AI lung cancer screening shows promise but falls short of clinical autonomy
A systematic review and meta-analysis finds pooled sensitivity of 85.4 percent and specificity of 83.5 percent for deep learning-assisted low-dose ...
A systematic review and meta-analysis finds pooled sensitivity of 85.4 percent and specificity of 83.5 percent for deep learning-assisted low-dose ...
A multicenter retrospective study of 101 patients defines the CT, MRI and PET/CT features of primary pulmonary artery sarcoma and ...
A fine-tuned Segment Anything pipeline matched bespoke networks for thigh muscle segmentation on MRI, while radiologist-flagged errors barely changed volume ...
Researchers found that contrast-enhanced ultrasound parameters TTP and R-PI demonstrate strong diagnostic capability for identifying testicular torsion and assessing subsequent ...
A domain-specialized reasoning model called Impression-R1 matched or outperformed general-purpose AI and participating radiologists on radiological impression generation across 11,884 ...
A cross-sectional study of 60 knee osteoarthritis patients found ultrasound strongly correlated with MRI in measuring medial femoral cartilage thickness ...
A large multicentre analysis of the METRIC trial found that MR enterography and intestinal ultrasound agree well on a global ...
A three-month clinical deployment in Oslo showed that radiologist feedback through the NeoMedSys platform raised VIOLA-AI's brain bleed detection sensitivity ...
A society statement in European Radiology Breast traces EUSOBI's growth from a 1997 initiative to 2,750 members in 98 countries ...
A two-cycle audit of 640 radiology request forms from private clinics in Asaba, Nigeria, found no fully completed forms at ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine