Radiomics Multifactorial Biomarker for Pulmonary Nodules

Completed

• Conditions: Neoplasms; Pathology; Carcinoma, Non-Small-Cell Lung; Lung Diseases; Lung Neoplasms
• Interventions: Diagnostic Test: radiomics

• Registration Number: NCT03872362
• Lead Sponsor: Maastricht University

Brief Summary

The investigators aim to investigate the utility of radiomics to differentiate malignant nodules from benign nodules and invasive adenocarcinoma from non-invasive adenocarcinoma.

Detailed Description

With the development of computed tomography (CT) equipment and the increasing use of lung cancer screening programs with low-dose CT, a growing number of early-stage lung cancers were detected so that a large number of patients have undergone surgery.

Although a number of radiological studies have been used morphological signs so-called semantic features to make a differential diagnosis, it is still hard to apply by clinician because pulmonary nodules especially ground-glass nodules and small size nodules have atypical radiology signs and have strong subjectivity from different observers. Recently, CT-based radiomics, extracting the quantitative high-throughput features from medical images and facilitating clinical decision-making system, showed a good performance to predict diagnosis and prognosis of diverse cancer.

Therefore, the proposed project aims to develop and validate radiomics models based on CT images to identify malignant nodules and then to discriminate the different types of lung adenocarcinoma in patients with pulmonary nodules.

Study Timeline

• Study Start: 2018-07-11
• Status Verified: 2019-01
• Primary Completion: 2019-01-11
• Study Completion: 2019-02-01
• Study First Submitted: 2019-03-11
• Study First Submitted QC: 2019-03-11
• Last Update Submitted: 2019-03-11
• Study First Posted: 2019-03-13
• Last Update Posted: 2019-03-13

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 800

Inclusion Criteria

• intraoperative frozen section diagnosis and final pathology diagnosis are available
• preoperative standard non-enhanced CT is available
• Pathologically confirmed

Exclusion Criteria

• with a previous history of radiation therapy, chemotherapy or biopsy
• the time interval between the CT examination and surgery was more than two weeks

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
External validation1	radiomics	No interventions
Training dataset	radiomics	No interventions
External validation2	radiomics	No interventions

Primary Outcome Measures

Name	Time	Method
Malignant nodules classifier	30 days	Model based on Radiomic that can differentiate malignant nodules from benign nodules.
Invasive adenocarcinoma classifier	30 days	Model based on Radiomic that can differentiate invasive adenocarcinoma from non-invasive adenocarcinoma.

Trial Locations

Locations (1)

Affiliated Zhongshan Hospital of Dalian University; 🇨🇳 Dalian, Liaoning, China