🟣 https://www.i3-journal.org/
Social Media Editor: @cannellaroberto.bsky.social
(Jonathan P. McNulty et al.) #InsightsintoImaging
insightsimaging.springeropen.com/articles/10....
@myESR @EFRadiographerS
(Jonathan P. McNulty et al.) #InsightsintoImaging
insightsimaging.springeropen.com/articles/10....
@myESR @EFRadiographerS
🔹 Standardised, competency-based curricula aligned with evolving tech & safety standards
🔹 Structured clinical placements and mandatory CPD
🔹 Flexible learning pathways & equitable financial support for students
🔹 Expansion of postgraduate and specialised training
🔹 Standardised, competency-based curricula aligned with evolving tech & safety standards
🔹 Structured clinical placements and mandatory CPD
🔹 Flexible learning pathways & equitable financial support for students
🔹 Expansion of postgraduate and specialised training
🔹 Identified major gaps in workforce planning across EU member states
🔹 Introduces a workload-based staffing model (WISN method)
🔹 Recommends national registries and recognition of advanced & emerging roles
🔹 Aims to harmonise staffing, improve safety, and enhance patient outcomes
🔹 Identified major gaps in workforce planning across EU member states
🔹 Introduces a workload-based staffing model (WISN method)
🔹 Recommends national registries and recognition of advanced & emerging roles
🔹 Aims to harmonise staffing, improve safety, and enhance patient outcomes
✅ 67% completed the challenge in time
✅ High ratings for learning, teamwork, and enjoyment
🩻 A step-by-step guide now shows how to design these interactive, team-based learning experiences for radiology education.
(Jonas Oppenheimer et al.) #InsightsintoImaging
shorturl.at/rBzJQ
✅ 67% completed the challenge in time
✅ High ratings for learning, teamwork, and enjoyment
🩻 A step-by-step guide now shows how to design these interactive, team-based learning experiences for radiology education.
(Jonas Oppenheimer et al.) #InsightsintoImaging
shorturl.at/rBzJQ
• Shear wave velocity was the strongest predictor (AUC = 0.84)
• Combined ultrasound indices improved accuracy (AUC = 0.88)
• Matched endoscopic specificity (100%) with 71% sensitivity
(Xielu Sun et al.)
insightsimaging.springeropen.com/articles/10....
• Shear wave velocity was the strongest predictor (AUC = 0.84)
• Combined ultrasound indices improved accuracy (AUC = 0.88)
• Matched endoscopic specificity (100%) with 71% sensitivity
(Xielu Sun et al.)
insightsimaging.springeropen.com/articles/10....
🔹 Transparency (56%) is the top trust factor - more than liability or data protection
🔹 Main barriers: “black box” models, unclear accountability, privacy concerns
🔹 No major trust differences across specialties
🔹 Transparency (56%) is the top trust factor - more than liability or data protection
🔹 Main barriers: “black box” models, unclear accountability, privacy concerns
🔹 No major trust differences across specialties
(Liyun Xue et al.) #InsightsintoImaging
insightsimaging.springeropen.com/articles/10....
(Liyun Xue et al.) #InsightsintoImaging
insightsimaging.springeropen.com/articles/10....
🔹 Strong correlation with biopsy, MRI-PDFF & ¹H-MRS (ρ = 0.80–0.85)
🔹 Higher AUCs (0.91–0.95) than HSI or FLI for steatosis grading
🔹 A new dual-threshold UDFF system (≥90% sensitivity/specificity) accurately stratified disease severity
🔹 Strong correlation with biopsy, MRI-PDFF & ¹H-MRS (ρ = 0.80–0.85)
🔹 Higher AUCs (0.91–0.95) than HSI or FLI for steatosis grading
🔹 A new dual-threshold UDFF system (≥90% sensitivity/specificity) accurately stratified disease severity
👉 Even highly active lesions didn’t justify taking fewer samples.
📍 Recommendation: obtain ≥3 samples, prioritizing safety over metabolic intensity. (Mathieu Conjeaud et al.) #InsightsintoImaging
👉 Even highly active lesions didn’t justify taking fewer samples.
📍 Recommendation: obtain ≥3 samples, prioritizing safety over metabolic intensity. (Mathieu Conjeaud et al.) #InsightsintoImaging
🔹 Logistic regression–based clinical-radiomics model achieved the best performance
- AUC = 0.94 (internal) | 0.85 (external)
🔹 Combines CT radiomics + clinical data for robust prediction
🔹 Offers a noninvasive tool for early assessment of immunotherapy efficacy
🔹 Logistic regression–based clinical-radiomics model achieved the best performance
- AUC = 0.94 (internal) | 0.85 (external)
🔹 Combines CT radiomics + clinical data for robust prediction
🔹 Offers a noninvasive tool for early assessment of immunotherapy efficacy
insightsimaging.springeropen.com/articles/10....
insightsimaging.springeropen.com/articles/10....
🔹 MTV and true diffusion coefficient (D) were independent predictors
🔹 Combined PET–MRI model achieved AUC = 0.84, improving diagnostic performance
🔹 MTV and true diffusion coefficient (D) were independent predictors
🔹 Combined PET–MRI model achieved AUC = 0.84, improving diagnostic performance