Abstract
Computer-aided diagnosis (CAD) and other risk stratification systems may improve ultrasound image interpretation. This prospective study aimed to compare the diagnostic performance of CAD and the European Thyroid Imaging Reporting and Data System (EU-TIRADS) classification applied by physicians with S-Detect 2 software CAD based on Korean Thyroid Imaging Reporting and Data System (K-TIRADS) and combinations of both methods (MODELs 1 to 5). In all, 133 nodules from 88 patients referred to thyroidectomy with available histopathology or with unambiguous results of cytology were included. The S-Detect system, EU-TIRADS, and mixed MODELs 1–5 for the diagnosis of thyroid cancer showed a sensitivity of 89.4%, 90.9%, 84.9%, 95.5%, 93.9%, 78.9% and 93.9%; a specificity of 80.6%, 61.2%, 88.1%, 53.7%, 73.1%, 89.6% and 80.6%; a positive predictive value of 81.9%, 69.8%, 87.5%, 67%, 77.5%, 88.1% and 82.7%; a negative predictive value of 88.5%, 87.2%, 85.5%, 92.3%, 92.5%, 81.1% and 93.1%; and an accuracy of 85%, 75.9%, 86.5%, 74.4%, 83.5%, 84.2%, and 87.2%, respectively. Comparison showed superiority of the similar MODELs 1 and 5 over other mixed models as well as EU-TIRADS and S-Detect used alone (p-value < 0.05). S-Detect software is characterized with high sensitivity and good specificity, whereas EU-TIRADS has high sensitivity, but rather low specificity. The best diagnostic performance in malignant thyroid nodule (TN) risk stratification was obtained for the combined model of S-Detect (“possibly malignant” nodule) and simultaneously obtaining 4 or 5 points (MODEL 1) or exactly 5 points (MODEL 5) on the EU-TIRADS scale.
Highlights
Thyroid nodules (TNs) are the most frequent endocrine disorder and occur in 10–70% of the general population, with a relatively low malignancy rate of 3–10% [1]
The best diagnostic performance in malignant thyroid nodule (TN) risk stratification was obtained for the combined model of S-Detect
Ultrasonography (US) of the thyroid gland is commonly used by physicians and is crucial to decide on further management, such as qualification for fine-needle aspiration biopsy (FNAB) as well as the decision on a conservative or surgical approach [2,3]
Summary
Thyroid nodules (TNs) are the most frequent endocrine disorder and occur in 10–70% of the general population, with a relatively low malignancy rate of 3–10% [1]. A meta-analysis of seven studies, evaluating 5672 thyroid nodules, indicated that stratifying the risk of thyroid nodules by EU-TIRADS showed high performance, while the prevalence of malignancy in EU-TIRADS class 5 was equal to 76.1% [13] Even this classification might be intricate for inexperienced physicians [8]. There is an unmet need for validation of the method on a large cohort of patients in highly referenced centers to provide reliable information on its real clinical utility and identify a target group of physicians who may benefit from the CAD-supported evaluation of TNs. the aim of our study was to compare CAD diagnostic performance with the state-of-the-art thyroid nodule classification EU-TIRADS applied by physicians based on US morphological features, in order to support decision-making regarding the further management of TNs
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
