Radiology

New deep learning model combining X-ray and MRI data shows promise in increasing efficiency of cervical spondylosis diagnosis.

An estimated 72% to 94% of cases were overdiagnosed in the USA between 1991 and 2019, according to a 2026 study.

Women experience unique changes in brain structure after a second pregnancy, MRIs revealed in a 2026 cohort study.

Integrated PET and MRI scans can distinguish a new type of dementia, LATE, from Alzheimer’s, a 2026 observational study has found.

Fused Deposition Modelling 3D printing has become a practical, accessible, and cost-effective tool in surgical settings, a 2026 systematic review has found.

AI can predict postoperative breast cancer recurrence using preoperative mammograms, a 2026 study has found.

A new AI model was able to read and diagnose brain MRI scans in seconds, researchers at the University of Michigan have found.

Mammographic surveillance and adjunct imaging techniques can lower morality and enhance early detection among breast cancer survivors.

AI-prefilled structured reporting improves diagnostic accuracy in chest radiograph reporting compared with free-text reporting, a 2026 prospective reader study has found.

MRI-based radiomics models may help predict tumour deposit burden in rectal cancer, with a fusion AI approach outperforming radiologists in preoperative risk assessment.

Computer-aided detection chest X-ray performed comparably to experienced radiologists for pulmonary tuberculosis diagnosis, supporting its potential role in low-resource, high-burden clinical settings.

A deep-learning serial CT biomarker accurately predicts overall survival in immunotherapy-treated NSCLC, outperforming RECIST in large real-world and trial cohorts.

Medical societies warn that flawed studies may deter patients from lung cancer screening despite clear survival benefits.

Ultra-high-field 5 T MRI delivers improved image quality and diagnostic accuracy compared with 3 T MRI for prostate cancer, according to a prospective intra-individual study.

New stainless steel neural probes promise safer deep brain sensing, reducing fracture risk while supporting high-resolution recordings for research and surgery.

The new analysis draws on the prospective MALRIC study, including patients treated between 2009 and 2024 across 10 hospitals