Lung Nodule Imaging Biobank for Radiomics and AI Research (LIBRA)

This study will collect retrospective CT scan images and clinical data from participants with incidental lung nodules seen in hospitals across London. The investigators will research whether machine learning can be used to predict which participants will develop lung cancer, to improve early diagnosis.

Study Overview

• Status: Recruiting
• Conditions: Lung Neoplasms; Lung Cancer; Pulmonary Nodule, Solitary; Pulmonary Nodule, Multiple
• Intervention / Treatment: Diagnostic test: Machine Learning Classification

• Study Type: Observational
• Enrollment (Anticipated): 1000

Contacts and Locations

• Study Contact: Name: Richard Lee, MBBS PhD; Phone Number: 020 7352 8171; Email: richard.lee@rmh.nhs.uk

Study Locations

• United Kingdom
  • London, United Kingdom, NW1 2PG
    • Recruiting
    • University College London Hospitals NHS Foundation Trust
    • Contact: Dr Neal Navani; Email: neal.navani@uclh.nhs.uk
  • London, United Kingdom, SW3 6NP
    • Recruiting
    • The Royal Brompton NHS Foundation Trust
    • Contact: Anand Deveraj; Phone Number: 020 7352 8121; Email: A.Devaraj@rbht.nhs.uk
    • Principal Investigator: Dr Anand Deveral
  • England
    • Sutton, England, United Kingdom, SM2 5PT
      • Recruiting
      • Royal Marsden - Surrey
      • Contact: Benjamin Hunter; Email: benjamin.hunter@rmh.nhs.uk
  • Greater London
    • London, Greater London, United Kingdom, SE6 4JH
      • Recruiting
      • Lewisham and Greenwich NHS Trust
      • Contact: Dr Shafick Gareeboo; Email: shafick.gareeboo@nhs.net
      • Principal Investigator: Shafick Gareeboo
  • Surrey
    • Carshalton, Surrey, United Kingdom, SM5 1AA
      • Not yet recruiting
      • Epsom and St Helier's Hospitals NHS Trust
      • Contact: Jonathon Ratoff; Email: Jonathan.ratoff@nhs.net
      • Principal Investigator: Jonathon Ratoff

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

Patients with previously identified lung nodules.

Description

Inclusion Criteria:

• Age > 18
• Baseline CT thorax imaging reported as having pulmonary nodule(s) between 5 and 30mm in the last 10 years.
• Ground truth known (either scan data showing stability for 2 years (based on diameter) or one year (based on volumetry), complete resolution, or biopsy-proven malignancy.
• Slice thickness < 2.5mm.

Exclusion Criteria:

• • Absence of at least one technically adequate CT thorax imaging series (defined by visual inspection of presence of imaging data of the thorax in the DICOM record).

  • Slice thickness > 2.5mm.
  • Imaging > 10 years old.
  • Ground truth unknown.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Lung Nodules; A cohort of 1000 patients with incidental lung nodules will be identified using clinical records at participating NHS sites. Link-anonymised CT scan images and data will be stored using a central database for radiomics and artificial intelligence research, to predict the risk of malignancy.	Diagnostic test: Machine Learning Classification; Patient's scans will be used as input into in-house software to extract multiple radiomics features. These features will be used to develop a risk-signature which can predict malignancy risk. Patient scans will also be used as input into deep learning/convolutional neural network models to perform automated imaging classification.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Development of an imaging biobank	The primary endpoint will be met if we are able to store baseline CT scans and the minimum clinical data set for 1000 patients.	1 year

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Discovery of a CT-thorax based radiomics profile to predict cancer risk.	We aim to identify distinct clusters of radiomics variables to generate a radiomics predictive vector (RPV), which can be used to stratify patients according to malignancy risk. This vector will be used in multivariate analysis and compared to existing risk models.	1 year

Collaborators and Investigators

• Sponsor: Royal Marsden NHS Foundation Trust
• Collaborators: King's College Hospital NHS Trust; University College London Hospitals; Guy's and St Thomas' NHS Foundation Trust; Royal Brompton & Harefield NHS Foundation Trust; Institute of Cancer Research, United Kingdom; Imperial College Healthcare NHS Trust; Lewisham and Greenwich NHS Trust; Epsom and St Helier University Hospitals NHS Trust; RM Partners West London Cancer Alliance; UCLH Biomedical Research Centre
• Investigators: Study Chair: Richard Lee, MBBS PhD, The Royal Marsden Hospital

Study record dates

Study Major Dates

• Study Start (ACTUAL): June 1, 2020
• Primary Completion (ANTICIPATED): August 1, 2021
• Study Completion (ANTICIPATED): August 1, 2021

Study Registration Dates

• First Submitted: February 12, 2020
• First Submitted That Met QC Criteria: February 12, 2020
• First Posted (ACTUAL): February 17, 2020

Study Record Updates

• Last Update Posted (ACTUAL): June 11, 2021
• Last Update Submitted That Met QC Criteria: June 8, 2021
• Last Verified: June 1, 2021

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Machine Learning; Radiomics; Incidental lung nodules
• Additional Relevant MeSH Terms: Respiratory Tract Diseases; Neoplasms; Lung Diseases; Neoplasms by Site; Respiratory Tract Neoplasms; Thoracic Neoplasms; Lung Neoplasms; Multiple Pulmonary Nodules; Solitary Pulmonary Nodule
• Other Study ID Numbers: CCR5215

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No