A deep learning-based model for screening and staging pneumoconiosis

Abstract

This study aims to develop an artificial intelligence (AI)-based model to assist radiologists in pneumoconiosis screening and staging using chest radiographs. The model, based on chest radiographs, was developed using a training cohort and validated using an independent test cohort. Every image in the training and test datasets were labeled by experienced radiologists in a double-blinded fashion. The computational model started by segmenting the lung field into six subregions. Then, convolutional neural network classification model was used to predict the opacity level for each subregion respectively. Finally, the diagnosis for each subject (normal, stage I, II, or III pneumoconiosis) was determined by summarizing the subregion-based prediction results. For the independent test cohort, pneumoconiosis screening accuracy was 0.973, with both sensitivity and specificity greater than 0.97. The accuracy for pneumoconiosis staging was 0.927, better than that achieved by two groups of radiologists (0.87 and 0.84, respectively). This study develops a deep learning-based model for screening and staging of pneumoconiosis using man-annotated chest radiographs. The model outperformed two groups of radiologists in the accuracy of pneumoconiosis staging. This pioneer work demonstrates the feasibility and efficiency of AI-assisted radiography screening and diagnosis in occupational lung diseases.

Pneumoconiosis computer aided diagnosis system based on X-rays and deep learning

“…In this study, the dataset of 1760 DR chest radiographs comes from multiple centers and multiple devices, and the research results are more comprehensive. Besides, to our knowledge, our dataset is larger than those considered in the past investigations [ 16 , 17 , 20 , 29 ].…”

The significance of serum S100 calcium-binding protein A4 in silicosis

“…Stage II is defined as: level 2 or 3 profusion of small opacities presented in four subregions or more. Stage III is defined as: large opacities presented [ 22 ]. Exclusion criteria for this study were as follows: subjects with other inflammatory diseases, other fibrotic diseases, other pulmonary diseases, such as chronic obstructive pulmonary disease (COPD), active tuberculosis, pneumonia and pulmonary heart disease and autoimmune disorders.…”

Computer-Aided Diagnosis of Coal Workers’ Pneumoconiosis in Chest X-ray Radiographs Using Machine Learning: A Systematic Literature Review

“…In the most recent computer vision applications, CNN has been used in many fields, including medical image analysis, which achieved outstanding state-of-the-art performances [ 98 , 99 ]. This study only found eight research articles based on the use of CNN to detect CWP in CXR in which non-texture features were extracted from the lung image [ 49 , 67 , 68 , 69 , 70 , 71 , 72 , 73 ]. Zheng et al [ 73 ] investigated the CAD of CWP with the CXR films dataset, which indicated that traditional texture analysis is not enough to diagnose.…”

“…They also verified the non-textured feature performances with older versions of CNN, for example, LeNet [ 101 ] and AlexNet [ 102 ]. Zhang et al [ 67 ] investigated the non-textured feature’s performances with two groups of radiologists. They found that the ResNet [ 103 ] model extracted the proper features from the six sub-regions in the lung, which outperformed the radiologists.…”

“…For the period 2019–2021, this review only found eights studies that proposed using deep convolutional neural network (CNN) models to classify CWP (black lung disease) in CXR [ 49 , 67 , 68 , 69 , 70 , 71 , 72 , 73 ]. They used different pre-trained deep learning models for non-textured feature extraction then applied a fully connected layer with binary classifier for normal or abnormal (black lung) classification.…”