Ultrasonography (US) is a primary imaging modality for diagnosing nodular thyroid disease and has an essential role in identifying the most appropriate management strategy for patients with nodular thyroid disease. Standardized imaging techniques and reporting formats for thyroid US are necessary. For this purpose, the Korean Society of Thyroid Radiology (KSThR) organized a task force in June 2021 and developed recommendations for standardized imaging technique and reporting format, based on the 2021 KSThR consensus statement and recommendations for US-based diagnosis and management of thyroid nodules. The goal was to achieve an expert consensus applicable to clinical practice.

Objective: To assess the contrast-enhanced CT and ultrasonography (US) findings of intracholecystic papillary neoplasm (ICPN) and determine the imaging features predicting ICPN associated with invasive carcinoma (ICPN-IC). Materials and Methods: In this retrospective study, we enrolled 119 consecutive patients, including 60 male and 59 female, with a mean age ± standard deviation of 63.3 ± 12.1 years, who had pathologically confirmed ICPN (low-grade dysplasia [DP] = 34, high-grade DP = 35, IC = 50) and underwent preoperative CT or US. Two radiologists independently assessed the CT and US findings, focusing on wall and polypoid lesion characteristics. The likelihood of ICPN-IC was graded on a 5-point scale. Univariable and multivariable logistic regression analyses were performed to identify significant predictors of ICPN-IC separately for wall and polypoid lesion findings. The performances of CT and US in distinguishing ICPN-IC from ICPN with DP (ICPN-DP) was evaluated using the area under the receiver operating characteristic curve (AUC). Results: For wall characteristics, the maximum wall thickness (adjusted odds ratio [aOR] = 1.4; 95% confidence interval [CI]: 1.1-1.9) and mucosal discontinuity (aOR = 5.6; 95% CI: 1.3-23.4) on CT were independently associated with ICPN-IC. Among 119 ICPNs, 110 (92.4%) showed polypoid lesions. Regarding polypoid lesion findings, multiplicity (aOR = 4.0; 95% CI: 1.6-10.4), lesion base wall thickening (aOR = 6.0; 95% CI: 2.3-15.8) on CT, and polyp size (aOR = 1.1; 95% CI: 1.0-1.2) on US were independently associated with ICPN-IC. CT showed a higher diagnostic performance than US in predicting ICPN-IC (AUC = 0.793 vs. 0.676; p = 0.002). Conclusion: ICPN showed polypoid lesions and/or wall thickening on CT or US. A thick wall, multiplicity, presence of wall thickening in the polypoid lesion base, and large polyp size are imaging findings independently associated with invasive cancer and may be useful for differentiating ICPN-IC from ICPN-DP.

Objective: To develop and test a machine learning model for classifying human papillomavirus (HPV) status of patients with oropharyngeal squamous cell carcinoma (OPSCC) using ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET-derived parameters in derived parameters and an appropriate combination of machine learning methods in patients with OPSCC. Materials and Methods: This retrospective study enrolled 126 patients (118 male; mean age, 60 years) with newly diagnosed, pathologically confirmed OPSCC, that underwent ¹⁸F-FDG PET-computed tomography (CT) between January 2012 and February 2020. Patients were randomly assigned to training and internal validation sets in a 7:3 ratio. An external test set of 19 patients (16 male; mean age, 65.3 years) was recruited sequentially from two other tertiary hospitals. Model 1 used only PET parameters, Model 2 used only clinical features, and Model 3 used both PET and clinical parameters. Multiple feature transforms, feature selection, oversampling, and training models are all investigated. The external test set was used to test the three models that performed best in the internal validation set. The values for area under the receiver operating characteristic curve (AUC) were compared between models. Results: In the external test set, ExtraTrees-based Model 3, which uses two PET-derived parameters and three clinical features, with a combination of MinMaxScaler, mutual information selection, and adaptive synthetic sampling approach, showed the best performance (AUC = 0.78; 95% confidence interval, 0.46-1). Model 3 outperformed Model 1 using PET parameters alone (AUC = 0.48, p = 0.047) and Model 2 using clinical parameters alone (AUC = 0.52, p = 0.142) in predicting HPV status. Conclusion: Using oversampling and mutual information selection, an ExtraTree-based HPV status classifier was developed by combining metabolic parameters derived from ¹⁸F-FDG PET/CT and clinical parameters in OPSCC, which exhibited higher performance than the models using either PET or clinical parameters alone.

As the majority of incidentally detected lesions in the anterior mediastinum is small nodules with soft tissue appearance, the differential diagnosis has typically included thymic neoplasm and prevascular lymph node, with benign cyst. Overestimation or misinterpretation of these lesions can lead to unnecessary surgery for ultimately benign conditions. Diagnosing mediastinal cysts using MRI serves as a problem-solving modality in distinguishing between surgical and nonsurgical anterior mediastinal lesions. The pitfalls of MRI evaluation for anterior mediastinal cystic lesions are as follows: first, we acknowledge the limitation of T2-weighted images for evaluating benign cystic lesions. Due to variable contents within benign cystic lesions, such as hemorrhage, T2 signal intensity may be variable. Second, owing to extensive necrosis and cystic changes, the T2 shine-through effect may be seen on diffusion-weighted images (DWI), and small solid portions might be missed on enhanced images. Therefore, both enhancement and DWI with apparent diffusion coefficient values should be considered. An algorithm will be suggested for the diagnostic evaluation of anterior mediastinal cystic lesions, and finally, a management strategy based on MRI features will be suggested.