CT-based Radiomic Signature Can Identify Adenocarcinoma Lung Tumor Histology

NCT03940846 | Unknown DMC

• 1 other identifier: LHist
• Study Type: observational
• Target: 650
• Locations: 1 country
• Sites: 1

Brief Summary

Lung cancer remains the leading cause of cancer related mortality worldwide, with more than 1.5 million related deaths annually. Lung cancer is divided into two main groups: Small Cell Lung Carcinoma (SCLC) and Non-Small Cell Lung Carcinoma (NSCLC), with prevalence of \~20% and 80% respectively. NSCLC is further subdivided into adenocarcinoma (the most common), squamous cell carcinoma (SCC), and large cell carcinoma. Furthermore, each subtype is likely to have specific mutations, which could be targeted for treatment. Medical imaging and radiomics feature extraction represent a candidate alternative to conventional tissue biopsy, a theory that is investigated in this study.

Conditions

Nonsmall Cell Lung Cancer

Outcome Measures

Primary Outcomes (1)

• Lung histology

  Is the tumor under investigation an adenocarcinoma of the lung?

  December 2019

Study Arms (4)

Maastro (Lung1)

Open source dataset available at TCIA.org. The cohort includes CT scans of 422 patients diagnosed with NSCLC.

Diagnostic Test: Virtual biopsy

UCSF

A cohort of patients diagnosed with NSCLC at UCSF medical center. It includes CT scans of 165 patients.

Diagnostic Test: Virtual biopsy

Radboud

A cohort of patients diagnosed with NSCLC at Radboud medical center. It includes CT scans of 255 patients.

Diagnostic Test: Virtual biopsy

Stanford

Open source dataset available at TCIA.org. The cohort includes CT scans of 211 patients diagnosed with NSCLC.

Diagnostic Test: Virtual biopsy

Interventions

Virtual biopsy DIAGNOSTIC_TEST

Radiomics -the high throughput extraction of quantitative features from medical imaging- extract features that might potentially decode biologic tumor information, which might ultimately reduce the need to use invasive procedure, such as tissue biopsy.

Also known as: Radiomics-based histology prediction

Maastro (Lung1); Radboud; Stanford; UCSF

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Patients diagnosed with NSCLC, who further underwent tissue biopsy to determine tumor histology.

You may qualify if:

• Availability of diagnostic non-contrast enhanced CT scan.
• Availability of histologic tumor analysis results

Sponsors & Collaborators

• Maastricht University: lead
• University of California, San Francisco: collaborator
• Radboud University Medical Center: collaborator

Study Sites (1)

Maastricht University

Maastricht, Limburg, 6229ER, Netherlands

Location

MeSH Terms

Conditions

Carcinoma, Non-Small-Cell Lung

Condition Hierarchy (Ancestors)

Carcinoma, Bronchogenic; Bronchial Neoplasms; Lung Neoplasms; Respiratory Tract Neoplasms; Thoracic Neoplasms; Neoplasms by Site; Neoplasms; Lung Diseases; Respiratory Tract Diseases

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: May 6, 2019
• First Posted: May 7, 2019
• Study Start: March 1, 2019
• Primary Completion: October 31, 2020
• Study Completion: January 31, 2021
• Last Updated: April 6, 2020

Record last verified: 2019-04

Locations

NL (1)