Ji-Young Hwang

This study was conducted to investigate and compare thyroid ultrasonography (US) findings in children and adolescents with goiter and normal thyroid function with positive or negative thyroid autoimmunity. From 2000 to 2020, we reviewed initial thyroid US images in 33 autoimmune thyroid diseases (AITDs) patients and 52 nonAITD patients. Our review of the images focused on thyroid parenchymal hypoechogenicity and heterogeneous echopattern subdivided into 2 groups according to severity: hypoechogenicity 1 and 2 (HO1 and HO2) and heterogeneity 1 and 2 (HE1 and HE2). HO1 and HE1 were observed more frequently in the nonAITD group (86.5% and 42.3%, respectively), while HO2 and HE2 were observed more frequently in the AITDs group (36.4% and 81.8%, respectively). More patients in the AITDs group showed change of both US groups and thyroid function state within the follow-up periods than in nonAITD group (33.3% and 5.77%, respectively). Children and adolescent AITDs patients showed more severe parenchyma hypoechogenicity and heterogeneous echopattern compared with nonAITD patients with goiter and normal thyroid function.

Purpose: This study evaluated how artificial intelligence-based computer-assisted diagnosis (AICAD) for breast ultrasonography (US) influences diagnostic performance and agreement between radiologists with varying experience levels in different workflows.Methods: Images of 492 breast lesions (200 malignant and 292 benign masses) in 472 women taken from April 2017 to June 2018 were included. Six radiologists (three inexperienced [<1 year of experience] and three experienced [10-15 years of experience]) individually reviewed US images with and without the aid of AI-CAD, first sequentially and then simultaneously. Diagnostic performance and interobserver agreement were calculated and compared between radiologists and AI-CAD.Results: After implementing AI-CAD, the specificity, positive predictive value (PPV), and accuracy significantly improved, regardless of experience and workflow (all P<0.001, respectively). The overall area under the receiver operating characteristic curve significantly increased in simultaneous reading, but only for inexperienced radiologists. The agreement for Breast Imaging Reporting and Database System (BI-RADS) descriptors generally increased when AI-CAD was used (κ=0.29-0.63 to 0.35-0.73). Inexperienced radiologists tended to concede to AI-CAD results more easily than experienced radiologists, especially in simultaneous reading (P<0.001). The conversion rates for final assessment changes from BI-RADS 2 or 3 to BI-RADS higher than 4a or vice versa were also significantly higher in simultaneous reading than sequential reading (overall, 15.8% and 6.2%, respectively; P<0.001) for both inexperienced and experienced radiologists.Conclusion: Using AI-CAD to interpret breast US improved the specificity, PPV, and accuracy of radiologists regardless of experience level. AI-CAD may work better in simultaneous reading to improve diagnostic performance and agreement between radiologists, especially for inexperienced radiologists.

김종희, et al. J Korean Soc Radiol. 2021 Aug;82:e116. https://doi.org/10.3348/jksr.2021.0011

Park M, et al. J Korean Soc Radiol. 2016 May;74(5):331-334. http://dx.doi.org/10.3348/jksr.2016.74.5.331