Thyroid cancer is one of the common types of cancer worldwide, and Ultrasound (US) imaging is a modality normally used for thyroid cancer diagnostics. The American College of Radiology Thyroid Imaging Reporting and Data System (ACR TIRADS) has been widely adopted to identify and classify US image characteristics for thyroid nodules. This paper presents novel methods for detecting the characteristic descriptors derived from TIRADS. Our methods return descriptions of the nodule margin irregularity, margin smoothness, calcification as well as shape and echogenicity using conventional computer vision and deep learning techniques. We evaluate our methods using datasets of 471 US images of thyroid nodules acquired from US machines of different makes and labeled by multiple radiologists. The proposed methods achieved overall accuracies of 88.00%, 93.18%, and 89.13% in classifying nodule calcification, margin irregularity, and margin smoothness respectively. Further tests with limited data also show a promising overall accuracy of 90.60% for echogenicity and 100.00% for nodule shape. This study provides an automated annotation of thyroid nodule characteristics from 2D ultrasound images. The experimental results showed promising performance of our methods for thyroid nodule analysis. The automatic detection of correct characteristics not only offers supporting evidence for diagnosis, but also generates patient reports rapidly, thereby decreasing the workload of radiologists and enhancing productivity.

OBJECTIVE: To explore the diagnostic performance of the currently used ultrasound-based thyroid nodule risk stratification systems (K-TIRADS, ACR -TIRADS, and C-TIRADS) in differentiating follicular thyroid adenoma (FTA) from follicular thyroid carcinoma (FTC).
METHODS: Clinical data and preoperative ultrasonographic images of 269 follicular thyroid neoplasms were retrospectively analyzed. All of them were detected by Color Doppler ultrasound instruments equipped with high-frequency liner array probes (e.g. Toshiba Apoli500 with L5-14MHZ; Philips IU22 with L5-12MHZ; GE LOGIQ E9 with L9-12MHZ and MyLab Class C with L9-14MHZ). The diagnostic performance of three TIRADS classifications for differentiating FTA from FTC was evaluated by drawing the receiver operating characteristic (ROC) curves and calculating the cut-off values.
RESULTS: Of the 269 follicular neoplasms (mean size, 3.67±1.53 cm), 209 were FTAs (mean size, 3.56±1.38 cm) and 60 were FTCs (mean size, 4.07±1.93 cm). There were significant differences in ultrasound features such as margins, calcifications, and vascularity of thyroid nodules between the FTA and FTC groups (P < 0.05). According to the ROC curve comparison analysis, the diagnostic cut-off values of K-TIRADS, ACR-TIRADS, and C-TIRADS for identifying FTA and FTC were K-TR4, ACR-TR4, and C-TR4B, respectively, and the areas under the curves were 0.676, 0.728, and 0.719, respectively. The difference between ACR-TIRADS and K-TIRADS classification was statistically significant (P = 0.0241), whereas the differences between ACR-TIRADS and C-TIRADS classification and between K-TIRADS and C-TIRADS classification were not statistically significant (P > 0.05).
CONCLUSIONS: The three TIRADS classifications were not conducive to distinguishing FTA from FTC. It is necessary to develop a novel malignant risk stratification system specifically for the identification of follicular thyroid neoplasms.

To compare the diagnostic efficacy of the Chinese Thyroid Imaging Reporting and Data Systems (C-TIRADS) with the well-accepted ACR-TIRADS guidelines in identifying benign from malignant thyroid nodules.
A total of 2064 nodules were collected from 1627 patients undergoing thyroid ultrasonography in our center between October 2019 and November 2021. Nodules were divided into two groups: \"≥1 cm\" and \"<1 cm\". Ultrasound features of each nodule were observed and recorded by two physicians with more than 15 years of experience and classified according to the ACR-TIRADS and C-TIRADS guidelines, respectively.
The area under the curve of the ACR-TIRADS guideline was higher than that of the C-TIRADS guideline (0.922, P = 0.017), the specificity and positive predictive value of the C-TIRADS guideline were higher (81.64%, 88.72%, all P < 0.05), which was more significant in the subgroup of nodules <1 cm (P = 0.001). In addition, there was no statistical difference between the two guidelines in the diagnostic efficacy indicators for nodules ≥1 cm. The ACR-TIRADS effectively reduced unnecessary biopsies compared with the C-TIRADS (P < 0.05).
There was high agreement between the two guidelines for the diagnosis of thyroid nodules, C-TIRADS guidelines had a higher specificity and simplicity while were inferior to the ACR-TIRADS guidelines in terms of reducing the number of biopsies.

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.
CONCLUSIONS: • 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%.

UNASSIGNED: To explore the value of the optimal parameters of shear wave elastography (SWE) to enhance the identification of benign and malignant thyroid nodules by C-TIRADS.
UNASSIGNED: The two-dimensional ultrasonography images and SWE images of 515 patients with a total of 586 thyroid nodules were retrospectively analyzed. The nodules were divided into the D ≤10 mm and D >10 mm groups according to size and were graded by C-TIRADS. With the pathological results as the gold standard, the receiver operating characteristic (ROC) curves were drawn, and the area under the curve (AUC) was calculated to compare the diagnostic performances of C-TIRADS, SWE, and the combination of the two on the benign and malignant thyroid nodules.
UNASSIGNED: The ROC showed that the AUC of the maximum elastic modulus (0.875) was higher than that of the mean elastic modulus (0.798) and elasticity ratio (0.772), with an optimal cutoff point of 51 kPa, which was the optimal parameter to distinguish the malignant from the benign nodules (P < 0.001). In the D ≤10 mm group, the AUC of TIRADS combined with SWE (0.955) was elevated by 0.172 compared with the application of C-TIRADS alone (0.783), and the difference was statistically significant (P < 0.05). In the D >10 mm group, the AUC of TIRADS combined with SWE (0.904) was elevated by 0.076 compared with the application of C-TIRADS alone (0.828), and the difference was statistically significant (P < 0.05). Among all nodules, the application of C-TIRADS alone had a sensitivity of 88.14%, a specificity of 74.56%, and an accuracy of 85.50% in diagnosing benign and malignant thyroid nodules, while the sensitivity, specificity, and accuracy were 93.22%, 90.35%, and 92.66%, respectively, in combination with SWE.
UNASSIGNED: The diagnostic performance of SWE in combination with TIRADS was better than that of SWE or C-TIRADS alone. Here, SWE enhanced the diagnostic performance of C-TIRADS for the benign and malignant thyroid nodules, most significantly for nodules with D ≤10 mm.

This study investigated the diagnostic value of the Angio Planewave Ultrasensitive (AngioPLUS) Doppler ultrasound in improving the efficacy of grey scale ultrasound in thyroid nodule diagnosis. The EU TIRADS was used for the grey scale ultrasound assessment of 94 thyroid nodules. conventional Doppler and AngioPLUS Doppler ultrasound images were evaluated using qualitative vascularity grading, where predominant central vascularity indicated malignancy-suspicion, and quantitative regional vascularity assessment, where predominant peripheral vascularity using a ratio vascularity index (RVI) of > 1 indicated benign disease. Diagnostic performance outcomes of sole and combination approaches were calculated based on final pathologic results. Using sole EU TIRADS and AngioPLUS + power Doppler imaging (APDI) based on qualitative vascularity and RVI, the results were a sensitivity of 83.3% vs. 83.3 vs. 66.7% and a specificity of 50% vs. 81.3% vs. 73.4, respectively. EU TIRADS combined with APDI significantly improved the specificity using both qualitative vascularity and RVI assessment approaches (84.4% and 81%, respectively, p < 0.05); and slightly reduced the sensitivity (76.7% and 58.1%). For cytologically-equivocal thyroid nodules, the combination approach using qualitative vascularity assessment outperformed the EU TIRADS (sensitivity: both were 88.9%; specificity: 77.4% vs. 38.7%, p < 0.05; and AUROC: 0.83 vs. 0.62, p < 0.05). APDI combined with EU TIRADS is diagnostically efficient in stratifying thyroid nodules, particularly cytologically-equivocal nodules.

OBJECTIVE: This study aimed to evaluate the impact of thyroid nodule sizes on the diagnostic performance of Korean thyroid imaging reporting and data system (TIRADS) and contrast-enhanced ultrasound (CEUS).
METHODS: In total, 308 consecutive patients with 382 thyroid nodules underwent US-guided FNA or surgery were included in this retrospective study. The nodule size was classified into 3 categories: ≤10 mm (group A), 10-20 mm (group B), and ≥20 mm (group C). We compared the risk of malignancy in each subgroup, categorized according to the TIRADS and CEUS patterns.
RESULTS: In group A, the differences in diagnostic value between TIRADS and CEUS were significant (AUC: 0.804 vs 0.733, P = 0.028, sensitivity: 81.8% vs 72.7%, P = 0.013, specificity: 88.9% vs 79.4%, P = 0.011). In group B, the AUC (0.897), sensitivity (88.1%) and specificity (91.9%) of CEUS were highest. In group C, the specificity of CEUS was significantly higher compared with TIRADS classification (90.8% vs 82.9%, P = 0.023), while the sensitivity and AUC showed no significant difference between the two models (84.2% vs 81.5%, P > 0.406, 0.848 vs 0.820, P = 0.545).
CONCLUSIONS: Nodule size influences the diagnostic accuracy of the two methods. TIRADS have best value in nodules ≤10 mm, while CEUS perform best for differentiating lesions >10 mm, especially in lesions ≥20 mm.