Intracranial hemorrhage (ICH) is a neurological emergency with high mortality rates requiring timely diagnosis. While computed tomography (CT) remains the gold standard, diagnostic accuracy varies with radiologist experience and workload. This systematic review and meta-analysis aims to evaluate the diagnostic performance of AI algorithms in detecting ICH on CT imaging and to explore key considerations for their clinical implementation in emergency and teleradiology settings. We conducted a systematic review and meta-analysis following PRISMA-DTA guidelines, searching seven databases up to May 2025. Studies evaluating AI diagnostic accuracy for ICH detection on non-contrast CT scans were included. Quality assessment used QUADAS-2 criteria. Pooled estimates were calculated using random-effects models, with subgroup analyses by algorithm architecture and ICH subtype. A total of 45 studies met the inclusion criteria, comprising 29 research algorithm evaluations (n = 185,847 patients) and 16 studies of commercial AI system implementations (n = 94,523 patients). Research algorithms demonstrated a pooled sensitivity of 0.890 (95 % CI: 0.839–0.942) and specificity of 0.926 (95 % CI: 0.899–0.954). Commercial AI systems exhibited slightly superior performance, with sensitivity of 0.899 (95 % CI: 0.858–0.940) and specificity of 0.951 (95 % CI: 0.928–0.974). Diagnostic accuracy varied notably across ICH subtypes, with epidural hemorrhage presenting the greatest detection challenge (difficulty score: 0.251). Among algorithmic designs, convolutional recurrent neural networks (CNN-RNNs) demonstrated the highest diagnostic performance. In real-world clinical implementation, AI integration demonstrated substantial workflow improvements: door-to-treatment decision time reduced by 26 % (92 → 68 min), critical case notification time decreased by 57 % (75 → 32 min), and triage accuracy improved by 8 % (86 %→94 %), directly impacting patient care pathways. Despite a 7–8 % sensitivity reduction compared to benchmark settings, these clinical benefits were consistent across implementations. AI algorithms demonstrate strong diagnostic performance in detecting ICH, with commercial systems demonstrating superior specificity compared to research models. Despite notable performance gaps in detecting certain hemorrhage subtypes, particularly epidural hemorrhage, the clinical benefits of AI integration, including improved workflow efficiency and reduced time to treatment decisions, are substantial. Future research should prioritize prospective validation and the development of algorithms tailored to enhance detection across challenging ICH subtypes.

Background/Objectives: Ultrasound shear-wave elastography (SWE) enables quantitative assessment of tissue stiffness and may provide a non-invasive biomarker of carotid plaque vulnerability. This study aimed to evaluate the ability of SWE to differentiate symptomatic from asymptomatic carotid plaques and to assess its reproducibility. Methods: A systematic search of PubMed, Web of Science, EMBASE, and the Cochrane Library was conducted in the last ten years until January 2026 for publications evaluating carotid plaques using ultrasound SWE. Inclusion criteria required original publications that used quantitative ultrasound SWE parameters for the evaluation of carotid plaque in symptomatic and asymptomatic patients and/or investigated the reproducibility of SWE parameters for carotid plaques; non-carotid studies, non-original articles, and studies not comparing symptomatic versus asymptomatic plaques or not reporting reproducibility were excluded. Fourteen studies comprising 1781 carotid plaques were included. Quantitative SWE measurements were meta-analyzed using random effects. Differences between symptomatic and asymptomatic plaques were assessed using standardized mean differences (SMDs). The reproducibility of SWE measurements was evaluated using pooled correlation coefficients. Publication bias was evaluated using funnel plots and Egger’s regression test. Results: Ten studies including 1246 plaques compared SWE stiffness between symptomatic (n = 472) and asymptomatic plaques (n = 774). The meta-analysis demonstrated significantly lower stiffness values in symptomatic plaques compared with asymptomatic plaques (SMD −1.10, p < 0.001). Reproducibility analysis of correlation coefficients extracted from seven studies demonstrated excellent agreement for SWE measurements (r = 0.92, n = 602). Heterogeneity was observed across the included studies. No statistically significant evidence of publication bias was detected. Conclusions: Ultrasound SWE is a promising approach for assessing carotid plaque vulnerability, with lower SWE stiffness observed in symptomatic plaques compared to asymptomatic plaques. This finding should be interpreted with consideration of methodological heterogeneity and the cross-sectional nature of the available assessed evidence. Further prospective studies with standardized imaging protocols and longitudinal follow-up are needed to determine clinically applicable stiffness thresholds and evaluate the prognostic value of ultrasound SWE in cerebrovascular risk stratification.

Objective: Accurate localization of epileptogenic foci remains of significant importance for surgical planning in drug‐resistant epilepsy. Multiple neuroimaging modalities are available; however, their comparative diagnostic performance lacks comparative detailed synthesis. This systematic review aimed to evaluate and compare the diagnostic accuracy of structural MRI, PET imaging, SPECT/SISCOM, and combined multimodal strategies for epileptogenic focus localization. Methods: We conducted a systematic review following PRISMA 2020 guidelines, searching PubMed, Scopus, Google Scholar, Cochrane Library, and Web of Science databases up to May 30, 2025. Studies evaluating the diagnostic performance of neuroimaging modalities for epilepsy focus localization with surgical correlation were included. Data extraction focused on sensitivity, specificity, and clinical manner. Quality assessment used QUADAS‐2 criteria. Results: Fifteen studies included a total of 1157 patients that met inclusion criteria. Combined multimodal strategies integrating two or more imaging modalities demonstrated the highest diagnostic performance (sensitivity 82–100%), followed by structural MRI in lesional epilepsy (72–100% sensitivity). PET imaging showed consistent performance across clinical contexts (33–89% sensitivity), while SPECT/SISCOM exhibited variable results (33–83% sensitivity). Strong complementarity existed between MRI and PET (85% concordance), with context‐dependent optimization for lesional versus non‐lesional epilepsy. Significance: Combined multimodal neuroimaging provides superior diagnostic performance for epileptogenic focus localization. Clinical context significantly impacts the modality selection, with MRI prioritized in lesional cases and functional imaging essential for MRI‐negative epilepsy. These findings support evidence‐based imaging protocols for surgical epilepsy evaluation. Plain Language Summary: This systematic review evaluated which brain imaging techniques are best for finding the exact location where seizures start in people with drug‐resistant epilepsy who need surgery. The researchers analyzed 15 studies involving 1157 patients. They found that using multiple imaging techniques together (combining structural and functional imaging) provides the most accurate results, with success rates of 82–100%. Standard MRI scans work very well (72–100% accuracy) when there is a visible brain abnormality causing seizures. However, for patients whose MRI looks normal, additional functional imaging techniques like PET or SPECT scans are crucial, achieving 63–89% accuracy. The study shows that the best imaging approach depends on the individual patient's situation: MRI should be used first when a brain lesion is suspected, but functional imaging becomes essential when MRI does not show anything abnormal. These findings help doctors choose the right combination of imaging tests for each patient to improve surgical planning and outcomes.

Digital tomosynthesis (DTS) of the chest is a relatively modern modality, based on conventional X-ray techniques, which allows superior visualization of anatomical structures and pathological findings in multiple sections that would otherwise be seen in the same projection in a standard posterior-anterior chest X-ray.^1,2 The ability to isolate small structures is ideal for the visualization of lung nodules. A lung nodule is a relatively well-defined approximately rounded opacity measuring up to 3 cm in diameter within the lung parenchyma.³ It is known that nodule size, morphology, nodule location, and nodule growth rate are characteristics associated with the risk of malignancy.⁴ Consequently, nodule size estimate is an important factor in nodule assessment in all major recommended algorithms.^{5 – 7}

Pulmonary nodule prevalence at chest CT was approximately the same among a middle-aged population from the Swedish CArdioPulmonary bioImage Study (known as SCAPIS), regardless of smoking history.

Background: Metabolic dysfunction–associated steatotic liver disease (MASLD) is a common metabolic liver condition primarily managed through lifestyle modification. Obeticholic acid (OCA), a farnesoid X receptor agonist, has shown therapeutic benefits in steatohepatitis, yet its short‐term metabolic effects remain unclear. This study compared OCA plus lifestyle modification versus lifestyle intervention alone in adults with MASLD. Methods: This quasi‐experimental study included 360 adults aged 18–60 years with ultrasound‐diagnosed MASLD and insulin resistance (HOMA − IR > 2.0). Patients with diabetes mellitus, viral hepatitis, cirrhosis, advanced fibrosis, ischemic heart disease or LDL − C > 160 mg/dL were excluded. Participants received either OCA (10 mg/day) plus standardised lifestyle modification or lifestyle intervention alone for 3 months. Anthropometric, biochemical and hepatic parameters were evaluated at baseline and follow‐up, with ANCOVA performed to adjust for baseline covariates. Results: Baseline demographic and metabolic characteristics were comparable between groups. After 3 months, the OCA plus lifestyle group demonstrated significantly greater improvements in ALT (36.65 ± 20.57 vs. 48.19 ± 21.35 U/L; p < 0.001), fatty liver index (55.99 ± 12.60 vs. 63.08 ± 11.89; p < 0.001) and HEPAMET score (0.33 ± 0.13 vs. 0.41 ± 0.13; p < 0.001), along with a greater reduction in body weight (77.28 ± 12.07 kg vs. 80.19 ± 12.37 kg; p = 0.024). Postintervention HOMA‐IR was significantly lower with OCA plus lifestyle than lifestyle alone (2.46 ± 0.92 vs. 2.96 ± 1.06; mean difference 0.50; p < 0.001). LDL‐C increased significantly in the OCA group (139.50 ± 15.74 mg/dL vs. 131.96 ± 16.36 mg/dL; p < 0.001). Conclusion: Over 3 months, OCA combined with lifestyle modification improved liver enzymes, steatosis and fibrosis‐related surrogate indices, and modestly reduced insulin resistance. Careful lipid monitoring is recommended, and longer term studies are required to clarify the overall metabolic and cardiovascular implications.