Radiomics machine learning models for lung cancer early diagnosis in heterogenous multicentre chest CT data: LIBRA study results.

Benjamin Hunter^1,2, Prashanthi Ratnakumar³, Daniel Tong², Nishanthi Senthivel², Amyn Bhamani⁴, Abigail Coe⁵, Susannah Bloch³, Samuel V Kemp⁶, Simon Doran⁷, Neal Navani⁴, Arjun Nair⁴, Jonathan Ratoff⁵, Claire E Wells⁵, Justin Garner⁸, Andrew Nicolson⁸, Catey Bunce², Matthew Blackledge⁷, Anand Devaraj^1,8, Eric O Aboagye¹, Richard W Lee^9,10,11

¹Imperial College London, London, England.

²The Royal Marsden NHS Foundation Trust, London, England.

³Imperial College Healthcare Trust, London, England.

⁴University College London Hospitals NHS Foundation Trust, London, England.

⁵Epsom and St Helier University Hospitals NHS Trust, Surrey, England.

⁶Nottingham University Hospitals NHS Foundation Trust, Nottingham, England.

⁷The Institute of Cancer Research, London, England.

⁸The Royal Brompton and Harefield Hospitals, Guy's and St Thomas's NHS Foundation Trust, London, England.

⁹Imperial College London, London, England. Richard.lee@rmh.nhs.uk.

¹⁰The Royal Marsden NHS Foundation Trust, London, England. Richard.lee@rmh.nhs.uk.

¹¹The Institute of Cancer Research, London, England. Richard.lee@rmh.nhs.uk.

PubMed DOI

Abstract

OBJECTIVE: We developed and validated radiomics models for lung cancer prediction in indeterminate pulmonary nodules that retain performance in heterogenous data from multiple centres. MATERIALS AND METHODS: The retrospective Lung Imaging Biobank for Radiomics and AI (LIBRA) study recruited 1,026 patients (2,071 computed tomography scans) with 5-to-30-mm lung nodules from seven UK hospitals (01/0…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.