Thyroid Ultrasonography Research Articles

Diagnostic efficacy of the contrast-enhanced ultrasound thyroid imaging reporting and data system classification for benign and malignant thyroid nodules.

The contrasted-enhanced ultrasound thyroid imaging reporting and data system (CEUS TI-RADS) is the first international risk stratification system for thyroid nodules based on conventional ultrasound (US) and CEUS. This study aimed to evaluate the diagnostic efficacy of CEUS TI-RADS for benign and malignant thyroid nodules and to assess the related interobserver agreement. The study recruited 433 patients who underwent thyroid US and CEUS between January 2019 and June 2023 at the Affiliated Hospital of Guangdong Medical University. A retrospective analysis of 467 thyroid nodules confirmed by fine-needle aspiration (FNA) and/or surgery was performed. Further, a CEUS TI-RADS classification was assigned to each thyroid nodule based on the CEUS TI-RADS scoring criteria for the US and CEUS features of the nodule. The nodules were grouped based on their sizes as follows: size ≤1 cm, group A; size >1 and ≤4 cm, group B; and size >4 cm, group C. Multivariate logistic regression was used to analyze independent risk factors for malignant thyroid nodules. Pathological assessment was the reference standard for establishing the sensitivity (SEN), specificity (SPE), accuracy (ACC), positive predictive value (PPV), and negative predictive value (NPV) of CEUS TI-RADS in diagnosing malignant thyroid nodules. The area under the curve (AUC) in the receiver operating characteristic (ROC) curve analysis was used to compare the diagnostic efficacy of the scoring system in predicting malignancy in three groups of nodules. The intragroup correlation coefficient (ICC) was adopted to assess the interobserver agreement of the CEUS TI-RADS score. Out of the 467 thyroid nodules, 262 were malignant and 205 were benign. Logistic regression analysis revealed that the independent risk factors for malignant thyroid nodules included punctate echogenic foci (P<0.001), taller-than-wide shape (P=0.015), extrathyroidal invasion (P=0.020), irregular margins/lobulation (P=0.036), hypoechoicity on US (P=0.038), and hypoenhancement on CEUS (P<0.001). The AUC for the CEUS TI-RADS in diagnosing malignant thyroid nodules was 0.898 for all nodules, 0.795 for group A, 0.949 for group B, and 0.801 for group C, with the optimal cutoff values of the CEUS TI-RADS being 5 points, 6 points, 5 points, and 5 points, respectively. Among these groups of nodules, group B had the highest AUC, with the SEN, SPE, ACC, PPV, and NPV for diagnosing malignant nodules being 95.9%, 88.1%, 92.8%, 92.6%, and 93.2%, respectively. The ICC of the CEUS TI-RADS classification between senior and junior physicians was 0.862 (P<0.001). In summary, CEUS TI-RADS demonstrated significant efficacy in distinguishing thyroid nodules. Nonetheless, there were variations in its capacity to detect malignant nodules across diverse sizes, and it demonstrate optimal performance in 1- to 4-cm nodules. These findings may serve as important insights for clinical diagnoses.

Thyroid Nodule Characterization: Overview and State of the Art of Diagnosis with Recent Developments, from Imaging to Molecular Diagnosis and Artificial Intelligence.

Ultrasound (US) is the primary tool for evaluating patients with thyroid nodules, and the risk of malignancy assessed is based on US features. These features help determine which patients require fine-needle aspiration (FNA) biopsy. Classification systems for US features have been developed to facilitate efficient interpretation, reporting, and communication of thyroid US findings. These systems have been validated by numerous studies and are reviewed in this article. Additionally, this overview provides a comprehensive description of the clinical and laboratory evaluation of patients with thyroid nodules, various imaging modalities, grayscale US features, color Doppler US, contrast-enhanced US (CEUS), US elastography, FNA biopsy assessment, and the recent introduction of molecular testing. The potential of artificial intelligence in thyroid US is also discussed.

A retrospective analysis thyroid function and ultrasonography in a group of subjects with lepramatous leprosy in Turkey.

There are several studies on thyroid functions and thyroid gland features in patients with leprosy in the literature. The relationship between them have not been clarified yet. These studies are time-expired and don't contain ultrasonography examination. The purpose of the study is to investigate thyroid functions and gland characteristics in leprosy patients by ultrasonography (US) and current laboratory techniques. This retrospective study was conducted by collecting the data of patients with lepramatous leprosy. Serum thyroid-stimulating hormone, free triiodothyronine, free thyroxine, anti-thyroid peroxidase, antithyroglobulin, and thyroglobulin values and thyroid ultrasonography reports were collected from previous records. The mean age is 75.12±9.89 years of total 17 subjects and 10 patients (58.8%) were male. Thyroid US was performed on 14 of the patients, nodules were detected in a total of 7 (50%) patients. The mean FT3, FT4, TSH, Anti-Tpo, Anti-TG, and TG values of the patients were found to be within normal limits. In the present study, no changes were detected in the thyroid functions and structures of the patients with Lepromatous Leprosy. We consider that prospective randomized studies that will include larger sample sizes are needed to determine whether there is a relationship between leprosy and thyroid disease.

Diagnosis of Thyroid Nodules in Children and Adolescents with Subclinical Hypothyroidism and Their Outcomes after Early Thyroxine Treatment-A Longitudinal Study.

Pediatric thyroid nodules (TNs) present a higher malignancy rate compared to adults. We sought to diagnose the frequency and characteristics of TNs in children and adolescents with subclinical hypothyroidism (SH) and their outcomes after levothyroxine (LT4) therapy. A total of 256 children with TNs and SH were followed every semester from 2006 to 2018. All patients were treated with LT4. Clinical and radiologic findings, such as the size and texture of the nodules, were documented. Analysis included one-way ANOVA, Kruskal-Wallis, Chi-square, and Fisher's exact tests. After initial LT4 therapy, TNs disappeared in 85.5% and did not reappear throughout follow-up. In 14.5%, TNs remained the same or increased in size, but they decreased after subsequent LT4 administration with an increased dose. Thyroid disease family history (FHTD) was documented in 77.0%. In total, 64.5% developed a goiter, 46.0% exhibited thyroid heterogeneity on ultrasound, 23.4% had positive Anti-Tg, and 25.4% had positive anti-TPO autoantibodies. Our findings support the possible premise that early pharmacologic intervention with LT4 may be beneficial in children and adolescents with TNs and SH. The increased frequency of FHTD, goiter, thyroid heterogeneity, and Hashimoto in our patients emphasizes that thyroid ultrasounds may be warranted in children and adolescents with these characteristics in order to rule out the presence of TNs.

Evaluation of Thyroid Nodule by US Including Elastography versus MRI T2W and Diffusion Sequences

Abstract Background The thyroid gland frequently develops thyroid nodules. Effective treatment of malignant thyroid nodules depends on an early and accurate diagnosis. Benign and malignant thyroid nodules are typically distinguished using conventional thyroid ultrasonography (US). In order to explore changes in tissue stiffness, strain elastography (SE) uses an external force and a deformation response detector. A promising method for distinguishing between benign and malignant thyroid nodules is ultrasound elastography. Malignant versus benign thyroid nodules might be distinguished using MRI apparent diffusion coefficient (ADC) values. This study compares MRI T2W and diffusion sequences with ultrasound, which includes elastography, to assess thyroid nodules. Methods This cross-sectional research was carried out at Ain-Shams University's radiodiagnosis department. It included 23 female or male patients with suspicious thyroid nodule by clinical examination, or ultrasonography including some cases elastography if present for further work up with MR diffusion subjected to DWI and ADC value and results were compared with histopathology if present or follow up of the patients. The duration of the study was 24 months. Results Diffusion had an accuracy of 91.3%, while the ADC value and elastography had a greater diagnostic accuracy with an area under the curve of 95.7% in discriminating between benign and malignant cases. Conclusions When describing thyroid nodules, ADC value provided better diagnostic performance than US TIRADS rating. Over and above ACR-TIRADS classification, useful information is added by ultrasound elastography and strain ratio analysis of thyroid nodules. It is advised as an auxiliary tool. However, the distinction of cancerous and benign thyroid nodules might potentially be done with greater precision using diffusion weighted MRI.

Preoperative prediction of central lymph node metastasis in follicular variant of papillary thyroid carcinoma using clinical and ultrasound features.

The most common metastatic site of follicular variant of papillary thyroid carcinoma (FVPTC) is the central lymph nodes, which may be associated with the prognosis and survival of patients. In the present study, we establish a combined model based on preoperative clinical and ultrasound (US) features of FVPTC to predict the risk of central lymph node metastasis (CLNM). From January 2013 to December 2022, 315 patients with FVPTC were enrolled and randomly divided into the training and validation cohorts in a ratio of 7:3. The independent risk factors for CLNM in FVPTC were analysed using univariate and multivariate logistic regression analyses. Then, three different models were established based on clinical and US data. Subsequently, a nomogram was constructed to predict CLNM. Its predictive effect was evaluated via receiver operating characteristic and calibration curve analyses. Backward multivariate regression analysis revealed that age (P=0.001), thyroid peroxidase antibody (TPOAb) (P=0.11), diameter (P=0.047), irregular/lobulated margin (P=0.15), extrathyroidal extension (P=0.001), nodules with macrocalcifications (P=0.009), nodules with microcalcification (P=0.003) and Thyroid Imaging Reporting and Data System (ACR-TI-RADS) category 5 (P=0.33) were independent risk factors for CLNM in FVPTC. The areas under the curve of the matching nomogram in the training (N=221) and validation cohorts (N=94) were 0.841 [95% confidence interval (CI): 0.788-0.895] and 0.735 (95% CI: 0.621-0.872), respectively. Preoperative thyroid US provides useful features for prediction of CLNM. The nomogram constructed based on combining US and clinical features can better predict the risk of CLNM and may facilitate decision-making in clinical settings.

The Causes of Thyrotoxicosis, Clinical Features, and Treatment Strategies in a Former Iodine Deficient Area

Thyrotoxicosis is a hypermetabolic condition caused by excess thyroid hormones in the circulation with/without increased production from the thyroid gland. In this prospective study, we aimed to investigate the causes of thyrotoxicosis, clinical features, and treatment strategies in a former iodine-deficient area. Thyroid function tests, antithyroid and antithyroid receptor antibodies, and routine thyroid ultrasonography was obtained, and a thyroid scintigraphy/radioactive iodine uptake test was performed on need. A statistically significant difference was found between toxic multinodular goiter (TMNG) and Graves’ disease (GD) groups when mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), alanine aminotransferase (ALT), and aspartate aminotransferase (AST) values were analyzed. TSH levels were significantly lower in GD patients compared to those in TMNG and TNG patients, but free triiodothyronine (FT3) and free thyroxine (FT4) values were higher. A high level of TSH receptor antibody (TRAb) was observed in patients with normal antithyroid peroxidase (Anti-TPO). TRAb levels were found to be high. Anti-TPO and anti-thyroglobulin (Anti-Tg) levels were observed to be positively correlated with sT3 and sT4 levels. TMNG is the leading cause of thyrotoxicosis; despite sufficient iodide intake in our former iodine-deficient region, TMNG is characteristically seen in older patients with much lower thyroid hormone levels than GD. According to the study results, the diagnosis of patients with thyrotoxicosis, their clinical presentation, the treatment they will receive, early detection of postoperative complications were predicted

Survey of clinician perspective on management of papillary thyroid microcarcinoma in Australia and New Zealand.

The incidence of thyroid cancer has been rapidly increasing in recent years largely due to improved diagnostic methods. There is evidence to suggest that in papillary thyroid microcarcinoma (PTMC), active surveillance (AS) is comparable in effectiveness compared to immediate surgery (IM). We conducted a survey of Clinicians and Surgeons from Australia and New Zealand to assess the role of AS in the management of PTMC. A short electronic survey was created on the platform Survey Monkey, separate links containing the survey were sent to various medical societies to be distributed to its members. The list of medical societies included: General Surgeons Australia, Endocrine Society of Australia, Australian and New Zealand Endocrine Surgeons, Australian and New Zealand Head and Neck Cancer Society and New Zealand Association of General Surgery. We received 110 complete responses, which demonstrated that 63% of clinicians will discuss AS with patients diagnosed with PTMC. Surgeons are more likely to discuss AS compared to endocrinologists (P=0.03). Forty-eight percent of respondents report managing patients with AS in the past year, those who are able to perform thyroid ultrasounds are more likely to utilise AS (P=0.03). Common perceived barriers to AS include patient anxiety, lack of access to regular follow-up and lack of patient compliance. Our survey shows that Australian and New Zealand clinicians are generally aware of AS as a treatment option for PTMC, but there remain considerable barriers for common implementation.

A Multi-View Deep Learning Model for Thyroid Nodules Detection and Characterization in Ultrasound Imaging.

Thyroid Ultrasound (US) is the primary method to evaluate thyroid nodules. Deep learning (DL) has been playing a significant role in evaluating thyroid cancer. We propose a DL-based pipeline to detect and classify thyroid nodules into benign or malignant groups relying on two views of US imaging. Transverse and longitudinal US images of thyroid nodules from 983 patients were collected retrospectively. Eighty-one cases were held out as a testing set, and the rest of the data were used in five-fold cross-validation (CV). Two You Look Only Once (YOLO) v5 models were trained to detect nodules and classify them. For each view, five models were developed during the CV, which was ensembled by using non-max suppression (NMS) to boost their collective generalizability. An extreme gradient boosting (XGBoost) model was trained on the outputs of the ensembled models for both views to yield a final prediction of malignancy for each nodule. The test set was evaluated by an expert radiologist using the American College of Radiology Thyroid Imaging Reporting and Data System (ACR-TIRADS). The ensemble models for each view achieved a mAP0.5 of 0.797 (transverse) and 0.716 (longitudinal). The whole pipeline reached an AUROC of 0.84 (CI 95%: 0.75-0.91) with sensitivity and specificity of 84% and 63%, respectively, while the ACR-TIRADS evaluation of the same set had a sensitivity of 76% and specificity of 34% (p-value = 0.003). Our proposed work demonstrated the potential possibility of a deep learning model to achieve diagnostic performance for thyroid nodule evaluation.

The common pathogenesis of nodular goiter in both sexes: An exploration into gene expression and signaling pathways

The past few years have witnessed an increasing incidence of nodular goiter (NG), with a well-documented higher prevalence in females than males. This gender disparity has led research to focus primarily on female subjects, potentially overlooking common pathogenic mechanisms in both sexes. In this study, we investigated the shared pathogenesis of NG in males and females. Utilizing a rat model and RNA sequencing, we identified differentially expressed genes associated with the disease. We further validated these findings in normal human thyroid cells and human papillary thyroid cancer cells. A randomized experiment was conducted with equal numbers of male and female rats divided into control and NG model groups. The NG model was established using propylthiouracil and various assessments such as thyroid ultrasonography, thyroid index, thyroid function, and thyroid histology were performed. Transcriptome analysis revealed numerous upregulated and downregulated genes in both male and female model groups. Key genes like KDR, FLT1, PDGFB, and CAV1, and pathways including PI3K-Akt, MAPK, Ras, fluid shear stress and atherosclerosis, calcium signaling, and Rap1 signaling pathways were linked with the disease. Western blot and immunofluorescence analysis confirmed these findings, which were further supported by cell-based experiments. In conclusion, our findings suggest that abnormal expression of specific genes and pathways leading to irregular cell growth, blood vessel formation, and inflammation may be common factors in the pathogenesis of NG in both males and females.

Technetium-99m (99mTc) and Iodine-123 (123I) in comparison with thyroid ultrasonography in the differential diagnosis of Saudi patients with Graves, disease

In thyroid autoimmune diseases diagnosis, there is growing evidence that thyroid ultrasonography (US) can be helpful without accurate differentiation of Graves’ disease GD from other autoimmune diseases. Using histopathological findings as a reference standard, this study aimed to determine the diagnostic accuracy of 99mTc and 123I in comparison with US for the differential diagnosis of GD in Saudi patients. Results demonstrated that thyroid scintigraphy using 99mTc (sensitivity = 96.1 vs. 23.5%) and 123I (sensitivity = 83.33 vs. 25%) was superior to US in detection of GD in Saudi patients. All GD patients detected by US were detected by both 99mTc and 123I scans, whereas, 99mTc (37/39) and 123I (14/18) scans detected many patients from GD cases that US failed to detect. This superiority was found regardless of gender and age particularly in 99mTc scan. In the same group of patients, both 99mTc and 123I scans had the same sensitivity (80%) (P = 0.151). In conclusion, the conducting study findings proved that 99mTc and 123I thyroid scintigraphy scans could be used in the differential diagnosis of GD from other thyroiditis disorders with a higher degree of diagnostic accuracy.

Ultrasound screening of thyroid pathology in primary medical care in Bulgaria

Thyroid diseases are common and, in most cases, can be safely and effectively detected and treated in primary medical care. This article aimed to analyze and evaluate the rate of thyroid ultrasonographic abnormalities in a primary medical care practice in Bulgaria. The research was conducted from 2016 to 2021. A random cohort of patients undergone annual preventive screening was included. Demographic information (age and sex) was collected. The descriptions of the ultrasonographic findings were standardized based on the following parameters: deviations in shape, size, position of the thyroid gland, deviations from normal parenchymal echogenicity (hyper-, hypo-, and heteroechogenic parenchyma), presence and size of detectable formations, and presence of calcifications. The total number of participants in this study was 3 178. Of these, 60% (1 907/3 178) were women and 40% (1 271/3 178) were men. The average age of participants was 40.1 &amp;plusmn; 11.3 years, and there was no significant difference between the males and females. Deviations from normal ultrasonographic findings were observed in 36.2% (1 151/3 178), with a frequency increasing with age. Detectable formations were seen in 19.7% (625/3 178) of the patients, and those larger than 1 cm accounted for 4.4% (139/3 178) of all cases and 22.2% of all formations (139/625). Calcifications were found in 0.5% (15/3 163). Over 1/3 of the performed thyroid ultrasounds revealed abnormalities. Thyroid ultrasonographic abnormalities were significantly more common in women compared to men, and their frequency increased with age.

Correlation between ultrasonographic and cytologic features of thyroid nodules: a single-center cross-sectional study.

A thyroid nodule is managed according to the clinical context, ultrasound (US) findings, and fine needle aspiration (FNA) results. Most thyroid nodules are benign; however, nodule classification is crucial to avoid unnecessary thyroid surgery. We conducted this study to compare the findings of fine-needle aspiration cytology (FNAC) expressed using the Bethesda system with the features of thyroid US classified using the EU-TIRADS classification to assess the risk of malignancy. A descriptive and analytical study involving 99 patients with thyroid nodules followed up in the Department of Endocrinology-Diabetology and Nutrition. Data were collected from medical records and analyzed using SPSS software V21. FNA was performed on 121 nodules using the BETHESDA system. These nodules were classified as malignant, suspicious for follicular neoplasm, and suspicious for malignancy in 5.8%, 5%, and 1.7% of cases, respectively. As for the EU-TIRADS 2017 classification, 59.5% of benign nodules were classified as EU-TIRADS III, whereas 66.7% of malignant nodules were classified as EU-TIRADS V and significantly related to malignant prediction (P = 0.000). The size of nodules was significantly correlated to the risk of malignancy (P = 0.013). Seventy-five percent of nodules with central vascularity were malignant (P = 0.012). Irregularity of nodule contours was significantly associated with the risk of malignancy, as 30% of nodules with irregular contours were Bethesda VI (P = 0.003). Hypoechogenicity was found in 77.8% of malignant nodules (P = 0.004). Additionally, only 9.2% of the nodules were taller than wide, of which 37.5% were malignant (P = 0.012). For a safe management strategy, US-guided FNAC should be performed on each suspicious thyroid nodule, given the correlation between EU-TIRADS classification features and the risk of malignancy.

Ultrasonographic Findings of Thyroid Parenchymal Disease

Thyroid parenchymal disease is an inflammatory disease that occurs in the thyroid parenchyma due to autoimmunity or infection. The differential diagnosis of thyroid parenchymal disease is based on clinical manifestation, physical examination, and serological findings. However, ultrasonography of thyroid has also a role in the diagnosis of thyroid parenchymal disease. This review describes common findings of ultrasonography in each thyroid parenchymal disease.

Super-resolution ultrasound and microvasculomics: a consensus statement.

This is a summary of a consensus statement on the introduction of "Ultrasound microvasculomics" produced by The Chinese Artificial Intelligence Alliance for Thyroid and Breast Ultrasound. The evaluation of microvessels is a very important part for the assessment of diseases. Super-resolution ultrasound (SRUS) microvascular imaging surpasses traditional ultrasound imaging in the morphological and functional analysis of microcirculation. SRUS microvascular imaging relies on contrast microbubbles to gain sensitivity to microvessels and improves the spatial resolution of ultrasound blood flow imaging for a more detailed depiction of vascular structures and hemodynamics. This method has been applied in preclinical animal models and pilot clinical studies, involving areas including neurology, oncology, nephrology, and cardiology. However, the current quantitative parameters of SRUS images are not enough for precise evaluation of microvessels. Therefore, by employing omics methods, more quantification indicators can be obtained, enabling a more precise and personalized assessment of microvascular status. Ultrasound microvasculomics-a high-throughput extraction of image features from SRUS images - is one novel approach that holds great promise but needs further validation in both bench and clinical settings. CLINICAL RELEVANCE STATEMENT: Super-resolution Ultrasound (SRUS) blood flow imaging improves spatial resolution. Ultrasound microvasculomics is possible to acquire high-throughput information of features from SRUS images. It provides more precise and abundant micro-blood flow information in clinical medicine. KEY POINTS: This consensus statement reviews the development and application of super-resolution ultrasound (SRUS). The shortcomings of the current quantification indicators of SRUS and strengths of the omics methodology are addressed. "Ultrasound microvasculomics" is introduced for a high-throughput extraction of image features from SRUS images.

Retrospective analysis of thyroid incidentalomas detected by [68Ga]Ga-PSMA-11 PET/CT.

Prostate cancer patients, undergo imaging procedures, with [68Ga]Ga-PSMA-11 PET/CT (prostate-specific membrane antigen based positron emission tomography/computed tomography) utilized for primary and secondary staging. PSMA thyroid incidentalomas (PTI) are discovered in the thyroid gland while imaging prostate cancer patients with [68Ga]Ga-PSMA-11 PET/CT. The aim of the study was to determine the clinical significance of PTIs detected on [68Ga]Ga-PSMA-11 PET/CT. Another goal was to identify a possible threshold for the maximum standardized uptake value (SUVmax), above which a malignant growth could be suspected. A retrospective cross-sectional study. 769 patients with prostat cancer who underwent [68Ga]Ga-PSMA-11 PET/CT scans in the nuclear medicine department of a tertiary care hospital between January 2020 and December 2022 were retrospectively screened in this study. We analyzed 67 patients in whom PTI was detected. Patients who exceeded the inclusion criteria had their thyroid ultrasonography and ultrasonography -guided fine needle aspiration findings analyzed. PTI was discovered in 67 patients (8%). 42 patients who met the inclusion and exclusion criteria were included in the study. Of the 4 malignant patients (9.5%) in the study population, 2 were classified as TIRADS 3 and 2 were classified as TIRADS 4. The cut-off SUVmax value was found to be 5.6. With 100% sensitivity and 47.37% specificity, a cutoff SUVmax of 5.3 was determined through receiver-operator characteristic analysis in order to predict malignant cytology. PTI is a significant clinical finding; most of diffuse and focal uptakes are frequently related to benign diseases. Each center should establish its own a possible SUVmax cut-off over which a malignant lesion should be suspected.

Machine learning to predict the occurrence of thyroid nodules: towards a quantitative approach for judicious utilization of thyroid ultrasonography.

Ultrasound is instrumental in the early detection of thyroid nodules, which is crucial for appropriate management and favorable outcomes. However, there is a lack of clinical guidelines for the judicious use of thyroid ultrasonography in routine screening. Machine learning (ML) has been increasingly used on big data to predict clinical outcomes. This study aims to leverage the ML approach in assessing the risk of thyroid nodules based on common clinical features. Data were sourced from a Chinese cohort undergoing routine physical examinations including thyroid ultrasonography between 2013 and 2023. Models were established to predict the 3-year risk of thyroid nodules based on patients' baseline characteristics and laboratory tests. Four ML algorithms, including logistic regression, random forest, extreme gradient boosting, and light gradient boosting machine, were trained and tested using fivefold cross-validation. The importance of each feature was measured by the permutation score. A nomogram was established to facilitate risk assessment in the clinical settings. The final dataset comprised 4,386 eligible subjects. Thyroid nodules were detected in 54.8% (n=2,404) individuals within the 3-year observation period. All ML models significantly outperformed the baseline regression model, successfully predicting the occurrence of thyroid nodules in approximately two-thirds of individuals. Age, high-density lipoprotein, fasting blood glucose and creatinine levels exhibited the highest impact on the outcome in these models. The nomogram showed consistency and validity, providing greater net benefits for clinical decision-making than other strategies. This study demonstrates the viability of an ML-based approach in predicting the occurrence of thyroid nodules. The findings highlight the potential of ML models in identifying high-risk individuals for personalized screening, thereby guiding the judicious use of ultrasound in this context.

Ultrasound thyroid size in young healthy women in the minsk city

Ultrasound thyroid size in young healthy women in the minsk city

Progression of Nodular Thyroid Disease in Familial Adenomatous Polyposis Syndrome: Refined Surveillance Recommendations

BackgroundPatients with familial adenomatous polyposis (FAP) have an increased risk of thyroid nodular disease. Previous studies demonstrated that screening thyroid ultrasound (US) will allow detection of nodules in 38% and thyroid cancer in 2.6% of patients. The aim of this study is to define the value of serial US evaluation at identifying disease progression in patients with FAP. MethodsRetrospective review from 2008 to 2023 at a single referral center. All patients with FAP and screening thyroid US were included. Patient demographics, initial US characteristics, follow-up regarding the development of new nodules and cancer were assessed using a Kaplan-Meier analysis. ResultsA total of 556 patients underwent screening. Fifty percent were male. Median age at first screening was 38 year old. Eighty percent underwent longitudinal follow-up for a median length of 7 years. At initial screening, 169 patients (30%) had nodules. For patients with normal baseline US, 14% developed a nodule overtime. A total of 20 patients (3.6%) were diagnosed with thyroid cancer. The cumulative incidence of initial and subsequent cancer was 4% by 5 years and 6% by 10 years, while the cumulative incidence of thyroid nodules was 40% and 48%, respectively. ConclusionsBased on the Kaplan-Meier analysis, ongoing longitudinal screening is warranted for patients with FAP as they are prone to thyroid cancer and nodule development overtime even when presenting with a baseline normal US. Additionally, these data demonstrate a slow development of thyroid cancer from a normal US, thus it is reasonable to consider selectively extending the screening interval for this population.

Diagnostic performance of artificial intelligence in interpreting thyroid nodules on ultrasound images: a multicenter retrospective study.

Thyroid nodules are commonly identified through ultrasound imaging, which plays a crucial role in the early detection of malignancy. The diagnostic accuracy, however, is significantly influenced by the expertise of radiologists, the quality of equipment, and image acquisition techniques. This variability underscores the critical need for computational tools that support diagnosis. This retrospective study evaluates an artificial intelligence (AI)-driven system for thyroid nodule assessment, integrating clinical practices from multiple prominent Thai medical centers. We included patients who underwent thyroid ultrasonography complemented by ultrasound-guided fine needle aspiration (FNA) between January 2015 and March 2021. Participants formed a consecutive series, enhancing the study's validity. A comparative analysis was conducted between the AI model's diagnostic performance and that of both an experienced radiologist and a third-year radiology resident, using a dataset of 600 ultrasound images from three distinguished Thai medical institutions, each verified with cytological findings. The AI system demonstrated superior diagnostic performance, with an overall sensitivity of 80% [95% confidence interval (CI): 59.3-93.2%] and specificity of 71.4% (95% CI: 53.7-85.4%). At Siriraj Hospital, the AI achieved a sensitivity of 90.0% (95% CI: 55.5-99.8%), specificity of 100.0% (95% CI: 69.2-100%), positive prediction value (PPV) of 100.0%, negative prediction value (NPV) of 90.9%, and an overall accuracy of 95.0%, indicating the benefits of AI's extensive training across diverse datasets. The experienced radiologist's sensitivity was 40.0% (95% CI: 21.1-61.3%), while the specificity was 80.0% (95% CIs: 63.6-91.6%), respectively, showing that the AI significantly outperformed the radiologist in terms of sensitivity (P=0.043) while maintaining comparable specificity. The inter-observer variability analysis indicated a moderate agreement (K=0.53) between the radiologist and the resident, contrasting with fair agreement (K=0.37/0.33) when each was compared with the AI system. Notably, 95% CIs for these diagnostic indexes highlight the AI system's consistent performance across different settings. The findings advocate for the integration of AI into clinical settings to enhance the diagnostic accuracy of radiologists in assessing thyroid nodules. The AI system, designed as a supportive tool rather than a replacement, promises to revolutionize thyroid nodule diagnosis and management by providing a high level of diagnostic precision.