Comparison of the International Classification of High-resolution Computed Tomography for occupational and environmental respiratory diseases with the International Labor Organization International Classification of Radiographs of Pneumoconiosis

Chest x-ray has low sensitivity to detect silicosis in artificial stone benchtop industry workers

BACKGROUND AND OBJECTIVE

Chest x-ray (CXR) remains a core component of health monitoring guidelines for workers at risk of exposure to crystalline silica. There has however been a lack of evidence regarding the sensitivity of CXR to detect silicosis in artificial stone benchtop industry workers.

METHODS

Paired CXR and high-resolution computed tomography (HRCT) images were acquired from 110 artificial stone benchtop industry workers. Blinded to the clinical diagnosis, each CXR and HRCT was independently read by two thoracic radiologists from a panel of seven, in accordance with International Labour Office (ILO) methodology for CXR and International Classification of HRCT for Occupational and Environmental Respiratory Diseases. Accuracy of screening positive (ILO major category 1, 2 or 3) and negative (ILO major category 0) CXRs were compared with identification of radiological features of silicosis on HRCT.

RESULTS

CXR was positive for silicosis in 27/110 (24.5%) workers and HRCT in 40/110 (36.4%). Of the 83 with a negative CXR (ILO category 0), 15 (18.1%) had silicosis on HRCT. All 11 workers with ILO category 2 or 3 CXRs had silicosis on HRCT. In 99 workers ILO category 0 or 1 CXRs, the sensitivity of screening positive CXR compared to silicosis identified by HRCT was 48% (95%CI 29-68) and specificity 97% (90-100).

CONCLUSION

Compared to HRCT, sensitivity of CXR was low but specificity was high. Reliance on CXR for health monitoring would provide false reassurance for many workers, delay management and underestimate the prevalence of silicosis in the artificial stone benchtop industry.

Silicosis: No longer exclusively a chronic disease

ABSTRACT

Silicosis typically has been classified as a chronic disease that develops after at least 10 years of exposure to silica dust, and often is associated with miners and stone workers. As industries have changed over time, other types of workers (including those in artificial stonework, jewelry polishing, and denim production) have become exposed to high levels of silica, leading to the development of acute and accelerated silicosis. Acute silicosis can develop in as little as a few months, and accelerated silicosis can develop in as little as 2 years. No cure exists for any form of silicosis, and lung transplantation is the only lifesaving treatment. Primary care clinicians must understand when patients are at risk for developing silicosis and not assume that a short time of exposure precludes the development of silicosis.

Clinical usefulness of serum angiotensin converting enzyme in silicosis

INTRODUCTION

Silicosis is an irreversible and incurable disease. Preventive measures to eliminate exposure are the only effective way to reduce morbidity and mortality. In such situations, having a biomarker for early diagnosis or to predict evolution would be very useful in order to improve control of the disease. The elevation of serum angiotensin-converting enzyme (sACE) in silicosis has been described in previous studies, although its relationship with severity and prognosis is not clear.

AIMS

To determine the levels of sACE in a cohort of patients with exposure to silica dust with and without silicosis, and to assess their impact on the prognosis of the aforementioned patients.

METHOD

Prospective observational study on patients treated in a silicosis clinic from 2009 to 2018. sACE levels and pulmonary function tests were performed. Radiological progression was assessed in patients who had already had 2 X-rays of the thorax and / or two CT scans with at least a 1-year interval, from the time of inclusion in the study.

RESULTS

A total of 413 cases of silicosis were confirmed, as well as 73 with exposure to silica dust but without silicosis. The mean sACE level for healthy subjects was 27.5±7.3U/L, for exposed patients without silicosis it was 49.6±24.2U/L, for simple silicosis it was 57.8±31,3U/L and for complicated silicosis it was 74.5±38.6U/L. Patients with a higher sACE generally progressed radiologically during follow-up (73.3±38.0 vs. 60.4±33.7; p<.001) and so the category of silicosis changed (73,9±38.1 vs. 62.5±34.6; p<.021).

CONCLUSIONS

sACE was elevated in patients with silicosis, and the greater its severity, the higher it was, which is associated with disease progression measured radiologically or as a category change of silicosis.

Current status, trends, and predictions in the burden of silicosis in 204 countries and territories from 1990 to 2019

Background

Silicosis, a severe lung disease caused by inhaling silica dust, predominantly affects workers in industries such as mining and construction, leading to a significant global public health challenge. The purpose of this study is to analyze the current disease burden of silicosis and to predict the development trend of silicosis in the future the world by extracting data from the GBD database.

Methods

We extracted and analyzed silicosis prevalence, incidence, mortality, and disability-adjusted life years (DALYs) data from the Global Burden of Disease 2019 program for 204 countries and territories from 1990 to 2019. The association between the Sociodemographic Index (SDI) and the burden of age-standardized rates (ASRs) of DALYs has been examined at the regional level. Jointpoint regression analysis has been also performed to evaluate global burden trends of silicosis from 1990 to 2019. Furthermore, Nordpred age-period-cohort analysis has also been projected to predict future the burden of silicosis from 2019 to 2044.

Results

In 2019, global ASRs for silicosis prevalence, incidence, mortality, and DALYs were 5.383, 1.650, 0.161, and 7.872%, respectively which are lower than that in 1990. The populations of 45-59 age group were more susceptible to silicosis, while those aged 80 or above suffered from higher mortality and DALY risks. In 2019, the most impacted nations by the burden of silicosis included China, the Democratic People's Republic of Korea, and Chile. From 1990 to 2019, most regions observed a declining burden of silicosis. An "M" shaped association between SDI and ASRs of DALYs for silicosis was observed from 1990 to 2019. The age-period-cohort analysis forecasted a decreasing trend of the burden of silicosis from 2019 to 2044.

Conclusion

Despite the overall decline in the global silicosis burden from 1990 to 2019, some regions witnessed a notable burden of this disease, emphasizing the importance of targeted interventions. Our results may provide a reference for the subsequent development of appropriate management strategies.

Workers with Suspected Diagnosis of Silicosis: A Case Study of Sarcoidosis Versus Siderosis

Silicosis is one of the most important occupational respiratory diseases worldwide, hence the importance of making a correct diagnosis. Diagnosis is commonly based on radiological findings according to the ILO International Classification of Radiographs of Pneumoconioses and occupational exposure. High-resolution computed tomography is indicated for differential diagnosis. This article presents two cases with an initial diagnosis of silicosis that ended up being diagnosed as sarcoidosis and siderosis, respectively. The first case was a 42-year-old male who worked as a crushing operator in an underground copper and molybdenum mine for 22 years. He had a history of exposure to silicon dioxide and was asymptomatic. X-rays did not distinguish silicosis or siderosis, but histological findings (open lung biopsy) allowed for a diagnosis of sarcoidosis. The second case was a 50-year-old male who had worked as a welder in a molybdenum filter plant, an open pit mine since 2013; he spent the previous 20 years as a welder in an underground copper mine, with exposure to silicon dioxide and was symptomatic. The first radiograph showed opacities that were compatible with pulmonary silicosis. A subsequent high-resolution computed tomography and lung biopsy showed a pattern of pulmonary siderosis. Due to the similarities in the radiographs of these three diseases, greater emphasis must be placed on the differential diagnosis, for which a complete occupational and clinical history is important in order to provide clues for the performance of complementary tests to avoid misdiagnosing.

Artificial Intelligence in Quantitative Chest Imaging Analysis for Occupational Lung Disease

Occupational lung disease manifests complex radiologic findings which have long been a challenge for computer-assisted diagnosis (CAD). This journey started in the 1970s when texture analysis was developed and applied to diffuse lung disease. Pneumoconiosis appears on radiography as a combination of small opacities, large opacities, and pleural shadows. The International Labor Organization International Classification of Radiograph of Pneumoconioses has been the main tool used to describe pneumoconioses and is an ideal system that can be adapted for CAD using artificial intelligence (AI). AI includes machine learning which utilizes deep learning or an artificial neural network. This in turn includes a convolutional neural network. The tasks of CAD are systematically described as classification, detection, and segmentation of the target lesions. Alex-net, VGG16, and U-Net are among the most common algorithms used in the development of systems for the diagnosis of diffuse lung disease, including occupational lung disease. We describe the long journey in the pursuit of CAD of pneumoconioses including our recent proposal of a new expert system.

Exploratory study on noninvasive biomarker of silicosis in exhaled breath by solid-phase microextraction-gas chromatography-mass spectrometry analysis

BACKGROUND

As a chronic occupational disease, silicosis could cause irreversible and incurable impair to the lung. The current diagnosis of silicosis relies on imaging of X-ray or CT, but these methods cannot detect lung lesions in the early stage of silicosis.

OBJECTIVE

To establish a regular screening and early diagnosis methods for silicosis, which could be helpful for the prevention and treatment of silicosis.

METHODS

A total of 161 subjects were enrolled in the study, including 69 patients with silicosis (SILs) and 92 healthy controls. The exhaled breath samples of the subjects were collected with breath sampler and Tedlar bag. The analysis of volatile organic compounds (VOCs) in exhaled breath was performed by solid-phase microextraction (SPME) combined with gas chromatography mass spectrometry (GC-MS).

RESULTS

After excluding the pollutants from sampling bags and instruments, 86 VOCs have been identified in the exhaled breath. The orthogonal partial least squares-discriminant analysis (OPLS-DA) was employed for the screening of potential biomarkers of silicosis. Those components that related to smoking were also excluded from the biomarkers. Finally, nine possible biomarkers for silicosis were screened out, including 2,3-butanedione, ethyl acetate, chlorobenzene, o-cymene, 4-ethylhex-2-ynal, 3,5-dimethyl-3-heptanol, hydroquinone, phthalic anhydride and 5-(2-methylpropyl)nonane. Based on these biomarkers screened, a predicted model for silicosis was generated with the accuracy of 89.61%.

CONCLUSION

The nine biomarkers in exhaled breath were preliminarily screened out for the early diagnosis of silicosis, which can be helpful to the establishment of a noninvasive screening method for silicosis. Follow-up studies should be conducted to further verify these markers.

The Potential Diagnostic Biomarkers for the IgG Subclass in Coal Workers' Pneumoconiosis

Evidence suggests that exposure to coal dust increases immunoglobulin concentration. However, there is a paucity of data reporting immunoglobulin G (IgG) subclass in coal workers' pneumoconiosis (CWP). Therefore, this study intended to evaluate potential diagnostic biomarkers for the disease. CWP patients, dust-exposed workers without pneumoconiosis (DEW), and matched healthy controls (HCs) presented to the General Hospital of Datong Coal Mining Group and Occupational Disease Prevention and Treatment Hospital of Datong Coal Mining Group between May 2019 and September 2019 were recruited. The serum immunoglobulin concentration was determined by the multiplex immunoassay technique. Totally, 104 CWP patients, 109 DEWs, and 74 HCs were enrolled. Serum levels of IgG1, IgG2, IgM, and IgA were elevated in CWPs compared with those in DEWs and HCs (P < 0.05). The order of diagnostic accuracy between CWPs and DEWs depicted by the receiver operating characteristic (ROC) curve was IgG2, IgM, IgG1, IgG3, and IgA. Significantly higher IgG1/IgG3 and IgG2/IgG3 ratios were observed in the CWP group than in DEW and HC groups. Based on the IgG2/IgG3 ratio, the area under the ROC curve between CWP and DEW was 0.785 (95% CI 0.723-0.838), with a sensitivity of 73.1% and a specificity of 73.4%. Our findings suggest that IgG1, IgG2, IgM, and IgA are higher in the CWPs than DEWs and HCs. The IgG2/IgG3 ratio provides a viable alternative for the diagnosis of CWP.

Inhalational lung diseases

The term inhalational lung disease comprises a group of entities that develop secondary to the active aspiration of particles. Most are occupational lung diseases. Inhalational lung diseases are classified as occupational diseases (pneumoconiosis, chemical pneumonitis), hypersensitivity pneumonitis, and electronic-cigarette-associated lung diseases. The radiologic findings often consist of nonspecific interstitial patterns that can be difficult to interpret. Therefore, radiologists' experience and multidisciplinary teamwork are key to ensure correct evaluation. The role of the radiologist is fundamental in preventive measures as well as in diagnosis and management, having an important impact on patients' overall health. It is crucial to take into account patients' possible exposure to particles both at work and at home.

Understanding the pathogenesis of occupational coal and silica dust-associated lung disease

Workers in the mining and construction industries are at increased risk of respiratory and other diseases as a result of being exposed to harmful levels of airborne particulate matter (PM) for extended periods of time. While clear links have been established between PM exposure and the development of occupational lung disease, the mechanisms are still poorly understood. A greater understanding of how exposures to different levels and types of PM encountered in mining and construction workplaces affect pathophysiological processes in the airways and lungs and result in different forms of occupational lung disease is urgently required. Such information is needed to inform safe exposure limits and monitoring guidelines for different types of PM and development of biomarkers for earlier disease diagnosis. Suspended particles with a 50% cut-off aerodynamic diameter of 10 µm and 2.5 µm are considered biologically active owing to their ability to bypass the upper respiratory tract's defences and penetrate deep into the lung parenchyma, where they induce potentially irreversible damage, impair lung function and reduce the quality of life. Here we review the current understanding of occupational respiratory diseases, including coal worker pneumoconiosis and silicosis, and how PM exposure may affect pathophysiological responses in the airways and lungs. We also highlight the use of experimental models for better understanding these mechanisms of pathogenesis. We outline the urgency for revised dust control strategies, and the need for evidence-based identification of safe level exposures using clinical and experimental studies to better protect workers' health.

Artificial Intelligence Techniques to Predict the Airway Disorders Illness: A Systematic Review

Airway disease is a major healthcare issue that causes at least 3 million fatalities every year. It is also considered one of the foremost causes of death all around the globe by 2030. Numerous studies have been undertaken to demonstrate the latest advances in artificial intelligence algorithms to assist in identifying and classifying these diseases. This comprehensive review aims to summarise the state-of-the-art machine and deep learning-based systems for detecting airway disorders, envisage the trends of the recent work in this domain, and analyze the difficulties and potential future paths. This systematic literature review includes the study of one hundred fifty-five articles on airway diseases such as cystic fibrosis, emphysema, lung cancer, Mesothelioma, covid-19, pneumoconiosis, asthma, pulmonary edema, tuberculosis, pulmonary embolism as well as highlights the automated learning techniques to predict them. The study concludes with a discussion and challenges about expanding the efficiency and machine and deep learning-assisted airway disease detection applications.

Early Identification, Accurate Diagnosis, and Treatment of Silicosis

Silicosis is a global problem, and it has brought about great burdens to society and patients' families. The etiology of silicosis is clear, preventable, and controllable, but the onset is hidden and the duration is long. Thus, it is difficult to diagnose it early and treat it effectively, leaving workers unaware of the consequences of dust exposure. As such, a lack of details in the work history and a slow progression of lung disease contribute to the deterioration of patients until silicosis has advanced to fibrosis. These issues are the key factors impeding the diagnosis and the treatment of silicosis. This article reviews the literature on the early identification, diagnosis, and treatment of silicosis as well as analyzes the difficulties in the diagnosis and the treatment of silicosis and discusses its direction of future development.

Volume-based tomography for the diagnosis of incipient silicosis in former gold miners

Objective

To evaluate silicosis diagnosed through CT, with integration of clinical-occupational data, in silica-exposed workers presenting chest X-rays within International Labor Organization (ILO) category 0.

Methods

Cross-sectional study with 339 former gold miners, with comparable exposures and X-rays classified as ILO subcategory 0/0 (n=285) and 0/1 (n=54) were submitted to volume-based CT. The findings were classified according to the International Classification of HRCT CT for Occupational and Environmental Respiratory Diseases.

Results

A profusion degree of round opacities (RO)>1 was found in 22.4% (76/339) of the CT exams. After integrating the CT findings with clinical and occupational data, silicosis was diagnosed as follows: 43/285 (15.1%) and 14/54 (25.9%) in workers whose X-rays had been classified as 0/0 and 0/1, respectively. There was an upward trend towards longer exposures, reaching 38.9% when working more than 10 years underground and classified as 0/1 (p=0019). Those with presence of RO whose final diagnosis was not silicosis were mainly cases of tuberculosis or ‘indeterminate nodules’. Emphysema was found in 65/339 (19.1%), only 5 being detected in the X-ray.

Conclusion

Volume-based CT proved to be useful in the investigation of silicosis among individuals with a relevant exposure to silica, capturing diagnoses that had not been identified on X-rays. A response gradient of silicosis was showed by CT even in this population with ILO category 0 radiographs. It can be indicated based on quantitative and/or qualitative criteria of occupational exposure, especially considering the possibilities of low CT dosage.

Intelligent Image Diagnosis of Pneumoconiosis Based on Wavelet Transform-Derived Texture Features

Objective. Early diagnosis and treatment of occupational pneumoconiosis can delay the development of the disease. This study is aimed at investigating the intelligent diagnosis of occupational pneumoconiosis by wavelet transform-derived entropy. Method. From June 2013 to June 2020, the high KV digital radiographs (DR) and computed tomography (CT) images from a total of 60 patients with occupational pneumoconiosis in our department were selected. The wavelet transform-derived texture features were extracted from all images, and the decision tree was used for feature selection. The support vector machines (SVM) with three kernel functions were selected to classify the two kinds of images, and their diagnostic efficiency was compared. Result. After eight times of wavelet decomposition, eight wavelet entropy texture features (feature set) were extracted, and six were selected to form the feature subset. The classification effect of linear kernel function SVM is better than those of other functions, with an accuracy of 84.2%. The diagnostic values of DR and CT for occupational pneumoconiosis were the same ( $\text{kappa}=0.737,P<0.001$ ). The detection rate of CT for stage I of occupational pneumoconiosis was significantly higher than that of DR ( $P=0.031$ ). Conclusion. It is helpful to improve the early diagnosis level of pneumoconiosis by using SVM to make an intelligent diagnosis based on the wavelet entropy.

ACR Appropriateness Criteria® Diffuse Lung Disease

Diffuse lung disease, frequently referred to as interstitial lung disease, encompasses numerous disorders affecting the lung parenchyma. The potential etiologies of diffuse lung disease are broad with several hundred established clinical syndromes and pathologies currently identified. Imaging plays a critical role in diagnosis and follow-up of many of these diseases, although multidisciplinary discussion is the current standard for diagnosis of several DLDs. This document aims to establish guidelines for evaluation of diffuse lung diseases for 1) initial imaging of suspected diffuse lung disease, 2) initial imaging of suspected acute exacerbation or acute deterioration in cases of confirmed diffuse lung disease, and 3) clinically indicated routine follow-up of confirmed diffuse lung disease without acute deterioration. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

Early Detection Methods for Silicosis in Australia and Internationally: A Review of the Literature

Pneumoconiosis, or occupational lung disease, is one of the world’s most prevalent work-related diseases. Silicosis, a type of pneumoconiosis, is caused by inhaling respirable crystalline silica (RCS) dust. Although silicosis can be fatal, it is completely preventable. Hundreds of thousands of workers globally are at risk of being exposed to RCS at the workplace from various activities in many industries. Currently, in Australia and internationally, there are a range of methods used for the respiratory surveillance of workers exposed to RCS. These methods include health and exposure questionnaires, spirometry, chest X-rays, and HRCT. However, these methods predominantly do not detect the disease until it has significantly progressed. For this reason, there is a growing body of research investigating early detection methods for silicosis, particularly biomarkers. This literature review summarises the research to date on early detection methods for silicosis and makes recommendations for future work in this area. Findings from this review conclude that there is a critical need for an early detection method for silicosis, however, further laboratory- and field-based research is required.

Pneumoconiosis: current status and future prospects

ABSTRACT

Pneumoconiosis refers to a spectrum of pulmonary diseases caused by inhalation of mineral dust, usually as the result of certain occupations. The main pathological features include chronic pulmonary inflammation and progressive pulmonary fibrosis, which can eventually lead to death caused by respiratory and/or heart failure. Pneumoconiosis is widespread globally, seriously threatening global public health. Its high incidence and mortality lie in improper occupational protection, and in the lack of early diagnostic methods and effective treatments. This article reviews the epidemiology, safeguard procedures, diagnosis, and treatment of pneumoconiosis, and summarizes recent research advances and future research prospects.

Chest Imaging in the Diagnosis of Occupational Lung Diseases

Imaging plays a crucial role in the diagnosis and monitoring of occupational lung diseases (OLDs); however, the sensitivity and specificity of detection and diagnosis vary greatly depending on the imaging modality used. There is substantial overlap in appearance with non-occupation-related entities. OLDs should be considered in the differential even in the absence of a provided exposure history. Because many findings are not specific, a multidisciplinary approach is important in arriving at the diagnosis and will continue to be important as workplace-related pulmonary diseases evolve with changing industrial practices and workplace regulations.

Evaluation of lung densitometric and volumetric changes in silicosis patients using three-dimensional software for multidetector CT and the relationship with profusion scores

AIM

To evaluate the density and volume changes in the lungs of silicosis patients and their relationship with the disease severity classification of the International Labor Organization (ILO).

MATERIALS AND METHODS

The multidetector computed tomography (CT) images of 44 patients diagnosed with silicosis and 32 controls that underwent thoracic CT due to trauma were evaluated. Patients with silicosis were divided into three categories according to the ILO classification. Data related to the total lung volume, total lung mean density, lung opacity score, percentage of lung high opacity, and mean density in the lower and upper lobes were obtained using three-dimensional (3D) software.

RESULTS

There was no significant difference between the total lung mean densities of the silicosis and control groups (p=0.213); however, a significant difference was observed between the two groups in terms of the total lung volume (p<0.0001). According to the ILO classification, there was a significant difference between the disease severity categories in relation to the percentage of lung high opacity (p=0.000005). A strong correlation was detected between disease severity and high opacity percentage (p<0.0001, r=0.804). According to the ILO classification, there was also a significant difference between disease severity categories in terms of the lung opacity score (p=0.000144), as well as a moderate correlation between disease severity and opacity score (p<0.0001, r=0.580).

CONCLUSION

Total lung volume is a CT finding that shows variation in exposure to crystalline silica. The percentage of high opacity determined using multidetector CT is an effective parameter in evaluating disease severity.

International Classification of the Pneumoconiosis Radiograph Reader Training in Turkey

OBJECTIVES

We aimed to determine the characteristics of physicians who had attended the Readers Training of the International Labour Organization International Classification of Radiographs of Pneumoconioses (ILO ICRP) in Turkey.

MATERIALS AND METHODS

This study included 601 physicians attending the Reader Training of the ILO ICRP. Data were collected using an electronic questionnaire, and the inclusiveness of the study was 29.8% (n=179).

RESULTS

In this study, 70.6% of the physicians were men, and the mean age was 48.6±9.6 years; 46.6% of the participants had at least one medical specialty or side branch specialty, and 51.8% were pulmonologists. Furthermore, 52.6% of the physicians worked in the private sector, and 86.6% had an occupational physician certificate. Moreover, 55.3% of the participants evaluated the radiographs using the authority gained by the certification, and 68.3% of those who did not evaluate the films stated that the reason for not evaluating the films was a lack of demand. Participants who evaluated radiographs had received a demand for films most frequently from 1 to 2 different jobs (33.4%) and from 1 to 3 different workplaces (30.1%). Most films came from the mining (47.5%) and quarrying (50.5%) sectors. Some participants (64.3%) stated that the quality of the radiographs was insufficient, 59.2% experienced difficulties because the radiographs were not obtained using proper techniques, 23.4% stated that the fees per film evaluated were low, and 81.5% believed that update training is necessary.

CONCLUSION

The demand for these services will increase in line with the training and surveillance as stipulated by the legislation.

Relations between vital capacity, CO diffusion capacity and computed tomographic findings of former asbestos-exposed patients: a cross-sectional study

BACKGROUND

Asbestos-related lung diseases are one of the leading diagnoses of the recognized occupational diseases in Germany, both in terms of their number and their socio-economic costs. The aim of this study was to determine whether pulmonary function testing (spirometry and CO diffusion measurement (DLCO)) and computed tomography of the thorax (TCT) are relevant for the early detection of asbestos-related pleural and pulmonary fibrosis and the assessment of the functional deficiency.

METHODS

The records of 111 formerly asbestos-exposed workers who had been examined at the Institute for Occupational and Maritime Medicine, Hamburg, Germany, with data on spirometry, DLCO and TCT were reviewed. Workers with substantial comorbidities (cardiac, malignant, silicosis) and/or pulmonary emphysema (pulmonary hyperinflation and/or TCT findings), which, like asbestosis, can lead to a diffusion disorder were excluded. The remaining data of 41 male workers (mean 69.8 years ±6.9) were evaluated. The TCT changes were coded according to the International Classification of High-resolution Computed Tomography for Occupational and Environmental Respiratory Diseases (ICOERD) by radiologists and ICOERD-scores for pleural and pulmonary changes were determined. Correlations (ρ), Cohens κ and accuracy were calculated.

RESULTS

In all 41 males the vital capacity (VC in % of the predicted value (% pred.)) showed only minor limitations (mean 96.5 ± 18.0%). The DLCO (in % pred.) was slightly reduced (mean 76.4 ± 16.6%; median 80.1%); the alveolar volume related value (DLCO/VA) was within reference value (mean 102 ± 22%). In the TCT of 27 workers pleural asbestos-related findings were diagnosed whereof 24 were classified as pulmonary fibrosis (only one case with honey-combing). Statistical analysis provided low correlations of VC (ρ = - 0.12) and moderate correlations of DLCO (- 0.25) with pleural plaque extension. The ICOERD-score for pulmonary fibrosis correlated low with VC (0.10) and moderate with DLCO (- 0.23); DLCO had the highest accuracy with 73.2% and Cohens κ with 0.45. DLCO/VA showed no correlations to the ICOERD-score. The newly developed score, which takes into account the diffuse pleural thickening, shows a moderate correlation with the DLCO (ρ = - 0.35, p < 0.05).

CONCLUSIONS

In formerly asbestos-exposed workers, lung function alterations and TCT findings correlated moderate, but significant using DLCO and ICOERD-score considering parenchymal ligaments, subpleural curvilinear lines, round atelectases and pleural effusion in addition to pleural plaque extension. DLCO also showed highest accuracy in regard to pulmonary findings. However, VC showed only weaker correlations although being well established for early detection. Besides TCT the determination of both lung function parameters (VC and DLCO) is mandatory for the early detection and assessment of functional deficiencies in workers formerly exposed to asbestos.

Potential of deep learning in assessing pneumoconiosis depicted on digital chest radiography

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.