Prediction Model of Peripheral Pulmonary Lesions Based on R-EBUS Image

NCT04497233 | Unknown DMC

• 1 other identifier: SHCHE202001
• Study Type: observational
• Target: 1,300
• Locations: 1 country
• Sites: 1

Brief Summary

Peripheral pulmonary lesions(PPLs) have a wide spectrum of diseases, and the diagnosis will affect the treatment strategy and prognosis. Radial endobronchial ultrasound (R-EBUS) can be used for non-invasive diagnosis of PPLs, and the supplement pathological diagnosis results of EBUS-TBLB, which has important clinical application value. This project intends to select representative images from R-EBUS dynamic videos for qualitative and quantitative analysis, to establish and verify the diagnostic evaluation system of R-EBUS forPPLs. Then build 1,000 R-EBUS image databases of PPLs, train deep learning networks for automatic extraction and diagnosis of target areas, and automatically extract representative images from videos to establish a benign and malignant prediction model of PPLs. We will provide reliable theoretical basis for the diagnosis of PPLs, and optimize the diagnosis and treatment method.The network would be prospectively verified through 300 R-EBUS images from multi centers.

Conditions

Diagnoses Disease

Keywords

R-EBUS image; Deep learning; Peripheral pulmonary lesions; Prediction model; Diagnosis

Outcome Measures

Primary Outcomes (1)

• Diagnostic efficacy of R-EBUS prediction model.

  Diagnostic efficacy includes sensitivity, specificity, positive predictive value, negative predictive value and diagnostic accuracy

  18 months

Secondary Outcomes (1)

• Diagnostic efficacy of traditional qualitative and quantitative methods

  18 months

Study Arms (1)

Prospectively validation group

Two diagnosis methods will be used in the prospective validation section, one is traditional qualitative and quantitative method, the other is artificial intelligence prediction model based on videos to compare the diagnostic efficacy.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The population of this study are those who meet the inclusion and exclusion criteria.

You may qualify if:

• Patients with PPLs in Chest CT or PET / CT;
• Chest CT or PET / CT shows PPLs with diameter greater than 8 mm;
• Patients agree to perform EBUS-TBLB and sign the informed consent.

You may not qualify if:

• Thin-layer Chest CT or PET / CT indicates lack of bronchial access to PPLs;
• Patients refuse to participate in this clinical trial;
• Patients with severe cardiopulmonary dysfunction or other indications that not allowed for bronchoscopy;
• Visible lesions in the lumen during conventional bronchoscopy;
• Patients have other related contraindications of bronchoscopy;
• Patients have other reasons unfit for this study.

Sponsors & Collaborators

• Shanghai Chest Hospital: lead

Study Sites (1)

Shanghai Chest Hospital

Shanghai, China

RECRUITING

MeSH Terms

Conditions

Disease

Condition Hierarchy (Ancestors)

Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Jiayuan Sun, PhD

  Shanghai Chest Hospital

  STUDY DIRECTOR

Central Study Contacts

Jiayuan Sun, PhD

CONTACT

18017321598; jysun1976@163.com

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: OTHER
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Director,Endoscope Department,Shanghai Chest Hospital

Study Record Dates

• First Submitted: July 19, 2020
• First Posted: August 4, 2020
• Study Start: July 1, 2018
• Primary Completion: September 30, 2020
• Study Completion: March 31, 2021
• Last Updated: August 4, 2020

Record last verified: 2020-07

Locations

CN (1)