Automated detection and classification of thyroid nodules in ultrasound images using clinical-knowledge-guided convolutional neural networks

Thyroid nodules are very common all over the world, and China is no exception. Ultrasound plays an important role in determining the risk stratification of thyroid nodules, which is critical for clinical management of thyroid nodules. For the past few years, many versions of TIRADS (Thyroid Imaging Reporting and Data System) have been put forward by several institutions with the aim to identify whether nodules require fine-needle biopsy or ultrasound follow-up. However, no version of TIRADS has been widely adopted worldwide till date. In China, as many as ten versions of TIRADS have been used in different hospitals nationwide, causing a lot of confusion. With the support of the Superficial Organ and Vascular Ultrasound Group of the Society of Ultrasound in Medicine of the Chinese Medical Association, the Chinese-TIRADS that is in line with China's national conditions and medical status was established based on literature review, expert consensus, and multicenter data provided by the Chinese Artificial Intelligence Alliance for Thyroid and Breast Ultrasound.

2020 Chinese guidelines for ultrasound malignancy risk stratification of thyroid nodules: the C-TIRADS.

Balancing the benefits and harms of thyroid cancer surveillance in survivors of Childhood, adolescent and young adult cancer: Recommendations from the international Late Effects of Childhood Cancer Guideline Harmonization Group in collaboration with the PanCareSurFup Consortium

Thyroid nodules are a common occurrence in the general population, and these incidental thyroid nodules are often referred for ultrasound (US) evaluation. US provides a safe and fast method of examination. It is sensitive for the detection of thyroid nodules, and suspicious features can be used to guide further investigation/management decisions. However, given the financial burden on the health service and unnecessary anxiety for patients, it is unrealistic to biopsy every thyroid nodule to confirm diagnosis. The British Thyroid Association (BTA) has recently produced a US classification (U1–U5) of thyroid nodules to facilitate the decision-making process regarding the need to perform fine-needle aspiration cytology (FNAC) for suspicious cases. In this pictorial review, we provide a complete series of sonographic images to illustrate benign and malignant features of thyroid nodules according to the U1–5 classification. Specifically, we highlight morphologic characteristic of the nodule, including its echo signal in relation to its consistency, nodular size, number and contour. Additional diagnostic features such as halo, colloid, calcification and vascular patterns are also discussed in detail. The aim is to assist radiologists and clinicians in recognising sonographic patterns of benign, suspicious and malignant nodules based on U1–5 criteria, and in planning for further investigations. • Ultrasound is sensitive in identifying suspicious features, which require aspiration.
 • Whether nodules require aspiration should be based on sonographic features and clinical findings.
 • U1–5 classification of sonographic findings can help determine whether aspiration is necessary.

/pdf/ultrasonography-of-thyroid-nodules-a-pictorial-review-md335sp8jc.pdf

Ultrasonography of thyroid nodules: a pictorial review.

Objective.Contrast-enhanced ultrasound (CEUS) is a new noninvasive modality for the diagnosis of thyroid nodules. However, the performance of CEUS in differentiating malignant and benign thyroid nodules has not been systematically evaluated. This meta-analysis was performed to assess the accuracy of CEUS in diagnosing thyroid nodules.Data SourcesPubMed, Embase, and the references of included studies were examined.Review MethodsWe recorded the characteristics of the included studies and assessed the quality of each study using the Quality Assessment of Diagnostic Accuracy Studies tool. The pooled sensitivity, specificity, positive likelihood ratio (LR), negative LR, diagnostic odds ratio (DOR), and area under the curve (AUC) were calculated. We also evaluated the publication bias.ResultsThis meta-analysis included 7 studies with a total of 597 thyroid nodules. The pooled the sensitivity, specificity, and positive and negative LR were 0.853, 0.876, 5.822, and 0.195, respectively. The DOR and AUC were 34.730...

Contrast-Enhanced Ultrasound for Differentiation of Benign and Malignant Thyroid Lesions: Meta-analysis

Replacing palpating fingers with an ultrasound (US) probe has resulted in an epidemic of thyroid nodules. Despite the high prevalence of thyroid nodules in the general population, thyroid malignancy is rare. Although no imaging modality can accurately predict the nature of every nodule, high-resolution US is the most sensitive, easily available and cost-effective diagnostic test available to detect thyroid nodules, measure their dimensions and identify their structure. The presence of calcifications, irregular spiculated outline, hypoechogenicity in a solid nodule, chaotic intranodular vascularity and an elongated shape are well-known US features of malignancy in thyroid nodules. Cervical lymph node metastasis and extrathyroidal extension of a thyroid nodule are highly specific for malignancy but seen infrequently. Spongiform nodules, purely or predominantly cystic nodules, nodules with well-defined hypoechoic halo and echogenic as well as isoechoic nodules are usually benign. None of the US characteristics have 100% accuracy in detecting or excluding malignancy. Fine-needle biopsy is currently the best triage test for pre-operative evaluation of a thyroid nodule. There is no significant difference in the risk for malignancy between palpable and non-palpable nodules and size is not a reliable indicator for their malignant potential. The best tool for risk stratification for malignancy in thyroid nodules is US and guided biopsy of nodules with suspicious imaging features. This is especially relevant in patients with multinodular goitre.

Amogh Hegde

Papers

Thyroid nodules: risk stratification for malignancy with ultrasound and guided biopsy