#medical imaging

A study described in Gut found an AI model could flag subtle pancreatic changes in previously cleared CT scans, potentially opening a path to earlier intervention against one of the deadliest cancers.

Researchers report that pairing polarization-sensitive optical coherence tomography with AI can detect structural corneal changes linked to early keratoconus before conventional shape-based scans clearly show disease.

An analysis of two major clinical trials suggests imaging can reveal metastatic prostate cancer progression even when standard biomarkers remain unchanged during treatment.

A new radiology study finds that ultrasound’s emissions profile looks different from other imaging tools, with linens and disposable supplies accounting for most of its carbon footprint rather than the equipment itself.

Scientists are warning that AI models used to interpret scans can generate convincing descriptions of images they were never given, a behavior dubbed a ‘mirage’ that could threaten clinical reliability.

A report based on millions of medical imaging orders says Americans now wait twice as long for scan results as they did in 2014, with the sharpest recent jump arriving in the most recent period studied.

AI-enhanced colonoscopy platforms are helping gastroenterologists catch flat and sessile colon polyps that human visual inspection frequently misses, with clinical trials showing adenoma detection rates rising by roughly 10 percentage points.