ABSTRACT Objective To compare the diagnostic accuracy of the IOTA Simple Rules for classifying adnexal masses when applied by expert versus nonexpert ultrasound operators, and to assess whether diagnostic performance is maintained across different levels of examiner experience. Methods A systematic review and meta‐analysis was performed according to PRISMA‐DTA guidelines. PubMed, Scopus, and Embase were searched for studies evaluating the IOTA Simple Rules with histopathology as the reference standard. Studies were stratified by operator experience: experts (IOTA‐trained subspecialists) and nonexperts (general gynecologists or trainees). Pooled sensitivity, specificity, likelihood ratios, diagnostic odds ratios, and HSROC curves were calculated using a bivariate random‐effects model. Heterogeneity was quantified using I 2 and Q statistics, and publication bias was assessed. Results Thirty studies (25 with expert and 11 with nonexpert examiners) were included, encompassing adnexal masses with a mean malignancy prevalence of 27%. Among expert operators, pooled sensitivity and specificity were 0.90 (95% CI 0.86–0.92) and 0.93 (95% CI 0.91–0.95), respectively, with an AUC of 0.96. Among nonexpert operators, pooled sensitivity and specificity were 0.88 (95% CI 0.82–0.92) and 0.92 (95% CI 0.86–0.96), with an AUC of 0.95. Diagnostic odds ratios were 118 for experts and 86 for nonexperts. Differences in accuracy between groups were nonstatistically significant and, therefore, clinically negligible. Using an estimated prevalence of 27%, the positive posttest probability was 84% for experts and 81% for nonexperts, while the negative posttest probability was 4% and 5%, respectively. No significant publication bias was detected. Conclusion The IOTA Simple Rules demonstrate excellent diagnostic accuracy when used by both expert and nonexpert operators, with only minor differences in performance. These findings confirm that the Simple Rules are reproducible, robust and transferable across different clinical experience levels, supporting their role as an accessible and reliable triage tool for adnexal mass assessment, including outside tertiary referral centers.

ABSTRACTIntroductionIsolated abdominal aortic dissection (IAAD) has been reported to account for 1.1%–4.1% of all aortic dissections. If detected late, it is associated with a risk of aortic rupture. We investigated the risk factors and characteristic imaging findings of incidentally discovered IAAD using abdominal ultrasonography (AUS) during health check‐up and hereby report our findings.MethodsThe study sample included 41 patients with abdominal aortic abnormalities identified by AUS performed during a health check‐up at our hospital and who were diagnosed with IAAD by contrast‐enhanced computed tomography (CT); in addition, 205 patients were included in the nonevent group. Furthermore, risk factors and characteristic imaging findings of IAAD were examined retrospectively.ResultsCompared with the nonevent group, smoking and fatty liver were observed significantly more frequently in the IAAD group. Ultrasound findings indicated an intimal flap in 35 cases (85.4%), whereas CT scan revealed displacement of intimal calcifications in 32 cases (78.0%).ConclusionCompared with the nonevent group, there were significantly more cases of fatty liver and smoking habits in the IAAD group. In older patients with risk factors for fatty liver and smoking habits, if IAAD is suspected, it is important to monitor the abdominal aorta using ultrasonography during health check‐ups.

Radiomics-based eXtreme gradient boosting (XGBoost) model was developed to differentiate benign thyroid nodules from malignant thyroid nodules and to prevent unnecessary thyroid biopsies, including positive and negative effects. The study evaluated a data set of ultrasound images of thyroid nodules in patients retrospectively, who initially received ultrasound-guided fine-needle aspiration biopsy (FNAB) for diagnostic purposes. According to ACR TI-RADS, a total of five ultrasound feature categories and the maximum size of the nodule were determined by four radiologists. A radiomics score was developed by the LASSO algorithm from the ultrasound-based radiomics features. An interpretative method based on Shapley additive explanation (SHAP) was developed. XGBoost was compared with ACR TI-RADS for its diagnostic performance and FNAB rate and was compared with six other machine learning models to evaluate the model performance. Finally, 191 thyroid nodules were examined from 177 patients. The radiomics score were calculated using 8 features, which were selected among 789 candidate features generated from the ultrasound images. The model yielded an AUC of 93% in the training cohort and 92% in the test cohort. It outperformed traditional machine learning models in assessing the nature of thyroid nodules. Compared with ACR TI-RADS, the FNAB rate decreased from 34% to 30% in training and from 35% to 41% in test. The radiomics-based XGBoost model proposed could distinguish benign and malignant thyroid nodules, thereby reduced significantly the number of unnecessary FNAB. It was effective in making preoperative decisions and managing selected patients using the SHAP visual interpretation tools.

Explore the feasibility of using the multimodal ultrasound (US) radiomics technology to diagnose American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) 4-5 thyroid nodules. This study prospectively collected the clinical characteristics, conventional, and US elastography images of 100 patients diagnosed with ACR TI-RADS 4-5 nodules from May 2022 to 2023. Independent risk factors for malignant thyroid nodules were extracted and screened using methods such as the least absolute shrinkage and selection operator (LASSO) logistic regression (LR) model, and a multimodal US radiomics combined diagnostic model was established. Using a multifactorial LR analysis and a Rad-score rating, the predictive performance was validated and evaluated, and the final threshold range was determined to assess the clinical net benefit of the model. In the training set, the US radiomics combined predictive model area under curve (AUC = 0.928) had higher diagnostic performance compared with clinical characteristics (AUC = 0.779), conventional US (AUC = 0.794), and US elastography model (AUC = 0.852). In the validation set, the multimodal US radiomics combined diagnostic model (AUC = 0.829) also had higher diagnostic performance compared with clinical characteristics (AUC = 0.799), conventional US (AUC = 0.802), and US elastography model (AUC = 0.718). Multi-modal US radiomics technology can effectively diagnose thyroid nodules of ACR TI-RADS 4-5, and the combination of radiomics signature and conventional US features can further improve the diagnostic performance.