On 76 test cases, the AI framework achieved Cobb angle MAE 2.4°, Lenke curve type accuracy 0.895, and reduced review time from 8.2 to 1.5 min/case.
PSAD remained below 0.11 ng/mL² across all ages in 1037 healthy German men, contrasting with continuously rising PSA. 95th percentile reference: PV 51.39 mL, PSA 2.79 ng/mL, PSAD 0.071 ng/mL².
Noncontrast CT-based unimodal imaging AI detected anterior circulation large vessel occlusion with sensitivity 0.78 (95% credible interval 0.68-0.86) and specificity 0.88, versus expert readers' sensitivity 0.62 and similar specificity; low-certainty retrospective evidence.
SIR Foundation research consensus panel calls for standardized acute DVT intervention endpoints: biologically informed patient selection, anatomic/physiologic metrics, validated severity tools, longitudinal biomarkers, and economic/QoL measures to advance precision and reduce po…
A multimodal deep learning model combining MRI and clinical features predicted positive surgical margins after radical prostatectomy with an AUC of 0.843 (95% CI 0.770-0.911) in an external validation cohort of 155 patients from six centers, outperforming imaging-only and clinic…
Radiomic scores from cardiac MRI T1 and ECV maps had an AUC of 0.834 and 0.718, respectively, for predicting left ventricular reverse remodeling in dilated cardiomyopathy, improving AUC of late gadolinium enhancement from 0.618 to 0.903 when combined.
In early CKD detection, multiparametric MRI combining all four sequences (T1WI, DWI, T1 mapping, BOLD) achieved AUC 0.866. DWI alone had AUC 0.874; T1WI+DWI balanced performance and feasibility (accuracy 0.844, F1 0.815).
An AI-supported workflow increased patient notification of incidental pulmonary nodules from 75% to 88.4% (p=0.0001) and follow-up from 53.5% to 67.9% (p=0.0012) in the ED.
A denoising autoencoder restored CT perfusion image quality at up to 90% simulated radiation dose reduction (SSIM 0.81, PSNR 43 dB) and reduced infarct core volume error from 10-30 mL to 4-16 mL, with high agreement (R²>0.85).
AI can improve radiation protection in medical imaging and radiotherapy through referral support, image reconstruction, and QA, but data bias and opaque models necessitate robust validation and AI literacy training, per an ICRP Committee 3 perspective.
AI models detect acute Type A aortic dissection on CT with AUC 0.86 to 0.99 and sensitivity 91% to 97%, but direct evidence that they reduce door-to-surgery time or mortality is lacking. Simulated workflows cut report times 26% to 43%.
Multiparametric MRI with VI-RADS reliably separates muscle-invasive from non-muscle-invasive bladder cancer, but clinical utility hinges on quality control, reducing reader variability, and integrating AI—this review covers implementation, post-treatment response, and AI solutio…
RSNA launches Imaging Sustainability Challenge
MRI basics: T1 and T2 WI overview
WHO report: 20.6M cancer diagnoses in 2024 (+7% vs 2020). 23 low- and middle-income countries have no radiotherapy; 47% lack basic diagnostics. Breast cancer 5-year survival in high-income countries 4× that of sub-Saharan Africa (39%).
Cancer Imaging Education Cape Town
Making Mentorship More Accessible | RSNA Unscripted with Federica Vernuccio, MD, PhD
Ultrasound MinnieCast, Episode 13: Who owns echocardiography?
<![CDATA[Can the Combination of Photon-Counting CT and AI Change Our Approach to CAC Scoring?]]>
Multimodal Diagnostic Cross-Check: A Correlative Study of Fine-Needle Aspiration Cytology, Ultrasonography, Thyroid Profile, and Histopathology in Thyroid Swellings
Dementia - Role of MRI - 2026 update
Radiology AI marketplace CARPL.ai raised $10M in Series A funding led by IFC. The platform offers 300+ apps from 100+ AI partners and is used by 4 of the 5 top radiology groups. Funds will fuel product development and North American expansion.
NRC Proposes Major Changes to Medical Use Regulations
DHS Finalizes Fixed Admission Periods for J-1 Visa Holders
Facebook Live: CT of Liver Abscesses
ACR Releases Impact Tables for 2027 MPFS Proposed Rule
House Committees Advance Healthcare Transparency Bills
Federal Guidance Standardizes IDR Eligibility Codes
Multimodal ML model integrating CT radiomics and clinical features predicted ILD with AUC 0.715 (95% CI 0.661–0.770) on external validation (614 patients) and 0.733 on internal validation.
An 81-expert Chinese panel reached consensus (scores 8.06–8.58 on 9-point scale) on 30 statements covering AI applications from cancer screening to post-deployment surveillance. Recommendations include expert-supervised labeling, multicenter validation, interpretable outputs, an…
Graph-based white matter tractometry preserves spatial topology and detects distributed pathology patterns. A systematic maturity assessment finds modest improvements over traditional methods, but comprehensive benchmarking against TBSS and AFQ is absent, and validation platform…
A review proposes a shift from FDG-PET to multimodal molecular-structural fusion using novel PET tracers targeting synaptic density, neuroinflammation, and neurotransmitter systems, integrated with isotropic 3D MRI and AI coregistration, to improve surgical localization of epile…
A Vision Transformer-based nomogram using serial grayscale ultrasound images predicted 3-year graft-related adverse event-free survival with an AUC of 0.831 in external validation, outperforming a clinical model (AUC 0.808, p=0.048). A hepatic artery resistive index <0.55 within…
