Computed tomography articles from across Nature Portfolio

Early detection and accurate diagnosis of focal liver lesions are crucial for effective treatment and prognosis. Here, the authors present a fully automated diagnostic system that leverages multi-phase CT scans and clinical features, for diagnosing liver lesions.

A novel machine-learning-derived biomarker that can detect structural changes in perivascular fat improved cardiac risk prediction beyond traditional prediction tools.

Current clinical issues in testicular germ cell tumour management include limited sensitivity and specificity of conventional biomarkers and, therefore, reliance on serial CT imaging in follow-up monitoring, as well as poor ability to risk stratify patients. Circulating microRNAs are likely to help overcome these challenges and, importantly, could offer cost savings to health-care systems.

A new trial has demonstrated the benefits of intravenous thrombolysis, guided by perfusion imaging, 4.5–9.0 h after stroke onset and in individuals with wake-up stroke. In addition to extending the time window for thrombolysis after acute ischaemic stroke, these findings could aid the refinement of imaging and thrombolytic protocols.

Retinal microvascular changes are strongly linked to prevalent and incident cardiovascular disease. These changes can now be mapped with unparalleled accuracy using retinal optical coherence tomography. Novel retinal imaging, combined with the power of deep learning, might soon equip clinicians with unique and precise risk-assessment tools that enable truly individualized patient management.