Deep learning-based algorithm for classifying high-resolution computed tomography features in coal workers' pneumoconiosis.

Abstract

Background: Coal workers' pneumoconiosis is a chronic occupational lung disease with considerable pulmonary complications, including irreversible lung diseases that are too complex to accurately identify via chest X-rays. The classification of clinical imaging features from high-resolution computed tomography might become a powerful clinical tool for diagnosing pneumoconiosis in the future.

Methods: All chest high-resolution computed tomography (HRCT) medical images presented in this work were obtained from 217 coal workers' pneumoconiosis (CWP) patients and dust-exposed workers. We segmented regions of interest according to the diagnostic results, which were evaluated by radiologists. These regions were then classified regions into four categories. We employed an efficient deep learning model and various image augmentation techniques (DenseNet-ECA). The classification performance of the different deep learning models was assessed, and receiver operating characteristic (ROC) curves and accuracy (ACC) were used to determine the optimal algorithm for classifying CWP clinical imaging features obtained from HRCT images.

Results: Four primary clinical imaging features in HRCT images, with a total of more than 1700 regions of interest (ROIs), were annotated, augmented, and used as a training set for tenfold cross-validation to generate the model. We selected DenseNet-Attention Net as the optimal model through assessing the performance of different classification algorithms, which yielded an average area under the ROC curve (AUC) of 0.98, and all clinical imaging features were classified with an AUC greater than 0.92. For the individual classifications, the AUCs were as follows: small miliary opacities, 0.99; nodular opacities, 1.0; interstitial changes, 0.92; and emphysema, 1.0.

Conclusion: We successfully applied a data augmentation strategy to develop a deep learning model by combining DenseNet with ECA-Net. We used our novel model to automatically classify CWP clinical imaging features from 2D HRCT images. This successful application of a deep learning-data augmentation algorithm can help clinical radiologists by providing reliable diagnostic information for classification.

Trial registration: Chinese Clinical Trial Registry, ChiCTR2100050379. Registered on 27 August 2021, https://www.chictr.org.cn/bin/project/edit?pid=132619 .