Potential of Deep Learning in Assessing Pneumoconiosis Depicted on Digital Chest Radiography

NCT ID: NCT04963348

Last Updated: 2021-07-15

Basic Information

• Recruitment Status: COMPLETED
• Total Enrollment: 1881 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2015-01-01
• Study Completion Date: 2019-12-31

Brief Summary

Pneumoconiosis is relatively prevalent in low/middle-income countries, and it remains a challenging task to accurately and reliably diagnose pneumoconiosis. The investigators implemented a deep learning solution and clarified the potential of deep learning in pneumoconiosis diagnosis by comparing its performance with two certified radiologists. The deep learning demonstrated a unique potential in classifying pneumoconiosis.

Detailed Description

The investigators retrospectively collected a dataset consisting of 1881 chest X-ray images in the form of digital radiography. These images were acquired in a screening setting on subjects who had a history of working in an environment that exposed them to harmful dust. Among these subjects, 923 were diagnosed with pneumoconiosis, and 958 were normal. To identify the subjects with pneumoconiosis, the investigators applied a classical deep convolutional neural network (CNN) called Inception-V3 to these image sets and validated the classification performance of the trained models using the area under the receiver operating characteristic curve (AUC).

Conditions

Pneumoconiosis

Study Design

• Observational Model Type: CASE_ONLY
• Study Time Perspective: RETROSPECTIVE

Study Groups

convolutional neural network (CNN)

a classical deep convolutional neural network (CNN) called Inception-V3 was applied to the image sets and validated the classification performance of the trained models

convolutional neural networks (CNNs)

Intervention Type: OTHER

CNN architecture named U-Net architecture

Interventions

convolutional neural networks (CNNs)

CNN architecture named U-Net architecture

Intervention Type: OTHER

Other Intervention Names

deep learning technology

Eligibility Criteria

Inclusion Criteria

• industrial workers with a history of exposure to dust and underwent DR screening of pneumoconiosis from 2015 to 2018

Exclusion Criteria

• patients with poor image quality
• patients with incomplete clinical data

• Eligible Sex: ALL
• Accepts Healthy Volunteers: No

Sponsors

Peking University Third Hospital

OTHER

Sponsor Role: lead

Responsible Party

Responsibility Role: SPONSOR

Principal Investigators

Xiaohua Wang

Role: STUDY_CHAIR

Peking University Third Hospital

Other Identifiers

M2019467

Identifier Type: -

Identifier Source: org_study_id