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

Peking University

Status: Completed

Conditions: Pneumoconiosis

Treatments: Other: convolutional neural networks (CNNs)

Study type: Observational

Funder types: Other

Identifiers

NCT04963348

M2019467

Details and patient eligibility

About

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.

Full 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).

Enrollment: 1,881 patients

Sex: All

Volunteers: No Healthy Volunteers

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

Trial design

1,881 participants in 1 patient group

convolutional neural network (CNN)

Description:

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

Treatment:

Other: convolutional neural networks (CNNs)