RESUMEN
Objective@#To explore the diagnostic efficiency of K-TIRADS, ACR-TIRADS and ATA risk stratification in computer-aided detection and diagnosis(CAD) software and the application value of CAD-assisted ultrasound physicians in diagnosing thyroid nodules.@*Methods@#One hundred and ninety-two thyroid nodules with postoperative pathological results were retrospectively analyzed. All of them were graded by K-TIRADS, ACR-TIRADS and ATA with CAD software, and the best guide was recognized by calculating the area under the ROC curve, sensitivity and specificity. Then, based on the best guidelines for the classification criteria, the double-blind method was used to compare the ability of the same ultrasonologist to diagnose thyroid nodules before and after CAD.@*Results@#The AUC value of K-TIRADS, ACR-TIRADS, ATA was 0.88, 0.77, 0.62 respectively in the CAD software. The difference between the two groups was statistically significant (P<0.05). There was no significant difference in the specificity between K-TIRADS and ATA(P=0.176), which were both higher than ACR-TIRADS with statistically significant differences (P<0.05). The AUC value of the diagnosis among CAD itself, ultrasound physicians and physicians combined CAD was 0.88, 0.80, 0.93, respectively. The difference between the two groups was statistically significant (P<0.05). There was no significant difference in the sensitivity between CAD itself and physicians combined CAD(P=0.163), which were both higher than ultrasound physicians with statistical significant differences(P<0.05). Among ultrasound physicians, CAD itself and physicians combined CAD, the difference in specificity between the two groups was statistically significant(P<0.05).@*Conclusions@#All the three risk stratification systems of thyroid ultrasound in CAD software have good diagnostic values, among which K-TIRADS has the largest AUC. The CAD software can assist ultrasound physicians to improve the thyroid nodule diagnostic performance, and has a good clinical application prospect.
RESUMEN
PURPOSE: This study aimed to assess the diagnostic efficacy of Korean Thyroid Imaging Reporting and Data System (K-TIRADS) features for distinguishing follicular thyroid adenoma (FTA) from follicular thyroid carcinoma (FTC). METHODS: From January 2013 to July 2016, 46 follicular neoplasms in 45 patients who underwent preoperative thyroid ultrasonography (US) and thyroid surgery were included. The US features of each thyroid nodule were retrospectively evaluated by a single radiologist using a picture archiving and communication system. The diagnostic indices of K-TIRADS for follicular neoplasms were calculated according to whether K-TIRADS category 4 lesions were excluded or classified as benign or malignant. RESULTS: Of the 46 follicular neoplasms (mean size, 3.1±1.6 cm), 37 were FTAs (mean size, 3.1±1.7 cm) and nine were FTCs (mean size, 3.0±1.5 cm). A statistically significant difference was found between FTAs and FTCs regarding the margin (P=0.035), while no significant differences were observed in the composition, echogenicity, shape, orientation, calcification, or vascularity of the lesions (P<0.05). The FTAs belonged to K-TIRADS categories 3 (n=22) and 4 (n=15), while the FTCs belonged to K-TIRADS categories 3 (n=4), 4 (n=4), and 5 (n=1). However, there was no statistically significant difference in the distribution of K-TIRADS categories between FTAs and FTCs (P=0.184). CONCLUSION: K-TIRADS features were not helpful for distinguishing FTA from FTC, although follicular neoplasms showed a high prevalence of K-TIRADS categories 3 and 4.