Insights Into Imaging

An MRI-derived intratumoral heterogeneity score (ITHscore) was developed to estimate 21-gene recurrence risk in ER+/HER2− breast cancer.

📊 Higher ITHscore was associated with high-risk recurrence groups
🧠 Adding ITHscore improved prediction performance (AUC up to 0.86)
📈 Model showed good generalization in an external cohort

https://link.springer.com/article/10.1186/s13244-026-02342-0 (Yang Chen et al.)

🎓 A competency-based modular training model was evaluated in radiology residency education.

📚 Interdisciplinary, disease-focused modules integrated with clinical rotations and image post-processing
📊 No overall score difference vs traditional training
👩‍⚕️ Significant improvement in non-graduate subgroup (theory and practice)

https://link.springer.com/article/10.1186/s13244-026-02335-z (Shang Wan et al.)

Ultrasound radiomics combined with clinical features improves breast lesion diagnosis in a large multicenter study.

📊 Combined model outperformed radiomics and clinical models alone (AUC up to 0.93)
📉 Potential to reduce unnecessary biopsies while maintaining diagnostic sensitivity
🧠 Stable performance across external and prospective validation cohorts

https://link.springer.com/article/10.1186/s13244-026-02344-y (Di Zhang et al.)

A multimodal CT urography model improves perioperative risk stratification in upper tract urothelial carcinoma.

📊 Fusion of clinical data, radiomics, and deep learning outperforms single-modality models
📈 Highest predictive performance achieved for 3-year overall survival (external AUC ~0.77)
🧠 2.5D deep learning adds incremental prognostic value over 2D approaches

https://link.springer.com/article/10.1186/s13244-026-02337-x (Xiang Peng et al.)

🖐️ Foveal triangular fibrocartilage complex lesions are frequently underreported on wrist arthro-computed tomography.

📊 Review identified lesions in 59% of cases, with many ulnar/foveal injuries missed in initial reports
🔍 Structured re-evaluation improved detection in 28% of cases and aligned better with surgical findings
⚠️ Foveal involvement was strongly associated with ulnar-sided wrist pain

https://link.springer.com/article/10.1186/s13244-026-02327-z (Julien Dejean-Servieres et al.)

🫁 A clinicoradiological model predicts spread through air spaces (STAS) in stage IA lung adenocarcinoma.

📊 CT features (CTR ≥90%, bronchial truncation, pleural retraction, satellite nodules) independently predict STAS
📈 Model stratifies recurrence risk with good validation performance (AUC ~0.83)
🧬 STAS-positive tumors show distinct molecular patterns

https://link.springer.com/article/10.1186/s13244-026-02339-9 (Feng Xu et al.)

🌍 Deep learning-based CT reconstruction improves environmental sustainability in high-volume imaging.

⚡ Lower electricity use and reduced CO₂e emissions compared with hybrid iterative reconstruction
🧪 Reduced iodinated contrast media consumption with protocol optimization
📉 Overall environmental impact decreased across >42,000 examinations

https://link.springer.com/article/10.1186/s13244-026-02333-1 (Paolo Niccolò Franco et al.)

4D flow MRI improves non-invasive detection of high-risk esophageal varices in liver cirrhosis.

📊 Splenic vein velocity, spleen volume, and splenic extracellular volume fraction show strong diagnostic value
📈 Combined model achieves best performance for risk stratification

https://link.springer.com/article/10.1186/s13244-026-02341-1 (Xiaohuan Li et al.)

📚 Systematic review of fat necrosis after breast reconstruction and autologous fat transfer.

🩻 Imaging features are largely similar across ultrasound, mammography, and magnetic resonance imaging
📍 Flap surgery shows more peripheral distribution vs more diffuse patterns in fat transfer
📊 Prevalence varies widely across studies

https://link.springer.com/article/10.1186/s13244-026-02330-4 (Nieke N. P. M. Smeins et al.)

In pancreatic ductal adenocarcinoma, CT-based assessment of vascular invasion was compared with surgical and histopathological findings.

📊 NCCN-derived CT criteria showed good concordance with intraoperative and histopathological venous invasion
⏱️ Agreement decreased when the interval between CT and surgery exceeded 4 weeks
🎯 Highlights the importance of standardized timing for preoperative imaging in staging

https://link.springer.com/article/10.1186/s13244-026-02318-0 (Gala Nacul Mora et al.)