Impact of ultrasound elastography in evaluating Bethesda category IV thyroid nodules with histopathological correlation.

Introduction: Fine needle aspiration (FNA) is the gold standard method recommended in the diagnosis of thyroid nodules. Bethesda IV cytology results are identified in 7-9% of nodules investigated through FNA, with reported malignancy rate in a wide range of 10-40%. The recommended treatment is either surgical or risk additional molecular testing before surgery. However, a large number of nodules belonging to this category (60-80%) are observed to be benign after surgical excision, which can put the patient at risk of unnecessary surgical morbidity. This study aimed to assess the diagnostic performance of conventional ultrasound, the ACR TI-RADS score and elastography in cases of Bethesda IV cytology on FNA. Methods: We evaluated ninety-seven consecutive cases with Bethesda category IV results on FNA by using conventional B-mode ultrasound, qualitative strain or shear-wave elastography (Hitachi Preirus Machine, Hitachi Inc., Japan and Aixplorer Mach 30 Supersonic Imagine, Aix-en-Provence, France) and all nodules were classified according to the ACR TI-RADS system. Conventional ultrasound was used to categorize the nodules as potentially malignant based on the following features: hypoechogenicity, inhomogeneity, a taller than wide shape, irregular margins, presence of microcalcifications, an interrupted thyroid capsule and suspicious cervical lymph nodes. Elastography classified nodules with increased stiffness as suspicious for malignancy. Results: We considered pathology results as the gold standard diagnosis, finding that 32 out of 97 nodules were carcinomas (33%) and 65 out of 97 were benign nodules (67%). The benign group included twenty cases of non-invasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP). Finally, we compared ultrasound data with pathology results, which showed that nineteen out of the 32 malignant nodules presented with increased stiffness on elastography (p=0.0002). On conventional ultrasound, we found that microcalcifications (p=0.007), hypoechogenicity and irregular margins (p=0.006) are features which can distinguish between benign and malignant nodules with statistical significance. Discussion: Integrating elastography as a parameter of the ACR TI-RADS score in the evaluation of Bethesda category IV nodules showed a sensitivity of 90.62% in detecting thyroid cancer cases (p=0.006). We can conclude that elastographic stiffness as an addition to high risk features observed on conventional ultrasound improves the detection of malignant nodules in cases with Bethesda IV cytology.

Thyroid ultrasound pattern in primary hypothyroidism is similar to Graves' disease: a report of three cases.

Ultrasound can identify important characteristics in primary hypothyroidism and diffuse hyperthyroidism (Graves' disease). Therefore, sonologists are actively investigating ultrasound criteria to differentiate between these two conditions. Nevertheless, practice shows the absence of such ultrasonic landmarks. For the first time in the literature, three cases of primary hypothyroidism have demonstrated an ultrasound pattern identical to that of Graves' disease. This pattern includes the presence of goiter, marked total hypoechogenicity of the parenchyma, significantly or moderately increased blood flow intensity ('thyroid inferno'), and elevated peak systolic velocity of the superior thyroid arteries. These signs are less common in hypothyroidism compared to hyperthyroidism. Diagnostic data suggest that the pathogeneses of primary hypothyroidism and Graves' disease share the same mechanisms, leading to similar thyroid ultrasound patterns. One of these shared mechanisms is presumably thyroid overstimulation by the autonomic nervous system, which is adequate to the body's hormonal requirements in hypothyroidism but excessive in hyperthyroidism.

Minor hyperthyroidism with normal levels of thyroid-stimulating hormone receptor antibodies: a case report.

The present report describes for the first time a case of diffuse hyperthyroidism in a 30-year-old female patient who had normal levels of thyroid-stimulating hormone receptor antibodies (TSHR-Ab), slightly elevated plasma levels of thyroid hormones, and slightly increased thyroid blood flow. Seven years before, after severe stress, she had Graves' disease with elevated plasma levels of TSHR-Ab. The patient's recent medical history included mental stress and autonomic dysfunction. This report describes a mild form of hyperthyroidism in terms of elevated plasma levels of thyroid hormones and Doppler ultrasonography data; this condition was first defined as 'minor hyperthyroidism'. The examination data suggest a probable secondary role of the immune system and primary role of the autonomic nervous system in the pathogenesis of Graves' disease.

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

BACKGROUND: Patients 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. METHODS: Retrospective 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. RESULTS: A 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. CONCLUSIONS: Based 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.

Three-dimensional visualization of thyroid ultrasound images based on multi-scale features fusion and hierarchical attention.

BACKGROUND: Ultrasound three-dimensional visualization, a cutting-edge technology in medical imaging, enhances diagnostic accuracy by providing a more comprehensive and readable portrayal of anatomical structures compared to traditional two-dimensional ultrasound. Crucial to this visualization is the segmentation of multiple targets. However, challenges like noise interference, inaccurate boundaries, and difficulties in segmenting small structures exist in the multi-target segmentation of ultrasound images. This study, using neck ultrasound images, concentrates on researching multi-target segmentation methods for the thyroid and surrounding tissues. METHOD: We improved the Unet++ to propose PA-Unet++ to enhance the multi-target segmentation accuracy of the thyroid and its surrounding tissues by addressing ultrasound noise interference. This involves integrating multi-scale feature information using a pyramid pooling module to facilitate segmentation of structures of various sizes. Additionally, an attention gate mechanism is applied to each decoding layer to progressively highlight target tissues and suppress the impact of background pixels. RESULTS: Video data obtained from 2D ultrasound thyroid serial scans served as the dataset for this paper.4600 images containing 23,000 annotated regions were divided into training and test sets at a ratio of 9:1, the results showed that: compared with the results of U-net++, the Dice of our model increased from 78.78% to 81.88% (+ 3.10%), the mIOU increased from 73.44% to 80.35% (+ 6.91%), and the PA index increased from 92.95% to 94.79% (+ 1.84%). CONCLUSIONS: Accurate segmentation is fundamental for various clinical applications, including disease diagnosis, treatment planning, and monitoring. This study will have a positive impact on the improvement of 3D visualization capabilities and clinical decision-making and research in the context of ultrasound image.

Determining the Best Thyroid Imaging Reporting and Data System: A Prospective Study Comparing the Diagnostic Performance of ACR, EU, and K TIRADS in the Evaluation of Thyroid Nodules.

Background Many different risk stratification systems have been formulated for thyroid nodules, differing in their fine-needle aspiration cytology (FNAC) indication, suggesting a lack of consensus around the world. Purpose This prospective study was conducted to find the best guideline for risk stratification, for a better malignancy yield, and with reduced rates of negative FNACs among three Thyroid Imaging, Reporting, and Data System (TIRADS) guidelines. Materials and Methods A total of 625 thyroid nodules with conclusive FNAC or histopathological diagnosis were included in the study. Various sonographic parameters were recorded. They were classified into categories as per the three guidelines and compared with FNAC diagnosis. The guidelines were evaluated in terms of sensitivity, specificity, predictive values, and diagnostic accuracy. Sensitivity and specificity were compared by McNemar's test. Results American College of Radiology (ACR) TIRADS had the highest diagnostic accuracy (56.8%), specificity (50.75%), positive predictive value (23.92%), lowest rates of negative FNACs (76.08%), and high negative predictive value (97.84 %). Korean (K) TIRADS had the maximum sensitivity (97.75%), highest negative predictive value (98.44%), and gross malignancy yield. European TIRADS was between the two other guidelines in most parameters with specificity like K TIRADS. Conclusion All the three guidelines are very good screening tools, with comparable high sensitivity. ACR TIRADS is better in terms of specificity and reduced rates of negative FNACs. Including the presence of a suspicious cervical lymph node as a criterion and more frequent follow-up might further improve the diagnostic performance of the guideline.

Principles and features of ultrasound hypoechogenicity in diffuse thyroid pathology.

For different thyroid diseases and hormonal metabolism, ultrasound (US) of the thyroid gland reveals hypoechogenicity. Despite the direct correlation of hypoechogenicity with the levels of thyroid-stimulating hormone and antibodies of thyroid peroxidase and thyroglobulin, ~20% of this correlation is inconsistent, thus restricting the comprehensive utilisation of this valuable diagnostic sign. Thus, it is necessary to investigate the additional circumstances affecting the extent and features of the US hypoechogenicity of the thyroid gland. The technique for assessing thyroid hypoechogenicity was based on the basic setting of the US mode and visual assessment in percentage of gray relative to a gradient gray scale. Doppler mode was used. US data were compared with the results of hormonal and immune blood tests. The study contains the morphofunctional basis of the various US hypoechogenicities detected in the diffuse pathology of the thyroid gland has been presented, and the principles and probable mechanisms of widespread and segmental hypoechogenicity formation are disclosed for the first time. Furthermore, a mandatory Doppler involving thyroid parenchyma blood flow intensity and peak systolic blood velocity of thyroid arteries, which indicates the magnitude of neurovegetative influence, has been suggested. The results of the study shows revealed that the evaluation of the importance and features of US hypoechogenicity in various diffuse thyroid pathologies is probably based on a single system involving neurohumoral regulation, segmental arrangement and compensatory reserve state of the gland parenchyma.

Using Bedside Spectral Doppler Ultrasound for the Assessment of Patients With Thyrotoxicosis.

OBJECTIVE: To assess the bedside utility of Spectral Doppler Ultrasound (SDUS) in the initial evaluation of patients presenting with thyrotoxicosis. METHODS: This is a retrospective cross-sectional study of patients diagnosed with thyrotoxicosis at an academic outpatient endocrinology clinic from August 2019 to November 2022. The thyroid arteries' peak systolic velocities (PSV) were measured bilaterally using SDUS. PSV ≥40 cm/s in at least a single thyroid artery was considered a reasonable cut-off for Graves' disease and PSV of perinodular artery ≥ 25 cm/s for toxic adenoma. RESULTS: We identified 73 patients. Mean age ± standard deviation 45.2 ± 16.4 years, 54 (74.0%) were female, 49 (67.1%) were Caucasian, 23 (31.5%) were African American, and 1 (1.4%) was Asian. The confirmed diagnoses were 48 (65.8%) Graves' disease, 13 (17.8%) thyroiditis, four (5.5%) toxic adenoma, four (5.5%) amiodarone-induced thyroiditis type 2, 1 (1.4%) toxic multinodular goiter, 1 (1.4%) had an unremarkable repeat thyroid function testing, and two (2.7%) were unconfirmed. Diagnosis based on the SDUS initial assessment was accurate in 65 (89.0%) of the patients, and it was conclusive and confirmatory during the initial encounter in 55 (75.3%) of the patients before additional testing. A thyroid scan was obtained in nine (12.3%) patients. Incorrectly diagnosed patients were observed in two patients of each of the following categories: Graves' disease, thyroiditis, toxic adenoma, and unconfirmed diagnoses. CONCLUSIONS: SDUS can be a valuable, efficient, and cost-effective bedside tool in the initial assessment of patients presenting with thyrotoxicosis.

Thyroid ultrasound diagnosis improvement via multi-view self-supervised learning and two-stage pre-training.

Thyroid nodule classification and segmentation in ultrasound images are crucial for computer-aided diagnosis; however, they face limitations owing to insufficient labeled data. In this study, we proposed a multi-view contrastive self-supervised method to improve thyroid nodule classification and segmentation performance with limited manual labels. Our method aligns the transverse and longitudinal views of the same nodule, thereby enabling the model to focus more on the nodule area. We designed an adaptive loss function that eliminates the limitations of the paired data. Additionally, we adopted a two-stage pre-training to exploit the pre-training on ImageNet and thyroid ultrasound images. Extensive experiments were conducted on a large-scale dataset collected from multiple centers. The results showed that the proposed method significantly improves nodule classification and segmentation performance with limited manual labels and outperforms state-of-the-art self-supervised methods. The two-stage pre-training also significantly exceeded ImageNet pre-training.

Interobserver variability in thyroid ultrasound.

PURPOSE: Ultrasound evaluation of thyroid nodules is the preferred technique, but it is dependent on operator interpretation, leading to inter-observer variability. The current study aimed to determine the inter-physician consensus on nodular characteristics, risk categorization in the classification systems, and the need for fine needle aspiration puncture. METHODS: Four endocrinologists from the same center blindly evaluated 100 ultrasound images of thyroid nodules from 100 different patients. The following ultrasound features were evaluated: composition, echogenicity, margins, calcifications, and microcalcifications. Nodules were also classified according to ATA, EU-TIRADS, K-TIRADS, and ACR-TIRADS classifications. Krippendorff's alpha test was used to assess interobserver agreement. RESULTS: The interobserver agreement for ultrasound features was: Krippendorff's coefficient 0.80 (0.71-0.89) for composition, 0.59 (0.47-0.72) for echogenicity, 0.73 (0.57-0.88) for margins, 0.55 (0.40-0.69) for calcifications, and 0.50 (0.34-0.67) for microcalcifications. The concordance for the classification systems was 0.7 (0.61-0.80) for ATA, 0.63 (0.54-0.73) for EU-TIRADS, 0.64 (0.55-0.73) for K-TIRADS, and 0.68 (0.60-0.77) for K-TIRADS. The concordance in the indication of fine needle aspiration puncture (FNA) was 0.86 (0.71-1), 0.80 (0.71-0.88), 0.77 0.67-0.87), and 0.73 (0.64-0.83) for systems previously described respectively. CONCLUSIONS: Interobserver agreement was acceptable for the identification of nodules requiring cytologic study using various classification systems. However, limited concordance was observed in risk stratification and many ultrasonographic characteristics of the nodules.

Thyroid Ultrasound Image Database and Marker Mask Inpainting Method for Research and Development.

OBJECTIVE: The main objective of this study was to build a rich and high-quality thyroid ultrasound image database (TUD) for computer-aided diagnosis (CAD) systems to support accurate diagnosis and prognostic modeling of thyroid disorders. Because most of the raw thyroid ultrasound images contain artificial markers, which seriously affect the robustness of CAD systems because of their strong prior location information, we propose a marker mask inpainting (MMI) method to erase artificial markers and improve image quality. METHODS: First, a set of thyroid ultrasound images were collected from the General Hospital of the Northern Theater Command. Then, two modules were designed in MMI, namely, the marker detection (MD) module and marker erasure (ME) module. The MD module detects all markers in the image and stores them in a binary mask. According to the binary mask, the ME module erases the markers and generates an unmarked image. Finally, a new TUD based on the marked images and unmarked images was built. The TUD is carefully annotated and statistically analyzed by professional physicians to ensure accuracy and consistency. Moreover, several normal thyroid gland images and some ancillary information on benign and malignant nodules are provided. RESULTS: Several typical segmentation models were evaluated on the TUD. The experimental results revealed that our TUD can facilitate the development of more accurate CAD systems for the analysis of thyroid nodule-related lesions in ultrasound images. The effectiveness of our MMI method was determined in quantitative experiments. CONCLUSION: The rich and high-quality resource TUD promotes the development of more effective diagnostic and treatment methods for thyroid diseases. Furthermore, MMI for erasing artificial markers and generating unmarked images is proposed to improve the quality of thyroid ultrasound images. Our TUD database is available at https://github.com/NEU-LX/TUD-Datebase.

Quality Improvement Methodology to Improve Standardized Reporting of Pediatric Thyroid Ultrasounds Using TI-RADS.

BACKGROUND/PURPOSE: The process of evaluating pediatric thyroid nodules at our institution was inconsistent with a high rate of negative biopsies raising concern of appropriate patient selection for biopsy. Our aim was to institute a standardized risk stratification reporting system for thyroid nodules to increase utilization and agreement of TI-RADS reporting at our institution. METHODS: Radiology report data were collected and analyzed as part of a quality improvement project. A standardized TI-RADS dictation template was created, ultrasound technicians were trained, a multi-disciplinary conference initiated, and education provided for radiologists and clinicians. Control charts were used to track utilization and agreement of scoring of TI-RADS reporting based upon review by a radiologist trained in TI-RADS scoring. RESULTS: From January 2019 to January 2021, 218 patients with a thyroid nodule had a thyroid ultrasound performed at our institution. TI-RADS was utilized in 0 % (0 of 57) of children in the four months prior to project initiation. Following creation of the template, utilization increased to 65 % (39 of 60) over 5 months. Utilization further increased after the first training conference and was maintained above 90 % for 13 months. Ultrasound reports were in agreement in 46.7 % (28 of 60) of children initially. Agreement in reporting improved to 71.4 % (10 of 14) in the 3 months following the first training and to 78.4 % (58 of 74) over 12 months. Agreement in reporting was maintained at 80 % in the following 6 months. CONCLUSIONS: A quality improvement initiative can improve utilization and agreement of scoring using the TI-RADS system in pediatrics. This may ultimately reduce unnecessary biopsies and sedation in children. LEVEL OF EVIDENCE: Level III. TYPE OF STUDY: Quality Improvement.

Simultaneous Occurrence of Medullary Thyroid Carcinoma and Papillary Thyroid Carcinoma: A Case Series with Literature Review.

BACKGROUND: Papillary thyroid carcinoma (PTC) is the most common type of differentiated TC, while medullary TC (MTC) accounts for 4%. The concomitant presence of PTC and MTC is rare. METHODS: This is a retrospective, single-center observational study conducted over 16 years (2001-2017). The data were collected from the clinical records of patients who underwent total thyroidectomy at the Endocrine Unit-Department of Medicine of the University Hospital of Pisa, Italy. RESULTS: Over 690 analyzed cases, 650 (94.2%) were exclusive DTC, 19 exclusive MTC (2.75%) and 5 PTC/MTC (0.7%). No case of mixed medullary/follicular TC or hereditary MTC (familial MTC/multiple endocrine neoplasia type 2) was found. Among the five PTC/MTC cases, there was a male prevalence (M:F = 3:2), and all PTC components were at stage I, whereas 40% of MTC were at stage I and III and 20% of MTC were at stage II; microPTC (mPTC) was prevalent (80%) and also microMTCs were frequent (40%); 60% of MTC patients recovered, while 40% of patients developed metastatic disease. The search for germline mutations of the RET gene resulted in being negative in all cases. CONCLUSIONS: The incidence of PTC/MTC has been increasing over the past 30 years. The etiology of PTC/MTC forms is still unknown, and although this simultaneous occurrence could be only a coincidence, we cannot exclude the hypothesis of a shared genetic origin.

Rates of Detecting Thyroid Nodules Recommended for Biopsy with Ultrasound: Are All Indications Equal?

Background: The use of thyroid ultrasound increases yearly, adding to costs and overdetection of clinically irrelevant nodules. We investigated which indications most commonly prompt referral for thyroid ultrasound and the diagnostic utility by indication. Methods: We performed a retrospective observational cohort study of adults (≥18 years) undergoing an initial dedicated thyroid ultrasound between 2017 and 2019 at a tertiary academic center. Indicated reasons for referral were categorized into suspected palpable nodule (SPN), compressive symptoms (CS), metabolic symptoms (MS), screening due to high-risk factors, follow-up of incidental finding on other imaging, and combination of factors. Percentage of ultrasounds with an identifiable nodule and with a nodule recommended for biopsy was compared by indication. Separate logistic regression models were used to identify factors associated with finding any nodule and a biopsy-recommended nodule. Results: Among the 1739 patients included, the most common indication for thyroid ultrasound was SPN (40%), followed by incidental imaging (28%), CS (13%), combination (11%), MS (6%), and high-risk factors (2%). Overall, 62% of ultrasounds identified a nodule. Ultrasounds performed for incidental findings had the highest rate of nodule identification (94%), compared with 55%, 39%, and 43%, for SPN, CS, and MS, respectively (p < 0.05). Only 27% of ultrasounds identified a biopsy-recommended nodule. Nodules found incidentally had the highest rate of biopsy-recommended nodules at 55%. Rates of biopsy-recommended nodules for SPN, CS, and MS were 21%, 6%, and 10%, respectively. Logistic regression demonstrated that compared with patients referred for an SPN, those with incidental nodules were 10 times more likely to have a nodule found on ultrasound (odds ratio [OR] = 10.6 [CI 7.0-16.0]), while those referred for CS were half as likely to have a nodule (OR = 0.5 [CI 0.4-0.7]). Similar factors were associated with identification of biopsy-recommended nodules. Conclusions: Of all new dedicated thyroid ultrasounds, only a quarter find biopsy-recommended nodules, and nearly 40% do not identify a nodule at all. Notably, only 55% of ultrasounds done for SPN found a nodule. Ultrasound for CS and MS had the lowest rates of detecting nodules. Providing clear guidance on when to order thyroid ultrasounds can help reduce unnecessary health care utilization and potential overtreatment.

Unmasking the Silent Invader: A Rare Case of Follicular Thyroid Carcinoma With Skull Metastasis and an Uncommon KRAS Q61R Mutation.

Follicular thyroid carcinoma (FTC) is a noteworthy subtype of thyroid cancer known for its tendency to metastasize through the bloodstream, usually to the lungs and bones. This case report examines an exceptionally rare instance involving an 81-year-old female presenting with an unusual metastatic scalp lesion. Remarkably, this aggressive metastasis originated from a thyroid lesion as small as 0.7 cm. Lab findings, including suppressed TSH and elevated T3 levels, revealed subclinical hyperthyroidism, adding another layer of rarity to this FTC case. Molecular profiling identified a rare KRAS Q61R mutation, providing potential insight into the case's aggressive behavior and underscoring the importance of genetic assessment in FTC. This report emphasizes the critical role of comprehensive diagnostic evaluations, including histopathological assessments, in properly diagnosing and managing FTC, especially when clinical presentations defy conventional paradigms.

Correlation of ACR TI-RADS and Patient Outcomes in a Real-World Cohort Presenting for Thyroid Ultrasonography.

Context: The American College of Radiology Thyroid Image Reporting and Data System (ACR TI-RADS) was developed to predict malignancy risk in thyroid nodules using ultrasound features. TI-RADS was derived from a database of patients already selected for fine-needle aspiration (FNA), raising uncertainty about applicability to unselected patients. Objective: We aimed to assess the effect of ACR TI-RADS reporting in unselected patients presenting for thyroid ultrasound in a real-world setting. Methods: Records for all patients presenting for thyroid ultrasonography in Canterbury, New Zealand, were reviewed across two 18-month periods, prior to and after implementation of TI-RADS reporting. Patient outcomes were compared between the 2 periods. Malignancy rates were calculated for nodules 10 mm or larger with a definitive FNA or histology result. Results: A total of 1210 nodules were identified in 582 patients prior to implementation of TI-RADS; 1253 nodules were identified in 625 patients after implementation of TI-RADS. TI-RADS category was associated with malignancy rate (0% in TR1 and TR2, 3% in TR3, 5% in TR4, 12% in TR5; P = .02); however, 63% of nodules were graded TR3 or TR4, for which malignancy rate did not meaningfully differ from baseline risk. After implementation of TI-RADS there was a small reduction in the proportion of patients proceeding to FNA (49% vs 60%; P < .01) or surgery (14% vs 18%; P < .05), with no difference in cancer diagnoses (3% vs 4%, not significant). Conclusion: TI-RADS category is associated with malignancy rate and may alter clinical decision-making in a minority of patients; however, it is nondiscriminatory in the majority of nodules. In this study of unselected patients, nodules classified as TR5 and thus considered "highly suspicious" for cancer had only a modest risk of malignancy.

Improving the Efficacy of ACR TI-RADS Through Deep Learning-Based Descriptor Augmentation.

Thyroid nodules occur in up to 68% of people, 95% of which are benign. Of the 5% of malignant nodules, many would not result in symptoms or death, yet 600,000 FNAs are still performed annually, with a PPV of 5-7% (up to 30%). Artificial intelligence (AI) systems have the capacity to improve diagnostic accuracy and workflow efficiency when integrated into clinical decision pathways. Previous studies have evaluated AI systems against physicians, whereas we aim to compare the benefits of incorporating AI into their final diagnostic decision. This work analyzed the potential for artificial intelligence (AI)-based decision support systems to improve physician accuracy, variability, and efficiency. The decision support system (DSS) assessed was Koios DS, which provides automated sonographic nodule descriptor predictions and a direct cancer risk assessment aligned to ACR TI-RADS. The study was conducted retrospectively between (08/2020) and (10/2020). The set of cases used included 650 patients (21% male, 79% female) of age 53 ± 15. Fifteen physicians assessed each of the cases in the set, both unassisted and aided by the DSS. The order of the reading condition was randomized, and reading blocks were separated by a period of 4 weeks. The system's impact on reader accuracy was measured by comparing the area under the ROC curve (AUC), sensitivity, and specificity of readers with and without the DSS with FNA as ground truth. The impact on reader variability was evaluated using Pearson's correlation coefficient. The impact on efficiency was determined by comparing the average time per read. There was a statistically significant increase in average AUC of 0.083 [0.066, 0.099] and an increase in sensitivity and specificity of 8.4% [5.4%, 11.3%] and 14% [12.5%, 15.5%], respectively, when aided by Koios DS. The average time per case decreased by 23.6% (p = 0.00017), and the observed Pearson's correlation coefficient increased from r = 0.622 to r = 0.876 when aided by Koios DS. These results indicate that providing physicians with automated clinical decision support significantly improved diagnostic accuracy, as measured by AUC, sensitivity, and specificity, and reduced inter-reader variability and interpretation times.

History of Thyroid Ultrasound.

From low-resolution images in the 1960s to current high-resolution technology, ultrasound has proven to be the initial imaging modality of choice for thyroid application. Point-of-care ultrasound has brought the technology to the thyroid specialist. Combined with physical examination, it provides real-time information regarding goiter, thyroid nodules, and thyroid cancer. Ultrasound-guided fine-needle aspiration biopsy has become the accepted norm, with biopsies rarely performed using palpation alone. Advantages of ultrasound-guided biopsy include precise placement of the needle within the nodule, selective sampling of areas with suspicious features, and accurate direction of the biopsy needle to actively growing viable cells in the periphery of the nodule. Education of endocrinologists in thyroid ultrasound began in the late 1990s and by 2016 more than 6000 clinicians had completed an ultrasound course. Concurrent with this rapid expansion of use of thyroid ultrasound was a rise in the diagnosis of small papillary carcinomas, which might have otherwise remained indolent and undetected. The 2009 American Thyroid Association Guidelines for the Management of Thyroid Nodules and Thyroid Cancer recommended biopsy for all solid hypoechoic nodules measuring larger than 1 cm. Attempting to decrease the frequency of biopsies of low-risk nodules, subsequent guidelines have focused on identifying and selectively biopsying those thyroid nodules at higher risk of clinically significant carcinoma based on ultrasound appearance. A major role for thyroid ultrasound has been in both preoperative staging and mapping to help determine the extent of surgery, as well as postoperative monitoring for locoregional soft tissue or lymph node metastases. With the recognition that the increase in papillary carcinoma was predominantly a result of early diagnosis of small often indolent cancers, active surveillance has become a promising management strategy for papillary thyroid microcarcinomas. Thyroid ultrasound is essential to active surveillance of thyroid cancer. Easy access to high-quality ultrasound studies is a requirement for a successful active surveillance program. Thyroid ultrasound has been used to facilitate interventional procedures, including treatment of thyroid nodules, treatment of recurrent thyroid cancer, and therapy of papillary thyroid microcarcinoma.

Confounding factors and biases involved in regional differences in the detection rate of thyroid cancer in the second-round Thyroid Ultrasound Examination: the Fukushima Health Management Survey.

In response to concerns about health due to radiation exposure, the Fukushima Prefecture launched the Thyroid Ultrasound Examination program for residents aged 0-18 years at the time of the earthquake. Herein, we considered the confounding factors involved in the regional differences in the development of thyroid cancer. In this study, the 242 065 individuals who participated in both first- and second-round surveys were classified into four groups by address according to their air radiation dose. The number of participants diagnosed as malignant or suspicious for malignancy by cytological examination were 17, 38, 10 and 4 with detection rates of 53.8, 27.8, 21.7 and 14.5 per 100 000 participants in Regions 1, 2, 3 and 4, respectively. Sex (P = 0.0400), age at the time of the primary examination (P < 0.0001) and interval between the first- and second-round surveys (P < 0.0001) were significantly different among the four regions, and these were suspected to be confounding factors affecting regional differences in malignant nodule detection rates. In addition, significant regional differences were observed in the participation rate in the confirmatory examination (P = 0.0037) and the fine needle aspiration cytology implementation rate (P = 0.0037), which could be potential biases. No significant regional differences in the detection of malignant nodules were found in the multivariate logistic regression analysis after adjusting for the survey interval alone or for sex, age and survey interval. The confounding factors and biases identified in this study that may have important impacts on thyroid cancer detection rate should be fully considered in future studies.

Cytological and Ultrasound Features of Thyroid Nodules Correlate With Histotypes and Variants of Thyroid Carcinoma.

CONTEXT: Prognosis is excellent for papillary thyroid carcinoma (PTC), noninvasive follicular thyroid neoplasia with papillary-like nuclear features (NIFT-P), and follicular thyroid carcinoma (FTC) but is poor for poorly differentiated thyroid carcinoma (PDTC) and anaplastic thyroid carcinoma (ATC). Among PTCs, the prognosis is more favorable for follicular (FV-PTC) and classic (CV-PTC) than for tall cell (TCV-PTC), and solid (SV-PTC) variants. OBJECTIVE: To associate histotypes and variants of thyroid carcinoma with ultrasound and cytological features. METHODS: Histology of 1018 benign tumors and 514 PTC (249 CV, 167 FV, 49 TC, 34 SV, and 15 other variants), 52 NIFT-P, 50 FTC, 11 PDTC, and 3 ATC was correlated with fine-needle aspiration biopsy categories (Italian classification: TIR1, TIR2, TIR3A, TIR3B, TIR4, and TIR5) and ultrasound features at the Endocrinology Unit, University Hospital of Pisa. In total, 1117 patients with thyroid nodule(s) who underwent thyroidectomy were included. RESULTS: Of PTC, 36.3% had indeterminate cytology (TIR3A or TIR3B), 56.6% were suspicious for malignancy or malignant (TIR4 or TIR5); 84.0% FTC and 69.3% NIFT-P were TIR3A or TIR3B; 72.5% FV-PTC and 73.6% SV-PTC were TIR3A or TIR3B; 79.9% CV-PTC and 95.9% TCV-PTC were TIR4 or TIR5. The association of a hypoechoic pattern, irregular margins, and no microcalcifications was more frequent in TCV-PTC than in CV-PTC (P = .02, positive predictive value = 38.9%; negative predictive value = 85.5%). CONCLUSION: At cytology, most FTC, NIFT-P, FV-PTC, and SV-PTC were indeterminate, most CV-PTC and TCV-PTC were suspicious for malignancy or malignant. Ultrasound can be helpful in ruling out TCV-PTC.