International Expert Consensus on US Lexicon for Thyroid Nodules.

Multiple US-based systems for risk stratification of thyroid nodules are in use worldwide. Unfortunately, the malignancy probability assigned to a nodule varies, and terms and definitions are not consistent, leading to confusion and making it challenging to compare study results and craft revisions. Consistent application of these systems is further hampered by interobserver variability in identifying the sonographic features on which they are founded. In 2018, an international multidisciplinary group of 19 physicians with expertise in thyroid sonography (termed the International Thyroid Nodule Ultrasound Working Group) was convened with the goal of developing an international system, tentatively called the International Thyroid Imaging Reporting and Data System, or I-TIRADS, in two phases: (phase I) creation of a lexicon and atlas of US descriptors of thyroid nodules and (phase II) development of a system that estimates the malignancy risk of a thyroid nodule. This article presents the methods and results of phase I. The purpose herein is to show what has been accomplished thus far, as well as generate interest in and support for this effort in the global thyroid community.

Artificial Intelligence for Evaluation of Thyroid Nodules: A Primer.

Background: Artificial intelligence (AI) is broadly defined as the ability of machines to apply human-like reasoning to problem solving. Recent years have seen a rapid growth of AI in many disciplines. This review will focus on AI applications in the assessment of thyroid nodules. Summary: AI encompasses two related computational techniques: machine learning, in which computers learn by observing data provided by humans, and deep learning, which employs neural networks that mimic brain structure and function to analyze data. Some experts believe the way AI systems reach a conclusion should be transparent, or explainable, while others disagree. Most AI platforms in thyroid disease have focused on malignancy risk stratification of nodules. To date, four have been approved by the United States Food and Drug Administration. While the results of validation studies have been mixed, there is ample evidence that AI can exceed the performance of some humans, particularly physicians with less experience. AI has also been applied to assessment of lymph nodes and cytopathology specimens. Conclusions: Adoption of AI in thyroid disease will require vendors to demonstrate that their software works as intended, is readily usable in real-world settings, and is cost effective. AI platforms that perform best in head-to-head comparisons will dominate and spur wider adoption.

An International Survey on Utilization of Five Thyroid Nodule Risk Stratification Systems: A Needs Assessment with Future Implications.

Background: Multiple ultrasound-based risk stratification systems (RSSs) for thyroid nodules are used worldwide. Variations in structure, performance, and recommendations are confusing for physicians and patients and complicate management decisions. The goal of this study was to determine the factors that are associated with choice of RSS and barriers to RSS use. These results are intended to inform development of a universal international thyroid ultrasound RSS. Methods: An online survey with questions about usage of RSSs, ultrasound practice and volumes, training, specialty, practice type, and geographic region was made available to members of five professional societies via email. Subgroup analysis was performed to identify the factors that governed use of one or more of five leading RSSs: American Association of Clinical Endocrinology (AACE), American College of Endocrinology (ACE), and Associazione Medici Endocrinologi (AME) Medical Guidelines, American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS), American Thyroid Association (ATA) guidelines, European Thyroid Association TIRADS (EU-TIRADS), and Korean Society of Thyroid Radiology/Korean Thyroid Association TIRADS (K-TIRADS). Results: There were 875 respondents from 52 countries (response rate not estimated due to overlapping society membership). More than 7 specialties were represented, with most (538; 61.5%) in endocrinology. The choice of RSS was strongly associated with medical specialty and geographic region. Of 692 respondents who indicated that their practice used an RSS, 213 (30.8%) used more than one. The specialties that were more likely to use multiple RSSs were surgery and others (40%), followed by endocrinology (33.0%), and radiology or nuclear medicine (17%) (p < 0.001). Of 271 (31.0%) respondents who indicated that they do not personally use an RSS, the majority (168; 62%) preferred to describe the specific sonographic characteristics/features that they believe are most relevant in a nodule. Conclusions: Almost one third of respondents indicated use of more than one RSS in their practice, potentially leading to confusion, and a similar proportion reported not using an RSS for various reasons. A unified international system that addresses their concerns and simplifies risk classification of thyroid nodules may benefit practitioners and patients. This is particularly important as newer thyroid nodule management options gain acceptance.

Comparison of Thyroid Risk Categorization Systems and Fine-Needle Aspiration Recommendations in a Multi-Institutional Thyroid Ultrasound Registry.

OBJECTIVES: The aim of this study was to compare how often fine-needle aspiration (FNA) would be recommended for nodules in unselected, low-risk adult patients referred for sonographic evaluation of thyroid nodules by ACR Thyroid Imaging Reporting and Data System (TI-RADS), the American Thyroid Association guidelines (ATA), Korean Thyroid Imaging Reporting and Data System (K-TIRADS), European Thyroid Imaging Reporting and Data System (EU-TIRADS), and Artificial Intelligence Thyroid Imaging Reporting and Data System (AI-TIRADS). METHODS: Seven practices prospectively submitted thyroid ultrasound reports on adult patients to the ACR Thyroid Imaging Research Registry between October 2018 and March 2020. Data were collected about the sonographic features of each nodule using a structured reporting template with fields for the five ACR TI-RADS ultrasound categories plus maximum nodule size. The nodules were also retrospectively categorized according to criteria from ACR TI-RADS, the ATA, K-TIRADS, EU-TIRADS, and AI-TIRADS to compare FNA recommendation rates. RESULTS: For 27,933 nodules in 12,208 patients, ACR TI-RADS recommended FNA for 8,128 nodules (29.1%, 95% confidence interval [CI] 0.286-0.296). The ATA guidelines, EU-TIRADS, K-TIRADS, and AI-TIRADS would have recommended FNA for 16,385 (58.7%, 95% CI 0.581-0.592), 10,854 (38.9%, 95% CI 0.383-0.394), 15,917 (57.0%, 95% CI 0.564-0.576), and 7,342 (26.3%, 95% CI 0.258-0.268) nodules, respectively. Recommendation for FNA on TR3 and TR4 nodules was lowest for ACR TI-RADS at 18% and 30%, respectively. ACR TI-RADS categorized more nodules as TR2, which does not require FNA. At the high suspicion level, the FNA rate was similar for all guidelines at 68.7% to 75.5%. CONCLUSION: ACR TI-RADS recommends 25% to 50% fewer biopsies compared with ATA, EU-TIRADS, and K-TIRADS because of differences in size thresholds and criteria for risk levels.

Incidental Thyroid Nodules on Imaging: Relevance and Management.

Incidental thyroid nodules (ITNs) are commonly detected on imaging examinations performed for other reasons, particularly computed tomography (CT) (and now PET-CT and even PET-MR imaging), MR imaging, and sonography, primarily a consequence of the increasing sensitivity of these diagnostic modalities. Appropriate management of ITNs is crucial to avoid the cost and medical consequences of unnecessary workups.

Update on ACR TI-RADS: Successes, Challenges, and Future Directions, From the AJR Special Series on Radiology Reporting and Data Systems.

The American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) is an ultrasound-based risk stratification system (RSS) for thyroid nodules that was released in 2017. Since publication, research has shown that ACR TI-RADS has a higher specificity than other RSSs and reduces the number of unnecessary biopsies of benign nodules compared with other systems by 19.9-46.5%. The risk of missing significant cancers using ACR TI-RADS is mitigated by the follow-up recommendations for nodules that do not meet criteria for biopsy. In practice, after a nodule's ultrasound features have been enumerated, the ACR TI-RADS points-based approach leads to clear management recommendations. Practices seeking to implement ACR TI-RADS must engage their radiologists in understanding how the system addresses the problems of thyroid cancer overdiagnosis and unnecessary surgeries by reducing unnecessary biopsies. This review compares ACR TI-RADS to other RSSs and explores key clinical questions faced by practices considering its implementation. We also address the challenge of reducing interobserver variability in assigning ultrasound features. Finally, we highlight emerging imaging techniques and recognize the ongoing international effort to develop a system that harmonizes multiple RSSs, including ACR TI-RADS.

Analysis of Malignant Thyroid Nodules That Do Not Meet ACR TI-RADS Criteria for Fine-Needle Aspiration.

OBJECTIVE. Compared with other guidelines, the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) has decreased the number of nodules for which fine-needle aspiration is recommended. The purpose of this study was to evaluate the characteristics of malignant nodules that would not be biopsied when the ACR TI-RADS recommendations are followed. MATERIALS AND METHODS. We retrospectively reviewed a total of 3422 thyroid nodules for which a definitive cytologic diagnosis, a definitive histologic diagnosis, or both diagnoses as well as diagnostic ultrasound (US) examinations were available. All nodules were categorized using the ACR TI-RADS, and they were divided into three groups according to the recommendation received: fine-needle aspiration (group 1), follow-up US examination (group 2), or no further evaluation (group 3). RESULTS. Of the 3422 nodules, 352 were malignant. Of these, 240 nodules were assigned to group 1, whereas 72 were assigned to group 2 and 40 were included in group 3. Sixteen of the 40 malignant nodules in group 3 were 1 cm or larger, and, on the basis of analysis of the sonographic features described in the ACR TI-RADS, these nodules were classified as having one of five ACR TI-RADS risk levels (TR1-TR5), with one nodule classified as a TR1 nodule, eight as TR2 nodules, and seven as TR3 nodules. If the current recommendation of no follow-up for TR2 nodules was changed to follow-up for nodules 2.5 cm or larger, seven additional malignant nodules and 316 additional benign nodules would receive a recommendation for follow-up. If the current size threshold (1.5 cm) used to recommend US follow-up for TR3 nodules was decreased to 1.0 cm, seven additional malignant nodules and 118 additional benign nodules would receive a recommendation for follow-up. CONCLUSION. With use of the ACR TI-RADS, most malignant nodules that would not be biopsied would undergo US follow-up, would be smaller than 1 cm, or would both undergo US follow-up and be smaller than 1 cm. Adjusting size thresholds to decrease the number of missed malignant nodules that are 1 cm or larger would result in a substantial increase in the number of benign nodules undergoing follow-up.

Management of Thyroid Nodules Seen on US Images: Deep Learning May Match Performance of Radiologists.

BackgroundManagement of thyroid nodules may be inconsistent between different observers and time consuming for radiologists. An artificial intelligence system that uses deep learning may improve radiology workflow for management of thyroid nodules.PurposeTo develop a deep learning algorithm that uses thyroid US images to decide whether a thyroid nodule should undergo a biopsy and to compare the performance of the algorithm with the performance of radiologists who adhere to American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS).Materials and MethodsIn this retrospective analysis, studies in patients referred for US with subsequent fine-needle aspiration or with surgical histologic analysis used as the standard were evaluated. The study period was from August 2006 to May 2010. A multitask deep convolutional neural network was trained to provide biopsy recommendations for thyroid nodules on the basis of two orthogonal US images as the input. In the training phase, the deep learning algorithm was first evaluated by using 10-fold cross-validation. Internal validation was then performed on an independent set of 99 consecutive nodules. The sensitivity and specificity of the algorithm were compared with a consensus of three ACR TI-RADS committee experts and nine other radiologists, all of whom interpreted thyroid US images in clinical practice.ResultsIncluded were 1377 thyroid nodules in 1230 patients with complete imaging data and conclusive cytologic or histologic diagnoses. For the 99 test nodules, the proposed deep learning algorithm achieved 13 of 15 (87%: 95% confidence interval [CI]: 67%, 100%) sensitivity, the same as expert consensus (P > .99) and higher than five of nine radiologists. The specificity of the deep learning algorithm was 44 of 84 (52%; 95% CI: 42%, 62%), which was similar to expert consensus (43 of 84; 51%; 95% CI: 41%, 62%; P = .91) and higher than seven of nine other radiologists. The mean sensitivity and specificity for the nine radiologists was 83% (95% CI: 64%, 98%) and 48% (95% CI: 37%, 59%), respectively.ConclusionSensitivity and specificity of a deep learning algorithm for thyroid nodule biopsy recommendations was similar to that of expert radiologists who used American College of Radiology Thyroid Imaging and Reporting Data System guidelines.© RSNA, 2019Online supplemental material is available for this article.

Using Artificial Intelligence to Revise ACR TI-RADS Risk Stratification of Thyroid Nodules: Diagnostic Accuracy and Utility.

Background Risk stratification systems for thyroid nodules are often complicated and affected by low specificity. Continual improvement of these systems is necessary to reduce the number of unnecessary thyroid biopsies. Purpose To use artificial intelligence (AI) to optimize the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS). Materials and Methods A total of 1425 biopsy-proven thyroid nodules from 1264 consecutive patients (1026 women; mean age, 52.9 years [range, 18-93 years]) were evaluated retrospectively. Expert readers assigned points based on five ACR TI-RADS categories (composition, echogenicity, shape, margin, echogenic foci), and a genetic AI algorithm was applied to a training set (1325 nodules). Point and pathologic data were used to create an optimized scoring system (hereafter, AI TI-RADS). Performance of the systems was compared by using a test set of the final 100 nodules with interpretations from the expert reader, eight nonexpert readers, and an expert panel. Initial performance of AI TI-RADS was calculated by using a test for differences between binomial proportions. Additional comparisons across readers were conducted by using bootstrapping; diagnostic performance was assessed by using area under the receiver operating curve. Results AI TI-RADS assigned new point values for eight ACR TI-RADS features. Six features were assigned zero points, which simplified categorization. By using expert reader data, the diagnostic performance of ACR TI-RADS and AI TI-RADS was area under the receiver operating curve of 0.91 and 0.93, respectively. For the same expert, specificity of AI TI-RADS (65%, 55 of 85) was higher (P < .001) than that of ACR TI-RADS (47%, 40 of 85). For the eight nonexpert radiologists, mean specificity for AI TI-RADS (55%) was also higher (P < .001) than that of ACR TI-RADS (48%). An interactive AI TI-RADS calculator can be viewed at http://deckard.duhs.duke.edu/∼ai-ti-rads . Conclusion An artificial intelligence-optimized Thyroid Imaging Reporting and Data System (TI-RADS) validates the American College of Radiology TI-RADS while slightly improving specificity and maintaining sensitivity. Additionally, it simplifies feature assignments, which may improve ease of use. © RSNA, 2019 Online supplemental material is available for this article.

Interobserver Variability of Sonographic Features Used in the American College of Radiology Thyroid Imaging Reporting and Data System.

OBJECTIVE: The purpose of this study was to assess interobserver variability in assigning features in the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) lexicon and in making recommendations for thyroid nodule biopsy. MATERIALS AND METHODS: The study cohort comprised 100 nodules in 92 patients who underwent fine-needle aspiration with definitive cytologic results (Bethesda category II or VI) or diagnostic lobectomy between April 2009 and May 2010. Eight board-certified radiologists evaluated the nodules according to the five feature categories that constitute ACR TI-RADS and gave a biopsy recommendation based on their own practice. Variability in feature assignment and biopsy recommendation was assessed with the Fleiss kappa statistic. RESULTS: Agreement in interpretation was fair to moderate for all features except shape (κ = 0.61) and macrocalcifications (κ = 0.73), which had substantial agreement. The features with the poorest agreement were margin and other types of echogenic foci, which had kappa values ranging from 0.25 to 0.39, indicating fair agreement. Interobserver agreement regarding biopsy recommendation was fair (κ = 0.22) based on radiologists' current practice. Applying ACR TI-RADS resulted in moderate agreement (κ = 0.51). CONCLUSION: Variability in interpreting thyroid nodule sonographic features was highest for margin and all types of echogenic foci, except for macrocalcifications. Because radiologists' interpretations of these features change the level of suspicion of thyroid malignancy, the results of this study suggest a need for further education. Despite the variability in assigning features, adoption of ACR TI-RADS improves agreement for recommending biopsy.

Thyroid Imaging Reporting and Data System (TI-RADS): A User's Guide.

In 2017, the Thyroid Imaging Reporting and Data System (TI-RADS) Committee of the American College of Radiology (ACR) published a white paper that presented a new risk-stratification system for classifying thyroid nodules on the basis of their appearance at ultrasonography (US). In ACR TI-RADS, points in five feature categories are summed to determine a risk level from TR1 to TR5. Recommendations for biopsy or US follow-up are based on the nodule's ACR TI-RADS level and its maximum diameter. The purpose of this article is to offer practical guidance on how to implement and apply ACR TI-RADS based on the authors' experience with the system. © RSNA, 2018.

Reduction in Thyroid Nodule Biopsies and Improved Accuracy with American College of Radiology Thyroid Imaging Reporting and Data System.

Purpose To compare the biopsy rate and diagnostic accuracy before and after applying the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) criteria for thyroid nodule evaluation. Materials and Methods In this retrospective study, eight radiologists with 3-32 years experience in thyroid ultrasonography (US) reviewed US features of 100 thyroid nodules that were cytologically proven, pathologically proven, or both in December 2016. The radiologists evaluated nodule features in five US categories and provided biopsy recommendations based on their own practice patterns without knowledge of ACR TI-RADS criteria. Another three expert radiologists served as the reference standard readers for the imaging findings. ACR TI-RADS criteria were retrospectively applied to the features assigned by the eight radiologists to produce biopsy recommendations. Comparison was made for biopsy rate, sensitivity, specificity, and accuracy. Results Fifteen of the 100 nodules (15%) were malignant. The mean number of nodules recommended for biopsy by the eight radiologists was 80 ± 16 (standard deviation) (range, 38-95 nodules) based on their own practice patterns and 57 ± 11 (range, 37-73 nodules) with retrospective application of ACR TI-RADS criteria. Without ACR TI-RADS criteria, readers had an overall sensitivity, specificity, and accuracy of 95% (95% confidence interval [CI]: 83%, 99%), 20% (95% CI: 16%, 25%), and 28% (95% CI: 21%, 37%), respectively. After applying ACR TI-RADS criteria, overall sensitivity, specificity, and accuracy were 92% (95% CI: 68%, 98%), 44% (95% CI: 33%, 56%), and 52% (95% CI: 40%, 63%), respectively. Although fewer malignancies were recommended for biopsy with ACR TI-RADS criteria, the majority met the criteria for follow-up US, with only three of 120 (2.5%) malignancy encounters requiring no follow-up or biopsy. Expert consensus recommended biopsy in 55 of 100 nodules with ACR TI-RADS criteria. Their sensitivity, specificity, and accuracy were 87% (95% CI: 48%, 98%), 51% (95% CI: 40%, 62%), and 56% (95% CI: 46%, 66%), respectively. Conclusion ACR TI-RADS criteria offer a meaningful reduction in the number of thyroid nodules recommended for biopsy and significantly improve the accuracy of recommendations for nodule management. © RSNA, 2018 Online supplemental material is available for this article.