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

Investigate the Potential of Deep Learning in Assessing Pneumoconiosis Depicted on Digital Chest Radiographs and to Compare Its Performance With Certified Radiologists

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.

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).

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