Small Opacities Research Articles

Accurate pneumoconiosis staging via deep texture encoding and discriminative representation learning.

Accurate pneumoconiosis staging is key to early intervention and treatment planning for pneumoconiosis patients. The staging process relies on assessing the profusion level of small opacities, which are dispersed throughout the entire lung field and manifest as fine textures. While conventional convolutional neural networks (CNNs) have achieved significant success in tasks such as image classification and object recognition, they are less effective for classifying fine-grained medical images due to the need for global, orderless feature representation. This limitation often results in inaccurate staging outcomes for pneumoconiosis. In this study, we propose a deep texture encoding scheme with a suppression strategy designed to capture the global, orderless characteristics of pneumoconiosis lesions while suppressing prominent regions such as the ribs and clavicles within the lung field. To further enhance staging accuracy, we incorporate an ordinal label distribution to capture the ordinal information among profusion levels of opacities. Additionally, we employ supervised contrastive learning to develop a more discriminative feature space for downstream classification tasks. Finally, in accordance with standard practices, we evaluate the profusion levels of opacities in each subregion of the lung, rather than relying on the entire chest X-ray image. Experimental results on the pneumoconiosis dataset demonstrate the superior performance of the proposed method confirming its effectiveness for accurate pneumoconiosis staging.

EP.04C.01 The Value of Ultrahigh Frequency Ultrasound in Localizing Small Pulmonary Ground Glass Opacity Intraoperatively: A Prospective Study

EP.04C.01 The Value of Ultrahigh Frequency Ultrasound in Localizing Small Pulmonary Ground Glass Opacity Intraoperatively: A Prospective Study

AMFP-net: Adaptive multi-scale feature pyramid network for diagnosis of pneumoconiosis from chest X-ray images

Early detection of pneumoconiosis by routine health screening of workers in the mining industry is critical for preventing the progression of this incurable disease. Automated pneumoconiosis classification in chest X-ray images is challenging due to the low contrast of opacities, inter-class similarity, intra-class variation and the existence of artifacts. Compared to traditional methods, convolutional neural networks have shown significant improvement in pneumoconiosis classification tasks, however, accurate classification remains challenging due to mainly the inability to focus on semantically meaningful lesion opacities. Most existing networks focus on high level abstract information and ignore low level detailed object information. Different from natural images where an object occupies large space, the classification of pneumoconiosis depends on the density of small opacities inside the lung. To address this issue, we propose a novel two-stage adaptive multi-scale feature pyramid network called AMFP-Net for the diagnosis of pneumoconiosis from chest X-rays. The proposed model consists of 1) an adaptive multi-scale context block to extract rich contextual and discriminative information and 2) a weighted feature fusion module to effectively combine low level detailed and high level global semantic information. This two-stage network first segments the lungs to focus more on relevant regions by excluding irrelevant parts of the image, and then utilises the segmented lungs to classify pneumoconiosis into different categories. Extensive experiments on public and private datasets demonstrate that the proposed approach can outperform state-of-the-art methods for both segmentation and classification.

Resting diffusing capacity and severity of radiographic disease predict gas exchange abnormalities with exercise in former US coal miners.

The US Department of Labor (DOL) does not fund diffusing capacity (DLCO) or metabolic measurements from cardiopulmonary exercise testing (CPET) for coal miners' disability evaluations. Although exercise arterial blood gas testing is covered, many miners are unable to perform maximal tests, and sampling at peak exercise can be challenging. We explored the relationship between resting DLCO, radiographic disease severity, and CPET abnormalities in former US coal miners. We analyzed data from miners evaluated between 2005 and 2015. Multivariable linear and logistic regression analyses were used to examine relationships between percent predicted (pp) forced expiratory volume in 1 s (FEV1pp), DLCOpp, VO2maxpp, A-a oxygen gradient (A-a)pp, dead space fraction (Vd/Vt), disabling oxygen tension (PO2), and radiographic findings of pneumoconiosis. Data from 2015 male coal miners was analyzed. Mean tenure was 28 years (SD 8.6). Thirty-twopercent had an abnormal A-a gradient (>150 pp), 20% had elevated Vd/Vt (>0.33), and 34% a VO2max < 60 pp. DLCOpp strongly predicted a disabling PO2, with an odds ratio (OR) of 2.33 [2.09-2.60], compared to 1.18 [1.08-1.29] for FEV1. Each increase in subcategory of small opacity (simple) pneumoconiosis increased the odds of a disabling PO2 by 42% [1.29-1.57], controlling for age, body mass index, pack-years of tobacco smoke exposure, and years of coal mine employment. DLCO is the best resting pulmonary function test predictor of CPET abnormalities. Radiographic severity of pneumoconiosis was also associated with CPET abnormalities. These findings support funding DLCO testing for impairment and suggest the term "small opacity" should replace "simple" pneumoconiosis to reflect significant associations with impairment.

Measuring lung diffusing capacity: an opportunity for improved medical surveillance and disability evaluation of coal miners

ObjectivesSpirometry is the primary lung function test utilised for medical surveillance and disability examination for coal mine dust lung disease. However, spirometry likely underestimates physiologic impairment. We sought to characterise...

NLTE modelling of water-rich exoplanet atmospheres. Cooling and heating rates

The hydrogen and water molecules respond very differently to the collisional-radiative processes taking place in planetary atmospheres. Naturally, the question arises whether H2O-rich atmospheres are more (or less) resilient to long-term mass loss than H2-dominated ones if they radiate away the incident stellar energy more (or less) efficiently. If confirmed, the finding would have implications on our understanding of the evolution of sub-Neptune exoplanets. As a key step towards answering this question, we present a non-local thermodynamic equilibrium (NLTE) model of H2O for the atmospheric region where the gas accelerates to escape the planet and conditions relevant to close-in sub-Neptunes. Our exploratory calculations for isothermal gas composed of H2, H2O and e− reveal that: (1) In the pressure region ∼10−2–10−4 dyn cm−2 where the stellar extreme-ultraviolet (XUV) photons are typically deposited in the atmosphere, H2O is in rotational LTE but vibrational NLTE. Vibrational LTE is facilitated by high H2O abundances and fractional ionizations, and we report critical densities for the LTE-NLTE transition; (2) Vibrational cooling may locally dominate over rotational cooling, partly because of the comparatively small opacities of ro-vibrational lines; (3) Even low H2O abundances notably enhance the cooling, foreseeably offsetting some of the stellar heating; (4) Heating due to the deposition of stellar infrared (IR) photons is significant at pressures ≳0.1 dyn cm−2. We estimate the contribution of H2O excitation to the internal energy of the gas and speculate on the photodissociation from the excited vibrational states. Ultimately, our findings motivate the consideration of NLTE in the mass loss rate calculations of H2O-rich atmospheres.

Sculpting - A Modern Menace.

Sculpting is a common occupation in India. However, there have been no studies from India on sculpting-related silicosis. The aims of this study were to evaluate- 1. awareness of disease related to sculpting. 2. Clinical, radiological, and physiological parameters in "sculpting workers" suffering from silicosis. This was a retrospective evaluation of data collected during compensation visits for silicosis in workers of the sculpting industries. The data were collected between January 2021 to April 2023. A total of 114 patients were evaluated. All patients underwent clinical evaluation including awareness about the disease, chest radiography, high-resolution computed tomography (HRCT) scan of the chest, and spirometry. The majority of patients (109) (95%) did not use any personal protective equipment while at work and did not have any awareness regarding preventive measures. On chest radiography, small opacities (rounded or irregular) and large opacities were seen in 84 (73.7%) and 26 (22.8%) patients, respectively. The size of large opacities was significantly proportionate with duration of job (P = 0.019). HRCT chest was more sensitive compared to chest radiographs. 94 (82.4%) patients were having abnormal spirometric findings. The benefits of prevention of silica dust exposure and patient education considerably outweigh the benefits of early detection and treatment of silicosis, as there was an increase in the size of lesions with increasing duration of exposure. There should be a national health program on silicosis to protect worker's health.

Immune Analysis Using Vitreous Optical Coherence Tomography Imaging in Rats with Steroid-Induced Glaucoma.

Glaucoma is a multifactorial pathology involving the immune system. The subclinical immune response plays a homeostatic role in healthy situations, but in pathological situations, it produces imbalances. Optical coherence tomography detects immune cells in the vitreous as hyperreflective opacities and these are subsequently characterised by computational analysis. This study monitors the changes in immunity in the vitreous in two steroid-induced glaucoma (SIG) animal models created with drug delivery systems (microspheres loaded with dexamethasone and dexamethasone/fibronectin), comparing both sexes and healthy controls over six months. SIG eyes tended to present greater intensity and a higher number of vitreous opacities (p < 0.05), with dynamic fluctuations in the percentage of isolated cells (10 µm2), non-activated cells (10-50 µm2), activated cells (50-250 µm2) and cell complexes (>250 µm2). Both SIG models presented an anti-inflammatory profile, with non-activated cells being the largest population in this study. However, smaller opacities (isolated cells) seemed to be the first responder to noxa since they were the most rounded (recruitment), coinciding with peak intraocular pressure increase, and showed the highest mean Intensity (intracellular machinery), even in the contralateral eye, and a major change in orientation (motility). Studying the features of hyperreflective opacities in the vitreous using OCT could be a useful biomarker of glaucoma.

Feasibility of thoracoscopic monosubsegmentectomy for small ground-glass opacity dominant lung cancer

BackgroundMonosubsegmentectomy (MSS) involves removal of less lung parenchyma than monosegmentectomy (MS) does. However, the clinical efficacy of MSS in lung cancer treatment remains unclear, with concerns regarding insufficient surgical margins and increased complications. MethodsBetween February 2015 and December 2019, patients who underwent thoracoscopic MSS (n = 126) or MS (n = 678) for small ground-glass opacity (GGO) dominant lung cancer were examined. The primary endpoints were the procedure success rate (defined as resection with a surgical margin ≥2 cm or tumor size) and surgical margin. ResultsThere were no significant differences in age, sex, smoking history, or comorbidities between the groups. Both groups achieved a success rate of 100%. No significant group differences were observed in the number of lymph nodes removed (p = 0.060), overall complications (p = 0.147), or major complications (p = 0.450). The MSS group had a smaller surgical margin (median, 17 vs. 21mm, p < 0.001) and longer operative time (median, 138 vs. 130 min, p = 0.005) than the MS group did. Propensity score-matched analysis of 122 pairs of patients revealed consistent results. Surgical margins were further compared based on the number of resected subsegments. The 1 subsegment group had the smallest median surgical margin, followed by the 2 and 3 subsegments groups (17, 20, and 23 mm, p < 0.001). ConclusionsThoracoscopic MSS is an acceptable option for treating patients with small-sized GGO-dominant lung cancer. However, the close surgical margins and prolonged operative time should be considered.

Omitting Lymph Node Dissection for Small Ground-Glass Opacity–Dominant Tumors

BackgroundThe purpose of this study was to determine the optimal extent of lymph node dissection required in patients with small (≤3 cm) radiologically ground-glass opacity–dominant, peripheral, non-small cell lung cancer tumors. MethodsThe study analyzed the clinicopathologic findings and surgical outcomes of 988 patients with radiologic, ground-glass opacity–dominant non-small cell lung cancer without lymph node involvement who underwent complete resection of the primary tumor between 2010 and 2020. Patients were followed up for 54.5 months (median). Kaplan-Meier curves and the log-rank test were used in statistical analyses of the prognosis. ResultsMedian age, whole tumor size, solid tumor size, and maximum standardized uptake values were 68 years, 1.7 cm, 0.4 cm, and 0.9, respectively. Sixty percent of the cohort was female (n = 590). Wedge resection, segmentectomy, and lobectomy were performed in 206, 372, and 410 patients, respectively. A total of 982 of 988 (99%) tumors were adenocarcinomas. One patient had hilar lymph node involvement; however, no mediastinal lymph node metastasis or hilar or mediastinal lymph node recurrence was detected. The 5-year overall survival rate was 96.5% (95% CI, 94.8%-97.7%). Excellent survival outcomes were achieved regardless of procedure (wedge resection, 94.7% [95% CI, 89.1%-97.5%]; segmentectomy, 96.9% [95% CI, 93.7%-98.5%]; and lobectomy, 97.1% [95% CI, 94.4%-98.5%]). ConclusionsOmitting lymph node dissection may be acceptable with curative intent for small tumors with radiologic ground-glass opacity dominance. Appropriate surgical procedures such as wedge resection, segmentectomy, or lobectomy can provide satisfactory outcomes in patients with indolent tumors if surgical margins are secured.

Asian Intensive Reader of Pneumoconiosis program: examination for certification during 2008-2020.

This study examined physicians' participation and performance in the examinations administered by the Asian Intensive Reader of Pneumoconiosis (AIR Pneumo) program from 2008 to 2020 and compared radiograph readings of physicians who passed with those who failed the examinations. Demography of the participants, participation trends, pass/fail rates, and proficiency scores were summarized; differences in reading the radiographs for pneumoconiosis of physicians who passed the examinations and those who failed were evaluated.By December 2020, 555 physicians from 20 countries had taken certification examinations; the number of participants increased in recent years. Reported background specialty training and work experience varied widely. Passing rate and mean proficiency score for participants who passed were 83.4% and 77.6 ± 9.4 in certification, and 76.8% and 88.1 ± 4.5 in recertification examinations. Compared with physicians who passed the examinations, physicians who failed tended to classify test radiographs as positive for pneumoconiosis and read a higher profusion; they likely missed large opacities and pleural plaques and had a lower accuracy in recognizing the shape of small opacities. Findings suggest that physicians who failed the examination tend to over-diagnose radiographs as positive for pneumoconiosis with higher profusion and have difficulty in correctly identifying small opacity shape.

Image-guided video-assisted thoracoscopic surgery (iVATS): a single center experience and review.

Lung cancer screening techniques using low-dose computed tomography (LDCT) scans have improved over the last decade. This means that there is an increased rate of detection of small, often non-palpable, nodules and ground-glass opacities. Obtaining a definitive diagnosis of these nodules using techniques such as percutaneous image-guided biopsy or intraoperative localization is challenging, and these nodules have traditionally undergone routine surveillance. Image-guided video-assisted thoracoscopic surgery (iVATS), which is performed in a hybrid operating room, has made it more feasible to biopsy and resect these nodules. The first thoracic surgery hybrid operative room was introduced at our institution at Brigham and Women's Hospital. Herein, we describe our experience implementing this technique including the methods we used to train key personnel such as radiologists, surgeons, and anesthesiologists to ensure that this technique successfully translated to a clinical setting. We review the benefits of iVATS, which includes decreased rate of fiducial dislodgement, real-time imaging which facilitates successful fiducial placement, and smaller sized resection of lung parenchyma. We will also describe the comparisons between traditional diagnostic methods and iVATS, patient selection criteria and important technical details. Some centers describe alternative techniques for several of the technical aspects, including patient positioning, which we also mention. Lastly, we describe adverse events after iVATS, which are comparable to those seen after a standard VATS.

Bilateral dense coin-like lenticular opacities in an infant

A 6-month-old child with impaired vision was taken to a tertiary care hospital. Ocular examination revealed no abnormalities, but under anesthesia, ultrasonic biomicroscopy (UBM) found small, white, and dense lenticular opacities, which were further confirmed on the intraoperative clinical examination. The morphology of these coin-like opacities was distinct from previously described pediatric cataracts, being larger than those in cataract pulverulenta and thinner than “ant-eggs.” The child underwent lens aspiration, anterior vitrectomy, and intraocular lens (IOL) insertion. Understanding the unique morphology of this cataract may contribute to improved management of similar cases and deepen our knowledge of lens embryology and etiopathogenesis of cataract.

CT-based radiomic phenotypes of lung adenocarcinoma: a preliminary comparative analysis with targeted next-generation sequencing.

This study aimed to explore the relationship between computed tomography (CT)-based radiomic phenotypes and genomic profiles, including expression of programmed cell death-ligand 1 (PD-L1) and the 10 major genes, such as epidermal growth factor receptor (EGFR), tumor protein 53 (TP53), and Kirsten rat sarcoma viral oncogene (KRAS), in patients with lung adenocarcinoma (LUAD). In total, 288 consecutive patients with pathologically confirmed LUAD were enrolled in this retrospective study. Radiomic features were extracted from preoperative CT images, and targeted genomic data were profiled through next-generation sequencing. PD-L1 expression was assessed by immunohistochemistry staining (chi-square test or Fisher's exact test for categorical data and the Kruskal-Wallis test for continuous data). A total of 1,013 radiomic features were obtained from each patient's CT images. Consensus clustering was used to cluster patients on the basis of radiomic features. The 288 patients were classified according to consensus clustering into four radiomic phenotypes: Cluster 1 (n = 11) involving mainly large solid masses with a maximum diameter of 5.1 ± 2.0 cm; Clusters 2 and 3 involving mainly part-solid and solid masses with maximum diameters of 2.1 ± 1.4 cm and 2.1 ± 0.9 cm, respectively; and Cluster 4 involving mostly small ground-glass opacity lesions with a maximum diameter of 1.0 ± 0.9 cm. Differences in maximum diameter, PD-L1 expression, and TP53, EGFR, BRAF, ROS1, and ERBB2 mutations among the four clusters were statistically significant. Regarding targeted therapy and immunotherapy, EGFR mutations were highest in Cluster 2 (73.1%); PD-L1 expression was highest in Cluster 1 (45.5%). Our findings provide evidence that CT-based radiomic phenotypes could non-invasively identify LUADs with different molecular characteristics, showing the potential to provide personalized treatment decision-making support for LUAD patients.

Radiological and pathological analysis of the galaxy sign in patients with pulmonary mucosa-associated lymphoid tissue (MALT) lymphoma.

Pulmonary mucosa-associated lymphoid tissue (MALT) lymphoma sometimes presents as large pulmonary nodules composed of small nodular opacities (galaxy sign) on computed tomography (CT). The aim of this study was to assess the presence, usefulness, and pathological characteristics of the galaxy sign on CT of pulmonary MALT lymphoma. From January 2011 to December 2021, chest CTs of 43 patients with pulmonary MALT lymphoma were reviewed by two radiologists for the galaxy sign and various other findings. Interreader agreement to characterize the galaxy sign and factors associated in making a correct first impression on CT prior to pathological diagnosis were assessed. Resected specimens were reviewed by two pathologists, and the proportion of peripheral lymphoma infiltrates was compared between lesions with and without the galaxy sign. Of 43 patients, 22 patients (44.2%) showed the galaxy sign (κ = 0.768, p < 0.0001). The galaxy sign (p = 0.010) was associated with making a correct first impression on CT prior to pathological diagnosis. On pathological examination, lesions showing the galaxy sign on CT demonstrated a significantly higher proportion of peripheral lymphoma infiltrates (p = 0.001). The galaxy sign can be seen on CT of pulmonary MALT lymphoma with a higher proportion of peripheral lymphoma infiltrates and may be useful in making a correct diagnosis of pulmonary MALT lymphoma.

Efficacy of Near-Infrared Fluorescence Video-Assisted Thoracoscopic Surgery for Small Pulmonary Nodule Resection with Indocyanine Green Inhalation: A Randomized Clinical Trial.

Small pulmonary nodules (<3cm) can sometimes be unrecognizable and nonpalpable in video-assisted thoracoscopic surgery (VATS). Near-infrared fluorescence (NIF) VATS after indocyanine green (ICG) inhalation may effectively guide surgeons to locate the nodules. This study aimed to investigate the safety, feasibility, and efficacy of ICG inhalation-based NIF imaging for guiding small pulmonary nodule resections. Between February and May 2021, the first-stage, non-randomized trial enrolled 21 patients with different nodule depth, ICG inhalation doses, post-inhalation surgery times, and nodule types at a tertiary referral hospital. Between May 2021 and May 2022, the second-stage randomized trial enrolled 56 patients, who were randomly assigned to the fluorescence VATS (FLVATS) or the white-light VATS (WLVATS) group. The ratio of effective guidance and the time consumption for nodule localization were compared. The first-stage trial proved this new method is safe and feasible, and established a standardized protocol with optimized nodule depth (≤1cm), ICG dose (0.20-0.25 mg/kg), and surgery window (50-90min after ICG inhalation). In the second-stage trial, the FLVATS achieved 87.1% helpful nodule localization guidance, which was significantly higher than the WLVATS (59.1%, p<0.05). The mean nodule locating time (standard deviation) was 1.8 [0.9] and 3.3 [2.3] min, respectively. Surgeons adopting FLVATS were significantly faster (p<0.01), especially when locating small ground-glass opacities (1.3 [0.6] min vs. 7.0 [3.5] min, p<0.05). Five of 31 nodules (16.1%) were only detectable by FLVATS, whereas both white light and palpation failed. This new method is safe and feasible for small pulmonary nodule resection. It significantly improves nodule localization rates with less time consumption, and hence is highly worthy for clinical promotion. Clinical Trial Registration Chinese Clinical Trial Registry Identifier: ChiCTR2100047326.

Chest computed-tomography 1 day before the diagnosis of coronavirus disease 2019.

A 63-year-old man presented for the further examination of chest radiographic abnormality to exclude lung cancer on November 14, 2022. For annual screening of lung cancer, he had visited another division of our hospital on October 21, 2022. A nodule with irregular margins was pointed out by the low-dose chest computed-tomography (CT) (Figure 1(a)). He had flu-like symptoms with a fever of 39.0° after returning home, then he had been diagnosed coronavirus disease 2019 (COVID-19) by polymerase chain reaction test on October 22, 2022. After 10 days isolation and his symptom recovery, he visited us on November 14, 2022. Chest CT performed on the same day revealed small ground-glass opacity (GGO), which seemed to be in recovery phase (Figure 1(b)). We diagnosed the series of radiological findings as the pneumonia caused by COVID-19 infection. Although bilateral GGO and consolidation were reported as the predominant imaging characteristics in COVID-19, chest CT manifestations can vary in different patients and stages.1 This case is interesting, since the radiological findings of COVID-19 might have the possibility to mimic those of lung cancer. Clinicians should be aware of this characteristic radiological manifestation especially in case of early stage and mild COVID-19. All authors have contributed significantly, and that all authors are in agreement with the content of the manuscript: Conception/Design: Hiromichi Yamane and Nagio Takigawa; Collection of data: Nobuaki Ochi and Yasunari Nagasaki; Data analysis and interpretation: all authors; Manuscript writing: all authors; Final approval of manuscript: all authors. We thank Ms. Miki Nomura, a medical secretary of Sumitomo-Besshi Hospital Cancer Center, for her great effort on the clinical data collection. All authors listed on this manuscript have no conflicts of interest concerning this study.

Reticulation Sign on Thin-Section CT: Utility for Predicting Invasiveness of Pure Ground-Glass Nodules.

BACKGROUND. Pure ground-glass nodules (pGGNs) may represent a diverse range of histologic entities of varying aggressiveness. OBJECTIVE. The purpose of this study was to evaluate the use of the reticulation sign on thin-section CT images for predicting the invasiveness of pGGNs. METHODS. This retrospective study included 795 patients (mean age, 53.4 ± 11.1 [SD] years; 254 men, 541 women) with a total of 876 pGGNs on thin-section CT that underwent resection between January 2015 and April 2022. Two fellowship-trained thoracic radiologists independently reviewed unenhanced CT images to assess the pGGNs for a range of features, including diameter, attenuation, location, shape, air bronchogram, bubble lucency, vascular change, lobulation, spiculation, margins, pleural indentation, and the reticulation sign (defined as multiple small linear opacities resembling a mesh or a net); differences were resolved by consensus. The relationship between the reticulation sign and lesion invasiveness on pathologic assessment was evaluated. RESULTS. On pathologic assessment, the 876 pGGNs included 163 nonneoplastic and 713 neoplastic pGGNs (323 atypical adenomatous hyperplasias [AAHs] or adenocarcinomas in situ [AISs], 250 minimally invasive adenocarcinomas [MIAs], and 140 invasive adenocarcinomas [IACs]). Interobserver agreement for the reticulation sign, expressed as kappa, was 0.870. The reticulation sign was detected in 0.0% of nonneoplastic lesions, 0.0% of AAHs/AISs, 6.8% of MIAs, and 54.3% of IACs. The reticulation sign had sensitivity of 24.0% and specificity of 100.0% for a diagnosis of MIA or IAC and sensitivity of 54.3% and specificity of 97.7% for a diagnosis of IAC. In multivariable regression analyses including all of the assessed CT features, the reticulation sign was a significant independent predictor of IAC (OR, 3.64; p = .001) but was not a significant independent predictor of MIA or IAC. CONCLUSION. The reticulation sign, when observed in a pGGN on thin-section CT, has high specificity (albeit low sensitivity) for invasiveness and is an independent predictor of IAC. CLINICAL IMPACT. Those pGGNs that show the reticulation sign should be strongly suspected to represent IAC; this suspicion may guide risk assessments and follow-up recommendations.

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.

Application of a light-weighted convolutional neural network for automatic recognition of coal workers' pneumoconiosis in the early stage

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.