{"entity":{"id":"radiomics","kind":"technology","name":"Radiomics","aka":[],"tldr":"Turning ordinary CT, MRI and PET scans into hundreds of measured features of shape and texture that computers relate to tumour biology and outcome.","summary":"Radiomics, a term coined in 2012, extracts quantitative descriptors of intensity, shape and texture from medical images and links them to diagnosis, prognosis or treatment response. Radiogenomics goes a step further by relating imaging phenotypes to tumour mutations and expression. Reproducibility across scanners and protocols has been the main obstacle, addressed by the Image Biomarker Standardisation Initiative and by deep-learning models trained end to end.","status":"emerging","asOf":"2026-09-04","wikipedia":"https://en.wikipedia.org/wiki/Radiomics","links":[{"label":"Wikipedia","url":"https://en.wikipedia.org/wiki/Radiomics"}],"tags":[],"related":[],"cancers":[],"sections":["imaging","ai-computation"],"technologies":["low-dose-ct-screening"],"targets":[],"drugs":[],"companies":[],"institutions":[],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"notes":[],"principle":"Segment the tumour, compute standardised feature sets or learned representations, then fit predictive models validated on external cohorts.","strengths":["Uses images already acquired in routine care","Whole-tumour and longitudinal view without a biopsy","Can complement genomics where tissue is scarce"],"limitations":["Features vary with scanner and reconstruction","Many published signatures fail external validation","Few prospective trials"]},"route":"/technologies/radiomics/","neighbours":{"section":[{"id":"ai-computation","kind":"section","name":"AI & Computation","route":"/fronts/ai-computation/"},{"id":"imaging","kind":"section","name":"Imaging","route":"/fronts/imaging/"}],"technology":[{"id":"low-dose-ct-screening","kind":"technology","name":"Low-dose CT lung screening","route":"/technologies/low-dose-ct-screening/"}]}}