate and efficient diagnosis, risk stratification, and medical or surgical management. Objective: This paper aims to review the latest developments in AI applications for diagnosing and managing thyroid nodules and cancers. Methods: English full-text articles published in the PubMed and Google Scholar databases from January 2014 to March 2024 were collected and reviewed to provide a comprehensive understanding of the topic. A total of 45 studies were selected based on relevance, robust methodology, statistical significance, and broader topic coverage. Results: Artificial intelligence has emerged as a powerful tool for managing thyroid nodules. First, several studies have demonstrated how AI-powered ultrasound interpretation enhances the diagnosis and classification of nodules while reducing the need for invasive fine-needle aspiration (FNA) biopsies. Second, AI significantly improves the cytopathological differentiation between benign and malignant thyroid nodules by minimizing reliance on pathologists' expertise and implementing standardized diagnostic criteria. When cytopathology is inconclusive, AI also aids in identifying molecular markers from omics data, distinguishing between normal and cancerous cells. Moreover, AI tools have been developed for prognosis assessment, predicting distant metastasis, recurrence, and surveillance by integrating medical imaging features with molecular and clinical factors. Additionally, some AI tools are designed for intraoperative evaluation, improving surgical techniques and reducing complications during thyroidectomy. In non-surgical treatments, several models have been developed to optimize therapeutic doses of radioactive iodine (RAI) and predict the outcomes of new drug formulations. Conclusions: Artificial intelligence has the potential to assist physicians in accurate thyroid nodule diagnosis, classification, decision-making, optimizing treatment strategies, and improving patient outcomes. However, there are still limitations to this technology. Artificial intelligence-driven tools require further advancements before they can be fully integrated into clinical practice and replace specialists.

Sonographic characteristics of thyroid nodules with a Halo

ObjectiveTo investigate the sonographic characteristics of thyroid nodules with a halo, explore the value of contrast-enhanced ultrasound (CEUS) combined with fine needle aspiration (FNA) in identifying nodules with a halo, and predict the risk of metastasis by analyzing the pathological features of the halo.MethodsA retrospective analysis was conducted on 185 postoperative cases of thyroid nodules accompanied by halos between January 2019 and December 2022. After describing the ultrasound characteristics of the thyroid nodules and their halos, all patients were divided into three groups, the first group (group I = CEUS only) of patients underwent CEUS, the second group (group II = CEUS + FNA) underwent FNA based on the first group, and the third group (group III = FNA only) underwent FNA directly. The CEUS and FNA results were graded using the Chinese Thyroid Imaging Report and Data System (C-TIRADS) and Bethesda Reporting System for Thyroid Cytopathology, respectively. Those graded below C-TIRADS 4b or Bethesda IV were defined as benign, and the results of FNA were referenced when the two methods were combined. The surgical pathology results were used as the gold standard. We plotted working curves to compare the diagnostic efficacy of CEUS and FNA alone and in combination in the diagnosis of thyroid nodules with halos. The pathological features of the halo were analyzed and the number of patients with cervical lymph node metastases was recorded.ResultsOne hundred and sixty patients met the requirements. Benign nodules were mainly characterized by a thin (0.75 ± 0.31 mm) and uniform halo with good integrity, while malignant nodules had a thicker (1.48 ± 0.51 mm) halo with uneven and irregular margins (P < 0.05). The sensitivity and specificity were highest when the cutoff value was 1.09 mm, with 76.08% and 84.29%, respectively. The halos of benign nodules were mostly hyper- or iso-enhanced, whereas the halos of malignant nodules were predominantly hypo-enhanced (P < 0.05). The areas under the curve (AUCs) for CEUS, FNA, and CEUS + FNA were 0.751(95% CI = 0.642–0.841), 0.863(95% CI = 0.767–0.929), and 0.918(95% CI = 0.834–0.967), respectively. Cervical lymph node metastasis occurred in only 13 (11.5%) malignant nodes with halos. The primary pathological components of the halo around malignant nodules were almost reactive hyperplastic fibrous tissue.ConclusionThe halo surrounding malignant thyroid nodules is thicker, with uneven and irregular margins, and shows hypo-enhancement on CEUS. Combining CEUS with FNA improves the diagnostic efficacy of thyroid nodules with halos. The reactive hyperplastic fibrous halo may be one of the reasons why malignant nodules are less likely to metastasize.

Effect of IGF-1 on Thyroid Nodules and its Relation to Insulin Resistance

Abstract Background The insulin/IGF-1 signaling pathway modulates the regulation of thyroid gene expression and it is an important factor in the proliferation and differentiation of thyroid cells. Numerous growth factors are identified in thyroid tissue: like epidermal growth factor (EGF), transforming growth factor- alpha (TGF-alpha), IGF receptor (IGF-R), insulin-like growth factor-1 (IGF-1), IGF1-receptor (IGF-R) and IGF binding proteins (IGFBPs) Overexpression of these growth factors and/or their receptors may play a role in the growth of the thyroid nodules. in addition to TSH, insulin is also a thyroid growth factor that stimulates the growth of thyroid cells. Aim of Work The aim of this study is to investigate the possible association between IGF-1 and thyroid nodules by determining the effect of serum IGF-1 on thyroid nodules and its u/s findings and to investigate IGF-1 relation with insulin resistance (IR) and whether IR also plays a role in the thyroid nodular formation and its ultrasonography(u/s) findings. Patients and Methods A total of 80 medically free euthyroid patients with thyroid nodules detected by clinical examination (palpation) and radiologically by neck u/s screening were selected from out patient endocrine clinic at Ain Shams University hospitals. for all participants the following was done: Glycemic profile (fasting plasma glucose (mg/dl), 2hours post prandial plasma glucose (mg/dl) and HBA1C(%)), Lipid profile (total cholesterol (mg/dl), LDL (mg/dl), HDL (mg/dl), triglycerides (mg/dl)),The thyroid function evaluation (free tetra iodothyronine (FT4)(ng/dl), (free tri iodothyronine (FT3)(pg./ml) and serum thyroid stimulating hormone (TSH)(uIU/ml), IGF-1 determined by enzyme linked immunosorbent assay (ELISA), Fasting serum insulin determined by (ELISA), HOMA-IR was determined for all patients as a quantitative method for insulin resistance. Neck u/s was done for all patients with TIRADS score of the nodule. Results The study conducted on 80 medically free euthyroid patients with thyroid nodules and revealed that IGF-1 was high in patients with thyroid nodules. but there was no statistical association with nodular number, size or volume, p value (0.184,0.75,0.25), respectively. there was a statistically significant association between IGF-1 and TIRADS score of the nodule, p value = (0.039). There was an association between HOMA-IR, volume and size of the nodules, p value (0.023,0.013), respectively. but no statistical significance with number of the nodules, p value (0.279). by logistic regression analysis HOMA-IR can’t be used as a predictor of nodular size and volume p value (0.384). there was a statistical significance between presence of metabolic syndrome and number of nodules, p value (0.048). also, there was no association between serum IGF-1 and HOMA-IR, p value (0.077). Conclusion IGF complex is involved in thyroid development and seems to play an important role in thyroid nodules formation. There is an association between IGF-1 and thyroid nodules but it may exert its effect through autocrine and paracrine pathways; therefore, the use of circulating IGF-1 levels in predicting and diagnosing thyroid nodules is not advisable. There is an association between metabolic syndrome and number of thyroid nodules, also a significant relationship was found between nodule formation and insulin resistance. Presence of Insulin resistance leads to higher nodular volume and size in non-diabetic euthyroid patients but HOMA-IR can’t be used as a predictor of nodular size or volume. However, these data must be confirmed by further studies in the future.

Evaluation of US Elastography in Thyroid Nodule Diagnosis: The ElaTION Randomized Control Trial.

Background There is variable evidence and no randomized trials on the benefit of US elastography-guided fine-needle aspiration cytology (FNAC) over conventional US-guided FNAC alone for thyroid nodules. Purpose To compare the efficacy of US elastography-guided FNAC versus US-guided FNAC in reducing nondiagnostic rates for thyroid nodules. Materials and Methods A pragmatic, multicenter randomized controlled trial was performed at 18 secondary and tertiary hospitals across England between February 2015 and September 2018. Eligible adults with single or multiple thyroid nodules who had not previously undergone FNAC were randomized (1:1 ratio) to US elastography FNAC (intervention) or conventional US FNAC (control). The primary outcome was the proportion of patients who have a nondiagnostic cytologic Thy1 (British Thyroid Association system) result following the first FNAC. Results A total of 982 participants (mean age, 51.3 years ± 15 [SD] [IQR, 39-63]; male-to-female ratio, 1:4) were randomized. Of the 493 participants who underwent US elastography, 467 (94.7%) were examined with strain US elastography. There was no difference between the two arms in the nondiagnostic (Thy1) rate following the first FNAC (19% vs 16%; risk difference [RD], 0.03 [95% CI: -0.01, 0.07]; P = .11) or in the median time to reach the final definitive diagnosis (3.3 months [IQR, 1.5-6.4] for US elastography FNAC vs 3.4 months [IQR, 1.5-6.2] for US FNAC). All sensitivity analyses supported the primary analysis. Fewer participants in the US elastography FNAC arm underwent diagnostic hemithyroidectomy than in the US FNAC arm (183 of 493 [37%] vs 196 of 489 [40%]), but this was not statistically significant (adjusted RD, 0.02 [95% CI: -0.06, 0.01]; P = 0.15). There was no evidence of a difference in malignancy rates between the two arms: 70 of 493 (14%) in US elastography FNAC arm versus 79 of 489 (16%) in US FNAC arm (P = .39). There was also no difference in the rate of benign histologic findings between the groups (RD, -0.01 [95% CI: -0.04, 0.03]; P = .7). Conclusion Strain US elastography does not appear to have additional benefit over conventional US FNAC in the diagnosis of malignancy in thyroid nodules. Clinical trial registration no. ISRCTN18261857 Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Isikbay and Harwin in this issue.

Detecting thyroid nodules along with surrounding tissues and tracking nodules using motion prior in ultrasound videos

Ultrasound examination plays a crucial role in the clinical diagnosis of thyroid nodules. Although deep learning technology has been applied to thyroid nodule examinations, the existing methods all overlook the prior knowledge of nodules moving along a straight line in the video. We propose a new detection model, DiffusionVID-Line, and design a novel tracking algorithm, ByteTrack-Line, both of which fully leverage the prior knowledge of linear motion of nodules in thyroid ultrasound videos. Among them, ByteTrack-Line groups detected nodules, further reducing the workload of doctors and significantly improving their diagnostic speed and accuracy. In DiffusionVID-Line, we propose two new modules: Freq-FPN and Attn-Line. Freq-FPN module is used to extract frequency features, taking advantage of these features to reduce the impact of image blur in ultrasound videos. Based on the standard practice of segmented scanning by doctors, Attn-Line module enhances the attention on targets moving along a straight line, thus improving the accuracy of detection. In ByteTrack-Line, considering the characteristic of linear motion of nodules, we propose the Match-Line association module, which reduces the number of nodule ID switches. In the testing of the detection and tracking datasets, DiffusionVID-Line achieved a mean Average Precision (mAP50) of 74.2 for multiple tissues and 85.6 for nodules, while ByteTrack-Line achieved a Multiple Object Tracking Accuracy (MOTA) of 83.4. Both nodule detection and tracking have achieved state-of-the-art performance.