Article Text

Download PDFPDF
Original research
Potential of deep learning in assessing pneumoconiosis depicted on digital chest radiography
  1. Xiaohua Wang1,
  2. Juezhao Yu2,
  3. Qiao Zhu1,
  4. Shuqiang Li3,
  5. Zanmei Zhao3,
  6. Bohan Yang2,
  7. Jiantao Pu2
  1. 1 Department of Radiology, Peking University Third Hospital, Beijing, China
  2. 2 Departments of Radiology and Bioengineering, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
  3. 3 Department of Occupational Disease, Peking University Third Hospital, Beijing, China
  1. Correspondence to Dr Jiantao Pu, Departments of Radiology and Bioengineering, University of Pittsburgh, Pittsburgh, PA 15213, Pennsylvania, USA; jip13{at}pitt.edu

Abstract

Objectives To investigate the potential of deep learning in assessing pneumoconiosis depicted on digital chest radiographs and to compare its performance with certified radiologists.

Methods We 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, we 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). In addition, we asked two certified radiologists to independently interpret the images in the testing dataset and compared their performance with the computerised scheme.

Results The Inception-V3 CNN architecture, which was trained on the combination of the three image sets, achieved an AUC of 0.878 (95% CI 0.811 to 0.946). The performance of the two radiologists in terms of AUC was 0.668 (95% CI 0.555 to 0.782) and 0.772 (95% CI 0.677 to 0.866), respectively. The agreement between the two readers was moderate (kappa: 0.423, p<0.001).

Conclusion Our experimental results demonstrated that the deep leaning solution could achieve a relatively better performance in classification as compared with other models and the certified radiologists, suggesting the feasibility of deep learning techniques in screening pneumoconiosis.

  • pneumoconiosis
  • deep learning
  • digital radiography
  • classification
View Full Text

Statistics from Altmetric.com

Footnotes

  • Contributors The data were collected and provided by XW and QZ, the image interpretations were performed by SL and ZZ, the computer models were developed and trained by JY, BY and JP, the manuscript was written by XW and JP with contributions from all other authors.

  • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

  • Competing interests None declared.

  • Patient consent for publication Not required.

  • Ethics approval This study was approved by the Peking University Third Hospital Medical Science Research Ethics Committee (M2019467-519-02).

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Data availability statement As a way to advance the research in pneumoconiosis, we will make the collected image data available to the community at no cost. Data are available on reasonable request.

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.