Latest

5678 stories
CardiacChest / ThoracicAI / InformaticsEducationTrainee

AI and deep learning in cardiovascular imaging: risk stratification to precision phenotyping

AI and deep learning are moving cardiovascular imaging beyond visual interpretation toward integrated risk stratification and precision phenotyping, but real-world generalizability still needs further validation before guiding individual patient management.

Arteriosclerosis, thrombosis, and vascular biology
Body / AbdominalEducationTrainee

MRI for prostate cancer screening: ESUR working group insights

MRI-based prostate cancer screening detects more clinically significant cancer and reduces unnecessary biopsies; biparametric MRI is recommended as the protocol of choice, though long-term mortality data are lacking.

European radiology
Nuclear / MolecularEducationTrainee

Implementing targeted alpha therapy: safety, dosimetry, and regulatory essentials

Targeted alpha therapy (TAT) creates dense local irradiation with alpha particles (range of few cell diameters). Radium-223 has strongest clinical foundation; other alpha emitters are under study. Routine use limited by supply, dosimetry, organ toxicity (renal, salivary, marrow)…

Seminars in nuclear medicine
Nuclear / MolecularBody / AbdominalAI / InformaticsResearch

Visual Q&A model predicts survival in PSMA radiopharmaceutical therapy

Visual QA model integrating PSMA PET/SPECT and PSA predicted 24-mo survival in 110 mCRPC patients: accuracy 81.8% internally (95% CI 0.52-0.95) and 71.9% externally, AUC 0.75.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine
Body / AbdominalAI / InformaticsResearch

CT radiomics fusion model predicts pancreatic neuroendocrine tumor grade with high accuracy

CT-based radiomics fusion model integrating semantic features predicted pancreatic neuroendocrine neoplasm grading with AUC 0.891 in validation, outperforming clinical and radiomics models alone. SHAP identified zone entropy and sphericity as key predictors, reflecting lesion ag…

Cancer treatment and research communications
Musculoskeletal (MSK)AI / InformaticsResearch

Deep Learning Enables Automated 3D Hip Morphology Assessment in 2,454 Adolescents

Automated nnU-Net segmentation of hip MRI achieved Dice scores of 0.97 for femoral bone and 0.76-0.77 for cartilage, providing reference ranges for 3D morphology in 2,454 young adults (mean age 18.4y). Significant sex and BMI differences found. Code open source.

Annals of biomedical engineering
EmergencyMusculoskeletal (MSK)AI / InformaticsEducation

AI in Trauma Imaging: Evidence, Integration, and Limitations

AI in trauma imaging can show impressive performance, but evidence for a definitive assessment is insufficient; users must critically evaluate results and remain aware of the regulatory framework.

Unfallchirurgie (Heidelberg, Germany)
NewerPage 8 of 190Older