Clinical value of artificial intelligence in thyroid ultrasound: a prospective study from the real world

OBJECTIVE

To evaluate the diagnostic performance of a commercial artificial intelligence (AI)-assisted ultrasonography (US) for thyroid nodules and to validate its value in real-world medical practice.

MATERIALS AND METHODS

From March 2021 to July 2021, 236 consecutive patients with 312 suspicious thyroid nodules were prospectively enrolled in this study. One experienced radiologist performed US examinations with a real-time AI system (S-Detect). US images and AI reports of the nodules were recorded. Nine residents and three senior radiologists were invited to make a "benign" or "malignant" diagnosis based on recorded US images without knowing the AI reports. After referring to AI reports, the diagnosis was made again. The diagnostic performance of AI, residents, and senior radiologists with and without AI reports were analyzed.

RESULTS

The sensitivity, accuracy, and AUC of the AI system were 0.95, 0.84, and 0.753, respectively, and were not statistically different from those of the experienced radiologists, but were superior to those of the residents (all p < 0.01). The AI-assisted resident strategy significantly improved the accuracy and sensitivity for nodules ≤ 1.5 cm (all p < 0.01), while reducing the unnecessary biopsy rate by up to 27.7% for nodules > 1.5 cm (p = 0.034).

CONCLUSIONS

The AI system achieved performance, for cancer diagnosis, comparable to that of an average senior thyroid radiologist. The AI-assisted strategy can significantly improve the overall diagnostic performance for less-experienced radiologists, while increasing the discovery of thyroid cancer ≤ 1.5 cm and reducing unnecessary biopsies for nodules > 1.5 cm in real-world medical practice.

KEY POINTS

• The AI system reached a senior radiologist-like level in the evaluation of thyroid cancer and could significantly improve the overall diagnostic performance of residents. • The AI-assisted strategy significantly improved ≤ 1.5 cm thyroid cancer screening AUC, accuracy, and sensitivity of the residents, leading to an increased detection of thyroid cancer while maintaining a comparable specificity to that of radiologists alone. • The AI-assisted strategy significantly reduced the unnecessary biopsy rate for thyroid nodules > 1.5 cm by the residents, while maintaining a comparable sensitivity to that of radiologists alone.

Cytological evaluation of thyroid nodules in children and young adults: a multi-institutional experience

PURPOSE

The utility of the Bethesda system for reporting thyroid cytopathology is debatable in determining the risk of malignancy in pediatric patients. Moreover, the upper age limit for defining the pediatric group has varied across different studies. The aim of this study is to compare the risk of malignancy (ROM) and risk of neoplasia (RON) across different Bethesda categories between the pediatric, young adult, and adult patients.

METHODS

This is a retrospective multi-institutional study performed in three Indian hospitals. ROM was calculated and compared across Bethesda categories in adult (>18 years) and pediatric age groups (≤18 years), with a subgroup analysis in young adults (19-21 years).

RESULTS

Thyroid nodules from a total of 5958 patients were subjected to fine needle aspiration. Of these 199 were pediatric (3.3%) and follow-up histology was available in 2276. The ROM and RON rates, including overall ROM/RON, were significantly higher in pediatric age group as compared to adults. Overall ROM of suspicious for malignancy and malignant categories was higher in children as compared to adults. The overall surgical resection rates were also higher in pediatric patients (45.2% vs. 35.7%; p < 0.01). The similar trend of increased ROM, RON and resection rates was seen among young adults as compared to adult age group.

CONCLUSION

Thyroid nodules presenting in children are more likely to be malignant than those in adults. Importantly, the young adult group behaved in a similar manner with regard to surgical resection rates, ROM and RON to pediatric.

Classification for thyroid nodule using ViT with contrastive learning in ultrasound images

The lack of representative features between benign nodules, especially level 3 of Thyroid Imaging Reporting and Data System (TI-RADS), and malignant nodules limits diagnostic accuracy, leading to inconsistent interpretation, overdiagnosis, and unnecessary biopsies. We propose a Vision-Transformer-based (ViT) thyroid nodule classification model using contrast learning, called TC-ViT, to improve accuracy of diagnosis and specificity of biopsy recommendations. ViT can explore the global features of thyroid nodules well. Nodule images are used as ROI to enhance the local features of the ViT. Contrast learning can minimize the representation distance between nodules of the same category, enhance the representation consistency of global and local features, and achieve accurate diagnosis of TI-RADS 3 or malignant nodules. The test results achieve an accuracy of 86.9%. The evaluation metrics show that the network outperforms other classical deep learning-based networks in terms of classification performance. TC-ViT can achieve automatic classification of TI-RADS 3 and malignant nodules on ultrasound images. It can also be used as a key step in computer-aided diagnosis for comprehensive analysis and accurate diagnosis. The code will be available at https://github.com/Jiawei217/TC-ViT.

Exposure to Bisphenol A increases malignancy risk of thyroid nodules in overweight/obese patients

Bisphenol A (BPA) is a widespread thyroid disruptor, but evidence about an association with thyroid cancer is weak. Excess body weight is a risk factor for thyroid cancer and affects activity of endocrine disruptors. Aim of the study was to investigate the association between BPA exposure and thyroid cancer, verifying the effect modification related to body weight. We performed a multicentre, cross-sectional study including consecutive patients referring for nodular goiter. The quantitative determination of BPA in serum samples was performed through high performance liquid chromatography system, coupled in tandem with ultraviolet and fluorescence detection. Ninety-six patients were included: 55 benign nodules, 41 thyroid cancers, 28 normal weight, and 68 overweight/obese. BPA was detected in 79 subjects. In the overall study population and in the group with BMI<25 kg/m² BPA exposure was not significantly correlated to thyroid cancer (p = 0.08 and 0.759, respectively). In the group with BMI≥25 kg/m², BPA-exposed subjects showed significantly higher risk of malignancy (OR: 5.3, p = 0.028). At multivariate analysis, such association was independent of smoking, alcohol consumption, occupational exposure, and phthalates exposure (p = 0.021 and 0.016, respectively), but was lost after adjustment for the presence of metabolic syndrome (p = 0.089). In overweight/obese subjects, BPA exposure was significantly associated with higher thyroid stimulating hormone levels. Our study suggests that BPA exposure is a risk factor for thyroid cancer in overweight/obese subjects.

A new discriminant strategy combined with four TIRADS screening procedures increases ultrasound diagnostic accuracy-focusing on "wrong diagnostic" thyroid nodules

OBJECTIVE

To utilize the discrepancies of different TIRADS, including ACR-TIRADS, Kwak-TIRADS, C-TIRADS, and EU-TIRADS, to explore methods for improving ultrasound diagnostic accuracy.

METHODS

In total, 795 nodules with cytological or surgical pathology were included. All nodules were screened by the four TIRADS according to their diagnostic concordance (Screening procedures, SP). Discriminant strategy (DS) derived from predictor variables was combined with SP to construct the evaluation method (SP+DS). The diagnostic performance of the SP+DS method alone and its derivational methods and two-TIRADS combined tests was evaluated.

RESULTS

A total of 86.8% (269/310) malignant nodules and 93.6% (365/390) benign cases diagnosed by the four TIRADS simultaneously were pathologically confirmed, while 12.0% (95/795) nodules could not be consistently diagnosed by them. The criteria of DS were that iso- or hyper-echogenicity nodules should be considered benign, while hypo- or marked hypo-echogenicity nodules malignant. For 95 inconsistently diagnosed nodules screened by at least two TIRADS, DS performed best with an accuracy of 79.0%, followed by Kwak-TIRADS (72.6%). In the overall sample, the sensitivity and AUC were highest for the SP+DS method compared to the four TIRADS (91.3%, 0.895). Combining ACR-TIRADS and Kwak-TIRADS via parallel test resulted in significant improvements in the sensitivity and AUC compared to ACR-TIRADS (89.2% vs. 81.4%, 0.889 vs. 0.863). Combining C-TIRADS and DS in serial resulted in the highest AUC (0.887), followed by Kwak-TIRADS (0.884), while EU-TIRADS was the lowest (0.879).

CONCLUSIONS

For undetermined or suspected thyroid nodules, two-TIRADS combined tests can be used to improve diagnostic accuracy. Otherwise, considering the inconsistent diagnosis of two TIRADS may require attention to the echo characteristics to differentiate between benign and malignant nodules.

KEY POINTS

• The discrepancies in the diagnostic performance of different TIRADS arise from their performance on inconsistently diagnosed nodules. • ACR-TIRADS improves sensitivity via combining with Kwak-TIRADS in parallel (from 81.4 to 89.2%), while C-TIRADS increases specificity via combining with EU-TIRADS in serial (from 80.9 to 85.7%). • If the diagnostic findings of two TIRADS are inconsistent, echo characteristics will be helpful for the differentiation of benign and malignant nodules with an accuracy of 79.0%.

Diagnostic value of multi-parameter MRI and colour B-ultrasound elastography in benign and malignant thyroid nodules

BACKGROUND

The early diagnosis of thyroid cancer depends on the popularisation and development of diagnostic imaging techniques and the continuous improvement of physician diagnosis.

OBJECTIVE

To investigate the clinical value of multi-parameter magnetic resonance imaging (MRI) and colour B-ultrasound elastography in thyroid nodules.

METHODS

The clinical and imaging data of 252 patients with thyroid nodules who were admitted to our hospital were collected. All patients underwent preoperative colour B-ultrasound elastography and MRI. The postoperative pathological results were the gold standard for diagnosing benign and malignant thyroid nodules. The accuracy, sensitivity and specificity of MRI, colour B-ultrasound elastography and their combination for diagnosing benign and malignant thyroid nodules were compared.

RESULTS

This study included 252 patients with 388 nodules. There were 169 patients with solitary nodules and 83 patients with multiple nodules. The maximum diameter of the thyroid nodules was 0.32-1.00 (0.75 ± 0.20) cm. The accuracy of MRI diagnosis (348/388) was 89.69%, the sensitivity was 92.98%, and the specificity was 65.22%. The diagnostic accuracy, sensitivity and specificity of colour B-ultrasound elastography (332/388) were 85.57%, 88.30% and 65.22%, respectively. The accuracy rate of combined diagnosis (376/388) was 96.91%, the sensitivity was 98.25%, and the specificity was 86.96%, which was significantly higher than MRI and colour B-ultrasound elastography alone. The area under the curve (AUC) of MRI, colour B-ultrasound elastography and combined diagnosis were 0.768, 0.791 and 0.926, respectively. The AUC of the three diagnostic methods was > 0.7, indicating that the three diagnostic methods had good diagnostic value. The AUC for combined diagnosis was significantly higher than that of MRI and colour B-mode ultrasound elastography alone.

CONCLUSION

Combined ultrasound and MRI have high diagnostic accuracy and specificity for benign and malignant thyroid nodules. This diagnostic method can be applied in clinical practice.

Associations between Lake Urmia disaster and the prevalence of thyroid nodules and metabolic syndrome: The AZAR cohort survey

Background: In this study, we investigated the associations Lake Urmia's drought to the prevalence of thyroid nodules (TNs) and metabolic syndrome (MetS) among local inhabitants of the lake. Methods: In this cross-sectional study which was started in 2014, we collected data on 992 adults who participated in the Azar cohort study, in Shabestar county, Iran. The sociodemographic status, smoking, and medical history of the subjects living in the areas adjacent to (n = 163) and far from (n = 829) Lake Urmia were collected through questionnaires. After obtaining written consent, anthropometric factors and blood pressure (BP) were measured. The lipid profile and fasting blood glucose (FBG) of the respondents were measured using colorimetric methods, and all underwent thyroid examination and sonography. Furthermore, the size and characteristics of nodules were determined with a fine-needle aspiration biopsy (FNAB) method. Results: We did not find any significant difference in the prevalence of TNs between the two groups (P=0.44), whereas the prevalence of MetS were significantly higher among the subjects from the regions that were far from the Lake (P=0.04). After adjustment for confounding factors (age and gender) in both groups, low risk of TNs (OR=1.20, 95% CI:0.89-1.62) and high risk of TNs (OR=1.19, 95% CI:0.65-2.19) were not significantly associated to MetS (P>0.05). Conclusion: In this study, Lake Urmia's drought was identified to be with no contribution to the prevalence of TNs and MetS. Therefore, long term perspective studies are suggested to reach precise results.

The combination of BRAFV600E mutation and Chinese Thyroid Imaging Reporting and Data System is helpful in the management of AUS/FLUS thyroid nodules

PURPOSE

To explore the utility of the BRAF^V600E mutation in combination with the Chinese Thyroid Imaging Reporting and Data System (C-TIRADS) in the management of atypia of undetermined significance/follicular lesion of undetermined significance (AUS/FLUS) thyroid nodule (TN).

METHODS

138 AUS/FLUS TNs in 129 patients were included. Each TN underwent preoperative BRAF^V600E mutation analysis and was classified using the C-TIRADS. Histopathologic diagnosis served as reference standard.

RESULTS

46 benign TNs and 92 malignant TNs were identified. The C-TIRADS 4C and 5 (OR = 10.409, P = 0.000), BRAF^V600E mutation (OR = 36.493, P = 0.000) were independent predictors of malignant nodules. There were significant differences in malignancy rate among the different C-TIRADS TNs (P = 0.000), and these TNs with higher C-TIRADS were associated with increased malignancy rate (P for trend = 0.000). The rate of the nodule with BRAF^V600E mutation increased with the increase of C-TIRADS (P for trend = 0.001). For AUS/FLUS TNs without BRAF^V600E mutation, the malignancy rates of the C-TIRADS 3, 4A, 4B, 4C, and 5 were 0%, 21.4%, 20.8%, 70.8%, and 100%, respectively (P = 0.000), and the malignancy rate increased from C-TIRADS 3 to C-TIRADS 5 (P for trend = 0.000). C-TIRADS and BRAF^V600E mutation had similar diagnostic efficacy (P > 0.05), and the sensitivity, negative predictive value, and accuracy of the combination were significantly higher than BRAF^V600E gene or C-TIRADS alone (P < 0.05).

CONCLUSIONS

C-TIRADS can effectively provide risk stratification for AUS/FLUS nodules. The combination is helpful in selecting appropriate management for AUS/FLUS patients.

SFE-AFCE-SFMN 2022 Consensus on the management of thyroid nodules : Thyroid nodules and pregnancy

The SFE-AFCE-SFMN 2022 consensus deals with the management of thyroid nodules, a condition that is a frequent reason for consultation in endocrinology. In more than 90% of cases, patients are euthyroid, with benign non-progressive nodules that do not warrant specific treatment. The clinician's objective is to detect malignant thyroid nodules at risk of recurrence and death, toxic nodules responsible for hyperthyroidism or compressive nodules warranting treatment. The diagnosis and treatment of thyroid nodules requires close collaboration between endocrinologists, nuclear medicine physicians and surgeons, but also involves other specialists. Therefore, this consensus statement was established jointly by 3 societies: the French Society of Endocrinology (SFE), French Association of Endocrine Surgery (AFCE) and French Society of Nuclear Medicine (SFMN); the various working groups included experts from other specialties (pathologists, radiologists, pediatricians, biologists, etc.). The present section deals with the epidemiology and specificities of diagnosis and treatment of thyroid nodules in pregnant women.

SFE-AFCE-SFMN 2022 consensus on the management of thyroid nodules: Synthesis and algorithms

The SFE-AFCE-SFMN 2022 consensus deals with the management of thyroid nodules, a condition that is a frequent reason for consultation in endocrinology. In more than 90% of cases, patients are euthyroid with benign and non-progressive nodules that do not warrant specific treatment. The clinician's objective is to detect malignant thyroid nodules at risk of recurrence and death, toxic nodules responsible for hyperthyroidism or compressive nodules warranting treatment. The diagnosis and treatment of thyroid nodules requires close collaboration between endocrinologists, nuclear medicine physicians and surgeons but also involves other specialists. Therefore, this consensus statement was established jointly by 3 societies, the French Society of Endocrinology (SFE), the French Association of Endocrine Surgery (AFCE) and the French Society of Nuclear Medicine (SFMN); the various working groups included experts from other specialties (pathologists, radiologists, pediatricians, biologists, etc.). This specific text is a summary chapter taking up the recommendations from specific sections and presenting algorithms for the exploration and management of thyroid nodules.

An institutional experience with DICER1 mutated thyroid nodules-evaluating the cytomorphology and molecular phenotype

INTRODUCTION

DICER1 mutated thyroid nodules are commonly seen in pediatric populations often, as part of DICER1 syndrome. We seek to evaluate DICER1 mutated thyroid nodules in adult populations to assess whether there exists distinctive clinical, cytologic, histologic, and molecular characteristics that underline our institutional cohort.

MATERIALS AND METHODS

Retrospective analysis was performed on all fine-needle aspiration (FNA) specimens with a corresponding ThyroSeq panel, to select a cohort of cases with DICER1 mutations. Clinical, radiologic, and cytology materials were reviewed, and histology was reviewed for corresponding resection cases were available. ThyroSeq panel was further scrutinized for additional molecular alterations and variant allele frequency.

RESULTS

DICER1 mutated thyroid nodules (n = 8), more commonly occurred in younger adults (P = 0.01) with larger (P = 0.01) nodules and only in female patients in our cohort. FNA commonly demonstrates cellular specimens with banal cytomorphologic cues including regular nuclei, inconspicuous nucleoli, smooth nuclear membranes, and abundant colloid. On retrospective review by 2 cytopathologists, the lesions were frequently diagnosed as Bethesda II (5 of 8) by both reviewers. Histology, when available, showed that all nodules were categorized as follicular adenomas (5 of 5), often demonstrating macrofollicles with papillary excrescences demonstrating bland nuclei (4 of 5). DICER1 mutational profile revealed a variant allele frequency of &gt;40% in 25% of cases (2 of 8) and &gt;30% in an additional 4 cases, highlighting a possible germline association.

CONCLUSIONS

DICER1 mutated nodules may be under-reported due to banal cytomorphologic features and may be associated with an underlying germline alteration.

Automatic classification of thyroid nodules in ultrasound images using a multi-task attention network guided by clinical knowledge

Thyroid cancer has been the most prevalent cancer in the recent three decades. Ultrasonography is one of the mainly used methods for diagnosing thyroid nodules. Several computer-aided diagnostic methods were proposed to aid radiologists in analyzing ultrasound images of the thyroid gland. Most methods, however, only determine the benignity or malignancy of the thyroid nodule and do not explain the decision-making process of them, which cannot gain the trustworthiness of clinicians because they are not consistent with the physician's diagnostic process. In our work, we design a multi-task branching attention network in which each of the descriptors of the ACR TI-RADS lexicon is first classified. All respective scores are calculated to get the risk stratification of the nodule. Ultimately, based on the risk stratification, the benignity or malignancy of the nodule is determined. This work provides an automated method that incorporates the ACR TI-RADS characterization of thyroid nodules for detecting the level of risk and the benignity or malignancy of thyroid nodules. Thus the work establishes the trustworthiness of clinicians in deep learning models and improves physician efficiency and diagnostic rates to some extent compared to previous studies. For the diagnosis of thyroid nodules, evaluation indices including accuracy, sensitivity, and specificity were 93.55%, 93.86%, and 93.14%, respectively. The experiments show that our approach obtains comparable performance to most advanced methods in diagnosing ultrasound images of the thyroid nodules and is supported by explanations in clinical terms using the ACR TI-RADS lexicon.

Comparison of diagnostic accuracy and utility of artificial intelligence-optimized ACR TI-RADS and original ACR TI-RADS: a multi-center validation study based on 2061 thyroid nodules

OBJECTIVE

To determine if artificial intelligence-based modification of the Thyroid Imaging Reporting Data System (TI-RADS) would be better than the current American College of Radiology (ACR) TI-RADS for risk stratification of thyroid nodules.

METHODS

A total of 2061 thyroid nodules (in 1859 patients) sampled with fine-needle aspiration or operation were retrospectively analyzed between January 2017 and July 2020. Two radiologists blinded to the pathologic diagnosis evaluated nodule features in five ultrasound categories and assigned TI-RADS scores by both ACR TI-RADS and AI TI-RADS. Inter-rater agreement was assessed by asking another two radiologists to score a set of 100 nodules independently. The reference standard was postoperative pathological or cytopathological diagnosis according to the Bethesda system. Inter-rater agreement was determined using intraclass correlation coefficient (ICC).

RESULTS

AI TI-RADS assigned lower TI-RADS risk levels than ACR TI-RADS (p < 0.001) and had larger area under receiver operating characteristic curve (0.762 vs. 0.679, p < 0.001). The sensitivities of ACR TI-RADS and AI TI-RADS were similar (86.7% vs. 82.2%, p = 0.052), but specificity was higher with AI TI-RADS (70.2% vs. 49.2%, p < 0.001). AI TI-RADS downgraded 743 (48.63%) benign nodules, indicating that 328 (42.3% of 776 biopsied nodules) unnecessary fine-needle aspirations (FNA) could have been avoided. Inter-rater agreement was better with AI TI-RADS than with ACR TI-RADS (ICC, 0.808 vs. 0.861, p < 0.001).

CONCLUSION

AI TI-RADS can achieve meaningful reduction in the number of benign thyroid nodules recommended for biopsy and significantly improve specificity despite a slight decrease in sensitivity.

KEY POINTS

• AI TI-RADS assigned lower TI-RADS risk levels than ACR TI-RADS, showing similar sensitivity but higher specificity. • Half of the benign nodules can be downgraded of which 42.3% of biopsy nodules avoided unnecessary fine-needle aspiration (FNA). • AI TI-RADS had a better overall inter-rater agreement.

Multi-objective data enhancement for deep learning-based ultrasound analysis

Recently, Deep Learning based automatic generation of treatment recommendation has been attracting much attention. However, medical datasets are usually small, which may lead to over-fitting and inferior performances of deep learning models. In this paper, we propose multi-objective data enhancement method to indirectly scale up the medical data to avoid over-fitting and generate high quantity treatment recommendations. Specifically, we define a main and several auxiliary tasks on the same dataset and train a specific model for each of these tasks to learn different aspects of knowledge in limited data scale. Meanwhile, a Soft Parameter Sharing method is exploited to share learned knowledge among models. By sharing the knowledge learned by auxiliary tasks to the main task, the proposed method can take different semantic distributions into account during the training process of the main task. We collected an ultrasound dataset of thyroid nodules that contains Findings, Impressions and Treatment Recommendations labeled by professional doctors. We conducted various experiments on the dataset to validate the proposed method and justified its better performance than existing methods.

Copy number variations: A novel molecular marker for papillary thyroid cancer

Background

We aimed to screen tumor-associated functional genes on a large scale through copy number variation (CNV) analysis of papillary thyroid cancer (PTC).

Methods

We analyzed 74 tissue samples from 41 patients with thyroid nodules. The samples were subjected to whole-genome resequencing and then analyzed by the ‘WISECONDOR’ method. Potential chromosome CNV regions were identified between the different sample groups.

Results

Of the 74 samples from 41 patients, 28 were PTC tissue samples, 29 were para-carcinoma tissue samples, 13 were benign tumor tissue samples and 4 were para-benign tumor tissue samples. According to our findings, PTC can be identified by CNVs at the corresponding positions on chromosomes 5, 7, 8, 10, and 17. For carcinoma tissue, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy and area under the curve (AUC) of the test method were 100%, 66.7%, 87.5%, 100.0%, 90.0% and 0.83 (95% confidence interval [CI], 0.67–1.00) and for para-carcinoma tissue, these values were 96.6%, 75.0%, 96.6%, 75.0%, 93.9% and 0.86 (95% CI, 0.60–1.00).

Conclusion

CNV analysis assays involving high-volume sequencing analysis can increase the identification of PTC, potentially avoiding errors caused by position deflection in sampling.

1.

Thyroid nodules can be identified by CNVs at the corresponding positions on chromosomes 5, 7, 8, 10, and 17.

2.

The identification rate of PTC can be greatly increased through high-volume CNV sequencing analysis.

Core Needle Biopsy in Suspicious Malignant Thyroid Nodules with Repeated Nondiagnostic Fine Needle Aspiration

Key message

The clinician could have CNB in mind for thyroid nodules when FNA results were nondiagnostic. Our study would suggest CNB a safe and efficient method for investigating thyroid nodules.

Abstract

Usefulness of preoperative tissue sampling and pathology diagnoses in thyroid tumors were accepted worldwide. We investigate the role of Core needle biopsy (CNB) in the thyroid nodules lesions when FNA results are nondiagnostic. We conducted a cross-sectional study to evaluate twenty-six CNBs results of suspicious malignant thyroid nodules with nondiagnostic repeated fine needle aspiration. 25 from 26 CNBs were diagnostic. Twenty-one needle biopsy reports were papillary thyroid carcinoma, three CNB samples diagnosed medullary thyroid carcinoma and one of them had anaplastic results. All diagnostic needle biopsies results were compatible with final pathology. Our study would suggest CNB a safe and efficient method for investigating thyroid nodules while repeated FNA yielded nondiagnostic results.

Diagnostic Value of Different 3-D Shear Wave Elastography Sections in the Diagnosis of Thyroid Nodules

The aim of the study was to explore the value of 3-D shear wave elastography (SWE) in differentiating malignant from benign thyroid nodules. A total of 188 patients with 216 nodules who underwent conventional ultrasound, 2-D SWE and 3-D SWE were included in this study. All patients underwent surgical excision, and the pathological results were the gold standard. Receiver operating characteristic (ROC) curves of the American College of Radiology's Thyroid Imaging Reporting and Data System (ACR TI-RADS), 2-D SWE and 3-D SWE were plotted, and the areas under the curves (AUCs) were compared using a Z-test. There were 62 benign thyroid nodules and 154 malignant thyroid nodules in this study. Young's modulus (E_min, E_mean, E_max, E_sd) values of thyroid malignant nodules in different sections of 2-D SWE and 3-D SWE were significantly higher than those of thyroid benign nodules (p < 0.001). The AUC of E_max in 2-D SWE transverse sections was significantly lower than that in 3-D SWE transverse sections and 3-D SWE sagittal sections (0.768 vs. 0.831 and 0.844, p < 0.05). The AUC of 3-D S-E_max combined with ACR TI-RADS was 0.859; the specificity increased from 54.84% to 85.71%, and the diagnostic accuracy increased from 74.54% to 85.19%, compared with ACR TI-RADS. The difference was statistically significant (p < 0.05). Three-dimensional SWE combined with ACR TI-RADS for the diagnosis of thyroid nodules significantly improved the diagnostic ability of ACR TI-RADS, and was significantly better than 2-D SWE combined with ACR TI-RADS.

Diagnostic performance of simplified TI-RADS for malignant thyroid nodules: comparison with 2017 ACR-TI-RADS and 2020 C-TI-RADS

Background

The aim of this study is to propose a new TI-RADS and compare it with the American College of Radiology (2017 ACR)-TI-RADS and the 2020 Chinese (2020 C)-TI-RADS.

Methods

A retrospective analysis of 749 thyroid nodules was performed. Based on the calculated odds ratio of ultrasonic signs between benign and malignant nodules, a new thyroid nodule score and malignancy rate were calculated. A receiver operating characteristic curve was drawn to analyze the new system’s effectiveness in the differential diagnosis of benign and malignant thyroid nodules and was compared with the 2020 C-TI-RADS and 2017 ACR-TI-RADS. Five ultrasound physicians with different qualifications graded another 123 thyroid nodules according to the 2017ACR-TI-RADS, 2020 C-TI-RADS, and the newly proposed TI-RADS. Intergroup and intragroup consistency was evaluated using the Kappa test and intraclass correlation coefficient (ICC) test.

Results

1) The new thyroid nodule score was divided into 0, 1, 2, 3, 4, and 5 points, with malignancy rates of 1.52%, 7.69%, 38.24%, 76.00%, 90.75%, and 93.75%, respectively. Using 3 points as the cutoff value to diagnose benign and malignant thyroid nodules, the sensitivity and specificity were 94.03% and 67.39%, respectively, which were higher than those of the 2017 ACR-TI-RADS and 2020 C-TI-RADS. The simplified TI-RADS, namely, sTI-RADS, was established as follows: sTI-RADS 3 (0 points), malignancy rate < 2%; sTI-RADS 4a (1 point), malignancy rate 2–10%; sTI-RADS 4b (2 points), malignancy rate 10–50%; sTI-RADS 4 (3 points), malignancy rate 50–90%; and sTI-RADS 5 (4 and 5 points), malignancy rate > 90%. 2) Five ultrasound doctors graded thyroid nodules by the 2017 ACR-TI-RADS, 2020C-TI-RADS and sTI-RADS. Intragroup consistency was good among all tests; ICC were 0.86 (0.82–0.90), 0.84 (0.78–0.88), and 0.88 (0.84–0.91), respectively, while only sTI-RADS had good intergroup consistency.

Conclusion

In summary, we proposed a new TI-RADS, namely, sTI-RADS, which was obtained using a simple assignment method with higher specificity, accuracy, positive predictive value, and Youden index than the 2017 ACR-TI-RADS and 2020 C-TI-RADS.

The association of uric acid with the development of thyroid nodules: a retrospective cohort study

BACKGROUND

Uric acid was found to have a positive correlation with thyroid nodules in the cross-sectional studies recently. We aimed to conduct a retrospective cohort study to investigate whether uric acid is a risk factor for the development of thyroid nodules.

METHODS

We reviewed the data of individuals who attended the medical check-ups in our hospital from 2010 to 2019. A total of 6587 adults without thyroid nodules at baseline were enrolled in this study. Logistic regression with or without restricted cubic spline function was used to investigate the non-linear or linear association between uric acid and thyroid nodules, respectively.

RESULTS

Baseline characteristics showed that subjects mainly consisted of the healthy, young population. After fully adjusting for the potential confounders, such as age, sex, metabolic and inflammatory indicators, hepatic and renal function, a logistic restricted cubic spline regression model suggested that uric acid had a significant association (P = 0.028) with the development of thyroid nodules, but the association was not non-linear (P = 0.516). The results indicate that the association between them is linear, which was demonstrated by a logistic regression model, in which the odds ratio of uric acid per 100 mmol/L was 1.137 (P = 0.004). Age, sex, diastolic blood pressure, fasting blood sugar, and blood monocyte were found to be risk factors for thyroid nodules as well.

CONCLUSION

Uric acid is an independent risk factor for the formation of thyroid nodules. This finding warrants attention to this risk factor in apparently healthy adults.

Added value of mass characteristic frequency to 2-D shear wave elastography for differentiation of benign and malignant thyroid nodules

Mass characteristic frequency (f_mass) is a novel shear wave (SW) parameter that represents the ratio of the averaged minimum SW speed within the regions of interest to the largest dimension of the mass. Our study objective was to evaluate if the addition of f_mass to conventional 2-D shear wave elastography (SWE) parameters would improve the differentiation of benign from malignant thyroid nodules. Our cohort comprised 107 patients with 113 thyroid nodules, of which 67 (59%) were malignant. Two-dimensional SWE data were obtained using the Supersonic Imagine Aixplorer ultrasound system equipped with a 44- to 15-MHz15-MHz linear array transducer. A receiver operating characteristic curve was generated based on a multivariable logistic regression analysis to evaluate the ability of SWE parameters with/without f_mass and with/without clinical factors to discriminate benign from malignant thyroid nodules. The addition of f_mass to conventional SW elasticity parameters increased the area under the curve from 0.808 to 0.871 (p = 0.02). The combination of SW elasticity parameters plus f_mass plus clinical factors provided the strongest thyroid nodule malignancy probability estimate, with a sensitivity of 93.4% and specificity of 91.1% at the optimal threshold. In summary, f_mass can be a valuable addition to conventional 2-D SWE parameters.

Diagnostic accuracy of palpation versus ultrasound-guided fine needle aspiration biopsy for diagnosis of malignancy in thyroid nodules: a systematic review and meta-analysis

Thyroid nodule is a common health problem in endocrinology. Thyroid fine-needle aspiration biopsy (FNAB) cytology performed by palpation guided FNAB (PGFNAB) and ultrasound-guided FNAB (USGFNAB) are the preferred examinations for the diagnosis of thyroid cancer and part of the integration of the current thyroid nodule assessment. Although studies have shown USGFNAB to be more accurate than PGFNAB, inconsistencies from several studies and clinical guidelines still exist.The purpose of this study is to compare the diagnostic accuracy of Palpation versus Ultrasound-Guided Fine Needle Aspiration Biopsy in diagnosing malignancy of thyroid nodules.The systematic review and meta-analysis were prepared based on the PRISMA standards. Literature searches were carried out on three online databases (Pubmed/MEDLINE, Embase, and Proquest) and grey literatures. Data extraction was carried out manually from various studies that met the eligibility, followed by analysis to obtain pooled data on sensitivity, specificity, Diagnostic Odds Ratio (DOR) and Area Under Curve (AUC), and the comparison of the two methods.Total of 2517 articles were obtained, with 11 studies were included in this systematic review. The total sample was 2382, including 1128 subjects using PGFNAB and 1254 subjects using USGFNAB. The risk of bias was assessed using QUADAS-2 with mild-moderate results. The results of sensitivity, specificity, AUC and DOR in diagnosing thyroid nodules using PGFNAB were 76% (95% CI, 49-89%), 77% (95% CI, 56-95%), 0.827 and 11.6 (95% CI, 6-21) respectively. The results of sensitivity, specificity, AUC and DOR in diagnosing thyroid nodules using USGFNAB were 90% (95% CI, 81-95%), 80% (95% CI, 66-89%), 0.92 and 40 (95% CI, 23-69), respectively the results of the comparison test between PGFNAB and USGFNAB; Tsens USGFNAB of 0.99 (p = 0.023), AUC difference test of 0.093 (p = 0.000023).The diagnostic accuracy of USGFNAB is higher than PGFNAB in diagnosing malignancy of thyroid nodules. If it is accessible, the author recommends using USGFNAB as a diagnostic tool for thyroid nodules.

Association of Ozone Exposures with the risk of thyroid nodules in Hunan Province: a population-based cohort study

BACKGROUND

Increasing evidence associates air pollution with thyroid dysfunction, whereas the potential relationship between exposure to ozone (O₃) and Thyroid Nodules (TNs) is unclear.

METHODS

This retrospective cohort study investigated the association between O₃ exposure and TNs in Hunan province, enrolling 191,357 Chinese adults who lived in Hunan province from January 2009 to December 2019 and received voluntary medical examinations. Individual exposure levels to O₃ from 2010 to 2019 were measured on account of participants' residential addresses at the district level. Associations of O₃ exposure with the risk of incidental TNs were assessed by restricted cubic splines and surveyed as odds ratios after adjusting for demographic factors.

RESULTS

In total, 81,900 adults were newly diagnosed with TNs during the study period. Age-standardized TNs detection rate in Hunan province increased from 25.9 to 46.3% between 2010 and 2019, with the greatest annual percent change being 8.1 [95% CI, 7.3-8.8]. A similar trend has been found in all tumor sizes, ages, and both sexes. O₃ exposure presented a statistically significant dose-dependent positive correlation (greater than 0.036 ppm) with TNs. Similarly, long-term exposure to high levels of O₃ (1-year average O₃ concentrations exceeding 0.0417 ppm) was found positively associated with increased TSH levels.

CONCLUSIONS

High-level O₃ exposure in the long term was associated with an increase in TSH. Consequently, increased TSH was related to the increased risk of TNs. Being exposed to high-level O₃ in the long term was related to the increased detection rates of TNs in Hunan province, which could be mediated by TSH.

The application value of CDFI and SMI combined with serological markers in distinguishing benign and malignant thyroid nodules

PURPOSE

The purpose of this study is to explore the application value of CDFI and SMI combined with serological markers in distinguishing benign and malignant thyroid nodules.

METHOD

A total of 192 patients with thyroid nodules admitted to our hospital from July 2019 to December 2020 were selected as subjects. Color Doppler blood flow imaging (CDFI) and supermicro blood flow imaging (SMI) methods are used to detect the blood flow of patients and the levels of serum thyroglobulin antibody (TgAb), thyroid peroxidase antibody (TPOAb), and thyroid stimulating hormone (TSH). The receiver operating characteristic curve (ROC curve) was used to observe the sensitivity and specificity of serological markers for distinguishing benign and malignant thyroid nodules, and combined with CDFI and SMI to observe the sensitivity and specificity for distinguishing benign and malignant thyroid nodules.

RESULTS

The levels of TgAb, TPOAb and TSH in benign thyroid nodules were lower than those of the malignant group, and the difference was statistically significant (P < 0.01). There was no statistically significant difference between benign and malignant thyroid nodules in the presence or absence of the capsule and the presence or absence of vocal halo (P > 0.05), while the differences in the nodule morphology, boundary, internal echo and internal calcification were statistically significant (P < 0.01).

CONCLUSION

CDFI and SMI combined with serological index detection have higher value in the differential diagnosis of thyroid cancer, which can significantly improve the sensitivity and specificity of differential diagnosis.

SuperSonic shear imaging for the differentiation between benign and malignant thyroid nodules: a meta-analysis

PURPOSE

To assess the diagnostic value of SuperSonic shear imaging (SSI) for the differentiation between benign and malignant thyroid nodules through meta-analysis.

METHODS

Online database searches were performed on PubMed, EMBASE, the Cochrane Library, and the Web of Science until 31 July 2021. The Quality Assessment of Diagnostic Accuracy Studies-2 tool was used to assess the quality of the included studies. Three measures of diagnostic test performance were used to examine the value of SSI, including the summary area under the receiver operating characteristic curve (AUROC), the summary diagnostic odds ratio (DOR), and the summary sensitivity and specificity. Heterogeneity was explored using meta-regression and subgroup analyses.

RESULTS

Finally, 21 studies with 3376 patients were included in this study. There were a total of 4296 thyroid nodules, in which 1806 malignant nodules and 2490 benign ones were involved. Thyroid nodules exhibited a malignancy rate of 42.0% (range 5.6-79.8%), 95.1% of which were of papillary variant. SSI showed a summary sensitivity of 74% [95% confidence interval (CI) 67-79%], specificity of 82% (95% CI 77-87%) and AUROC of 0.85 (95% CI 0.82-0.88) for the differentiation between benign and malignant thyroid nodules. The summary positive likelihood ratio (LR), negative LR, and DOR were 4.2 (95% CI 3.3-5.3), 0.32 (95% CI 0.26-0.40), and 13 (95% CI 9-18), respectively.

CONCLUSIONS

SSI showed high accuracy in the diagnostic differentiation between benign and malignant thyroid nodules and can be served as a noninvasive and important adjunct for thyroid nodule evaluation.

Clinicoradiological Characteristics in the Differential Diagnosis of Follicular-Patterned Lesions of the Thyroid: A Multicenter Cohort Study

OBJECTIVE

Preoperative differential diagnosis of follicular-patterned lesions is challenging. This multicenter cohort study investigated the clinicoradiological characteristics relevant to the differential diagnosis of such lesions.

MATERIALS AND METHODS

From June to September 2015, 4787 thyroid nodules (≥ 1.0 cm) with a final diagnosis of benign follicular nodule (BN, n = 4461), follicular adenoma (FA, n = 136), follicular carcinoma (FC, n = 62), or follicular variant of papillary thyroid carcinoma (FVPTC, n = 128) collected from 26 institutions were analyzed. The clinicoradiological characteristics of the lesions were compared among the different histological types using multivariable logistic regression analyses. The relative importance of the characteristics that distinguished histological types was determined using a random forest algorithm.

RESULTS

Compared to BN (as the control group), the distinguishing features of follicular-patterned neoplasms (FA, FC, and FVPTC) were patient's age (odds ratio [OR], 0.969 per 1-year increase), lesion diameter (OR, 1.054 per 1-mm increase), presence of solid composition (OR, 2.255), presence of hypoechogenicity (OR, 2.181), and presence of halo (OR, 1.761) (all p < 0.05). Compared to FA (as the control), FC differed with respect to lesion diameter (OR, 1.040 per 1-mm increase) and rim calcifications (OR, 17.054), while FVPTC differed with respect to patient age (OR, 0.966 per 1-year increase), lesion diameter (OR, 0.975 per 1-mm increase), macrocalcifications (OR, 3.647), and non-smooth margins (OR, 2.538) (all p < 0.05). The five important features for the differential diagnosis of follicular-patterned neoplasms (FA, FC, and FVPTC) from BN are maximal lesion diameter, composition, echogenicity, orientation, and patient's age. The most important features distinguishing FC and FVPTC from FA are rim calcifications and macrocalcifications, respectively.

CONCLUSION

Although follicular-patterned lesions have overlapping clinical and radiological features, the distinguishing features identified in our large clinical cohort may provide valuable information for preoperative distinction between them and decision-making regarding their management.