Objective: To construct and verify a light-weighted convolutional neural network (CNN), and explore its application value for screening the early stage (subcategory 0/1 and stage Ⅰ of pneumoconiosis) of coal workers' pneumoconiosis (CWP) from digital chest radiography (DR) . Methods: A total of 1225 DR images of coal workers who were examined at an Occupational Disease Prevention and Control Institute in Anhui Province from October 2018 to March 2021 were retrospectively collected. All DR images were collectively diagnosed by 3 radiologists with diagnostic qualifications and gave diagnostic results. There were 692 DR images with small opacity profusion 0/- or 0/0 and 533 DR images with small opacity profusion 0/1 to stage Ⅲ of pneumoconiosis. The original chest radiographs were preprocessed differently to generate four datasets, namely 16-bit grayscale original image set (Origin16), 8-bit grayscale original image set (Origin 8), 16-bit grayscale histogram equalized image set (HE16) and 8-bit grayscale histogram equalized image set (HE8). The light-weighted CNN, ShuffleNet, was applied to train the generated prediction model on the four datasets separately. The performance of the four models for pneumoconiosis prediction was evaluated on a test set containing 130 DR images using measures such as the receiver operating characteristic (ROC) curve, accuracy, sensitivity, specificity, and Youden index. The Kappa consistency test was used to compare the agreement between the model predictions and the physician diagnosed pneumoconiosis results. Results: Origin16 model achieved the highest ROC area under the curve (AUC=0.958), accuracy (92.3%), specificity (92.9%), and Youden index (0.8452) for predicting pneumoconiosis, with a sensitivity of 91.7%. And the highest consistency between identification and physician diagnosis was observed for Origin16 model (Kappa value was 0.845, 95%CI: 0.753-0.937, P<0.001). HE16 model had the highest sensitivity (98.3%) . Conclusion: The light-weighted CNN ShuffleNet model can efficiently identify the early stages of CWP, and its application in the early screening of CWP can effectively improve physicians' work efficiency.
Humans ; Retrospective Studies ; Anthracosis/diagnostic imaging* ; Pneumoconiosis/diagnostic imaging* ; Coal Mining ; Neural Networks, Computer ; Coal

Humans ; Lung ; Pneumoconiosis/diagnostic imaging* ; Radiography ; Tomography, X-Ray Computed

Humans ; Lung ; Pneumoconiosis/diagnostic imaging* ; Retrospective Studies ; Silicosis/diagnostic imaging* ; Tomography, X-Ray Computed

OBJECTIVETo conduct a systematic review of studies reporting the comparison of digital radiography (DR) with conventional film-screen radiograph (FSR) in the screening and recognition of pneumoconiosis worldwide, to evaluate the feasibility of DR in the screening and recognition of pneumoconiosis, to analyze the similarity and difference between DR and FSR, to explore the main challenge to utilize DR in the future.

METHODSThe national and international databases were systematically searched for original articles on DR for screening and recognition of pneumoconiosis published from first Jan 1998 to first Nov 2013, making evaluation and selection of them, and qualitative data and quantitative data were extracted independently from the selected articles and systematically reviewed.

RESULTSFive hundred and twenty articles were found and evaluated and nine of them met the inclusion criteria of systematic review. The research time started from 2002 to 2011 whose objects mainly came from pneumoconiosis cases and dust-exposed workers and control population examined with DR and FSR using the high kV radiography from 120 to 130 kV. The chest radiographs were read at blind and random and standard control method. There were only two papers compare the validity of DR and FSR for recognition and classification of pneumoconiosis using gold standards. There were still some diversity of imaging processing and imaging reading without design and assessment using Standards for Reporting of Diagnostic Accuracy (STARD) in these researches. The evaluation index of the nine articles include detection rate of small opacities, crude agreement, Kappa value of Kappa Consistency Test, Area Under the Curve of ROC, etc. Seven of the nine selected articles estimated DR has generally produced superior image qualities compared to FSR. Four papers had a conclusion that DR could be equivalent to FSR in identification of shapes and profusion of small opacities and in classification of pneumoconiosis. Five papers considered DR had higher presence of pneumoconiosis comparing with FSR especially in recognition the pneumoconiosis of category 1. The variation between different film formats of DR and FSR were smaller than that within and between readers for classification of pneumoconiosis.

CONCLUSIONAlthough there are still some imperfections in the existent researches to solve, DR can be equivalent to FSR in screening and recognition of pneumoconiosis. It is necessary to develop technical specifications of DR and standard digital chest radiographs for pneumoconiosis including both hard copy and soft copy, and develop an evaluation criterion on chest images of DR.

Humans ; Mass Screening ; Pneumoconiosis ; diagnostic imaging ; Radiographic Image Enhancement ; methods

OBJECTIVETo study the radiographycal changes and prognosis of welders' pneumoconiosis patients diagnosed within the last few years.

METHODSOccupational hygienics data (including years on welding work, welding materials exposed to and work environment), symptoms, lung function test results and follow-up data of 136 welders' pneumoconiosis patients were collected retrospectively. The follow-up lasted up till June 30, 2014, with follow-up interval being one year. Chest radiographs were read/reviewed together by 3 senior experts experienced in pneumoconiosis diagnosing and shape and size of small opacity, overall profusion, affected lung zones and pneumoconiosis stages were all logged.

RESULTSOf all 136 pneumoconiosis cases, five were of stage II and 131 were stage I, and they had been engaged in welding work for 9.2±6.34 years. All patients were present with slight symptoms including coughing, chest distress and dyspnea, while their lung function remained normal. Small round opacities were found on chest radiographs of 88.9% of the 136 cases. Years of follow-up on 131 cases of stage I Welder's pneumoconiosis showed that irregular small opacities remained fundamentally unchanged, while small round opacities tended to gradually lessen instead of coalescence. Two years after primary diagnosing, the total affected lung zones of follow-up objects were noticed to start lessening, and reduced by 0.02 per patient among the 48 follow-up subjects. Of the 48 cases followed up up to six years after primary diagnosing, the affected lung zone number was reduced by 0.54 per patient while 4 cases (8%) went down to below stage I. As of the 36 patients followed up 10 years after after primary diagnosis, the number of affected lung areas decreased by 1.14, and 22% (8 cases) appeared less than stage I on chest radiograph.

CONCLUSIONIt seemed that the so-called welders' pneumoconiosis featuring small round opacities tended to get improved over time, which suggested the diagnosis of siderosis.

Cohort Studies ; Humans ; Lung ; Occupational Exposure ; adverse effects ; Pneumoconiosis ; diagnostic imaging ; pathology ; Radiography, Thoracic ; Retrospective Studies ; Siderosis ; diagnostic imaging ; pathology ; Thoracic Cavity ; Welding

OBJECTIVETo evaluate the clinical value of (18)F-FDG PET/CT in the differentiation between benign lesions and lung cancer for large shadows in patients with pneumoconiosis.

METHODSA retrospective study was conducted in 21 patients with a confirmed diagnosis of pneumoconiosis who had a total of 37 large shadows in the lung fields as shown by whole-body (18)F-FDG PET/CT imaging, and (18)F-FDG uptake was evaluated using the maximum standardized uptake value (SUVmax). Twelve lesions were examined by CT-guided aspiration biopsy, and one case underwent fiberoptic bronchoscopy, as well as tests based on bronchoalveolar lavage fluid and sputum; the other cases were followed up for more than 2 years. The differences between pneumoconiosis nodules with high (18)F-FDG uptake and lung cancer were evaluated by t test.

RESULTSSeventeen lung masses or nodules with high (18)F-FDG uptake were detected in 13 patients; among the 13 patients, 5 lesions of 5 cases were confirmed as non?small cell lung cancer (1 case of squamous cell carcinoma, 3 cases of adenocarcinoma, and 1 case of recurrent squamous cell carcinoma after operation), and 7 lesions of 7 cases were progressive massive fibrosis as shown by CT-guided aspiration biopsy; one case had no tumor cells detected by fiberoptic bronchoscopy, and 2.5-year follow-up revealed no changes in the lesions. The other 8 patients showed no increased (18)F-FDG uptake in their 20 lung nodules, which were confirmed as benign lesions by follow-up. The diameter range of lung cancer was 1.6∼6.8 cm, and the SUVmax range was 4.8∼14.0; the diameter range of pneumoconiosis nodules with high (18)F-FDG uptake was 1.5∼4.6 cm, and the SUVmax range was 2.6∼12.4. There were no significant differences in diameter and SUVmax between the lung cancer and pneumoconiosis nodules with high (18)F-FDG uptake (P > 0.05 for both). (18)F-FDG PET/CT had a specificity of 62.5% (20/32), an accuracy of 67.6% (25/37), a false-positive rate of 37.5% (12/32), and a negative predictive value of 100% (20/20) for the diagnosis of lung cancer. The lung cancer detection rate was 23.8% (5/21).

CONCLUSIONIn (18)F-FDG PET/CT imaging for patients with pneumoconiosis, the lung lesions without (18)F-FDG uptake or symmetrical lesions with high (18)F-FDG uptake are considered as benign pneumoconiosis nodules; however, (18)F-FDG PET/CT might have a limited role in evaluating the solitary lung lesions in patients with pneumoconiosis and needs further study.

Adenocarcinoma ; diagnostic imaging ; pathology ; Adult ; Aged ; Female ; Fluorodeoxyglucose F18 ; Humans ; Lung ; pathology ; Lung Neoplasms ; diagnostic imaging ; pathology ; Male ; Middle Aged ; Pneumoconiosis ; diagnostic imaging ; pathology ; Positron-Emission Tomography ; Retrospective Studies ; Tomography, X-Ray Computed

OBJECTIVETo apply low-dose multi spiral computed tomography (MSCT) chest scans in the early diagnosis and differential diagnosis of pneumoconiosis.

METHODSOne hundred and twenty dust-exposed volunteers were examined by MSCT chest scans at conventional dose and low dose, and the results of conventional-dose scans were set as the gold standard. Comparative analysis was performed on the major CT findings and quality of post-processing images, including 1.5 mm and 5.0∼10.0 mm thick high -resolution reconstructed images, multiplanar reformat images, and maximum intensity projection images.

RESULTSOne hundred and twenty cases of small circular shadows, 36 cases of ribbon shadows in pulmonary parenchyma, 1 case of honeycombing shadow, and 13 cases of big shadows were all showed on low -dose MSCT. But 94 (95.9%) of 98 cases of interlobular septal thickening shadows and 98 (93.3%) of 105 cases of short branched shadows were detected on low-dose MSCT. There were no significant differences in display of the mentioned large and small shadows between low-dose scans and conventional-dose scans (P > 0.05). Eighty-five cases of small airway disease, 8 cases of pulmonary inflammatory lesions, and 47 cases of hilar and mediastinal lymph node swelling were all detected by MSCT. As for the 46 cases of emphysema, 38 (82.6%) were shown. The low-dose MSCT images of 1.5 mm thickness had more artifacts than those of other thickness. The radiation dose of low-dose MSCT was about 1/3-1/5 of that in the conventional-dose MSCT.

CONCLUSIONThere is no difference in display of pneumoconiosis between low-dose and conventional-dose MSCT chest scans. With lower radiation dose, low-dose MSCT can be applied in the diagnosis of pneumoconiosis.

Adult ; Aged ; Dust ; Female ; Humans ; Lung ; diagnostic imaging ; Male ; Middle Aged ; Occupational Exposure ; Pneumoconiosis ; diagnostic imaging ; Tomography, X-Ray Computed ; methods

OBJECTIVETo establish the optimal image post-processing parameters for digital chest radiography as preliminary research for introducing digital radiography (DR) to pneumoconiosis diagnosis in China.

METHODSA total of 204 pneumoconiosis patients and 31 dust-exposed workers were enrolled as the subjects in this research. Film-screen radiography (FSR) and DR images were taken for all subjects. DR films were printed after raw images were processed and parameters were altered using DR workstation (GE Healthcare, U.S.A.). Image gradations, lung textures, and the imaging of thoracic vertebra were evaluated by pneumoconiosis experts, and the optimal post-processing parameters were selected. Optical density was measured for both DR films and FSR films.

RESULTSFor the DR machine used in this research, the contrast adjustment (CA) and brightness adjustment (BA) were the main parameters that determine the brightness and gray levels of images. The optimal ranges for CA and BA were 115%∼120% and 160%∼165%, respectively. The quality of DR chest films would be optimized when tissue contrast was adjusted to a maximum of 0.15, edge to a minimum of 1, and both noise reduction and tissue equalization to0.The failure rate of chest DR (0.4%) was significantly lower than that of chest FSR (17%) (P < 0.05).

CONCLUSIONAfter appropriate image post-processing on DR machine purchased from GE Healthcare, the DR chest films can meet all requirements for the quality of chest X-ray films in the Chinese diagnostic criteria for pneumoconiosis.

Humans ; Image Processing, Computer-Assisted ; methods ; Pneumoconiosis ; diagnostic imaging ; Radiographic Image Enhancement ; standards ; X-Ray Film

OBJECTIVETo study the value of compute tomography (CT)-based quantitative assessment in the diagnosis of pneumoconiosis.

METHODSSixty patients with pneumoconiosis and 40 healthy volunteers (control) underwent CT scanning at the levels of the top of the aortic arch, tracheal carina, and 3 cm and 6 cm below the tracheal carina. All the CT images were analyzed with density histograms for a specific region to calculate the mean lung CT value (ME) and pixel index for assessment of lung density changes.

RESULTSAt the levels of the top of the aortic arch and 6 cm below the tracheal carina, the pixel indices in the 10 CT threshold density intervals within -832 to -352 HU was all significantly higher in pneumoconiosis group than in the control group (P<0.05). At the levels of the tracheal carina and 3 cm below the tracheal carina, the 11 pixel indices in the CT threshold density intervals within -880 to -352 HU were also significantly higher in pneumoconiosis group (P<0.05). At all the 4 scan levels, the pixel indices in the 10 intervals between -880 and -352 HU were all significantly higher in pneumoconiosis group (P<0.05).

CONCLUSIONCT density histograms allow quantitative evaluation of lung fibrosis in patients with pneumoconiosis for diagnostic purposes.

Adult ; Aged ; Case-Control Studies ; Humans ; Male ; Middle Aged ; Pneumoconiosis ; diagnostic imaging ; Pulmonary Fibrosis ; diagnostic imaging ; Spiral Cone-Beam Computed Tomography ; Tomography, X-Ray Computed ; methods

In order to investigate the fine distinction of the tomographic images and the dominant anatomic distributions, we carefully reviewed and analyzed the features and predominant anatomic distribution of forty-nine pneumoconiosis patients with confirmed diagnosis on multi-detector row CT (MDCT). It was found that the round and small opacity p and irregular small opacity were mostly shown in the MDCT features of pneumoconiosis, while the large opacity and progressive massive fibrosis (PMF) were less frequently depicted in the MDCT. Distributions of round and small opacity and irregular small opacity in the six lung lobes were significantly different (P < 0.01). The most common p opacity was significantly seen in the upper and lower left lungs as well as in the upper right lung's opacity was in the upper left lung as well as lower left and right lungs. The large opacity commonly distributed in upper left and right lungs, while the PMF was often shown in both of two lungs. The results demonstrated that the MDCT could be an effective modality for detecting tiny lesions and anatomic distribution of pneumoconiosis, and it would be helpful for early diagnosis and accurate staging of the pneumoconiosis disease.
Adult ; Aged ; Early Diagnosis ; Female ; Humans ; Lung ; diagnostic imaging ; pathology ; Male ; Middle Aged ; Multidetector Computed Tomography ; methods ; Pneumoconiosis ; diagnostic imaging ; pathology ; Silicosis ; diagnostic imaging ; pathology