HRCT diagnosis of diffuse parenchymal lung disease: inter-observer variation

Evaluating inter-and intra-rater reliability in the bronchoscopic grading of burn inhalation injury: The iBRONCH-BII study

BACKGROUND

The evidence that the severity of burn inhalation injury (BII) impacts clinical outcomes is inconsistent. This may be due to misclassification arising from the subjectivity in bronchoscopically grading BII using systems such as the Abbreviated Injury Score (AIS). This study aimed to evaluate inter- and intra-rater reliability in the grading of BII using the AIS.

METHODOLOGY

In a cohort study, specialist burns clinicians (n = 17) and novices (n = 10) graded sixteen BII bronchoscopic images using the AIS during an online meeting. Inter-rater reliability was evaluated using the Kappa statistic (k), with values < 0.60 considered clinically inadequate. The grade rating process was repeated after seven days to evaluate intra-rater reliability. Evaluation of reliability in the grading of BII bronchoscopy reports was conducted as a sensitivity analysis.

RESULTS

Amongst all raters, inter-rater reliability was low for grading images (k = 0.30, 95 % confidence interval (CI): 0.29-0.31). Intra-rater reliability was higher than inter-rater reliability, but was still low, with median image grade rate k = 0.45 (interquartile range [IQR]:0.24-0.53). Intensivists demonstrated the highest rater reliability.

CONCLUSION

Reliability in rating the grade of BII by bronchoscopic images was clinically inadequate. Strategies to improve the reliability of reporting the grade of BII are required.

The potential of semi-quantitative and quantitative methods in predicting progression in rheumatoid arthritis-associated interstitial lung disease

INTRODUCTION

Rheumatoid arthritis-associated interstitial lung disease (RA-ILD) presents with variable severity and progression, highlighting the need for effective tools to identify patients at risk. Although CT imaging plays a vital role in the management of RA-ILD, there is a lack of objective methods to predict disease progression. This study investigates the association between semi-quantitative and quantitative CT scoring methods and disease progression in early-stage RA-ILD.

METHODS

This observational study analyzed baseline and the first technically evaluable follow-up CT scans of patients who met the 2010 ACR/EULAR classification criteria for RA and were diagnosed with ILD. Only patients with ≤ 5 years between baseline and follow-up scans were included. Semi-quantitative assessments were conducted using the Goh and Warrick scoring systems, while quantitative analyses utilized Vitrea software to measure mean lung attenuation (MLA) and low-, medium-, and high-density lung volumes. Progression risk factors were evaluated using binary logistic regression, with progression defined by changes in CT parameters over time.

RESULTS

A total of 77 RA-ILD patients (45 females, 32 males) were included, with a median follow-up period of 20 months (interquartile range: 7.4-46 months). Disease progression was observed in 34 patients (44.2%). Baseline medium-density volume (MDV), follow-up mean lung attenuation (MLA), and low-density volume (LDV) differed significantly between the progression and non-progression groups (p < 0.05). Quantitative CT parameters demonstrated strong correlations with both the Goh and Warrick scoring systems. Binary logistic regression analysis identified the usual interstitial pneumonia (UIP) pattern on baseline imaging as the only independent predictor of disease progression (odds ratio: 3.1; 95% confidence interval: 1.1-12.4).

CONCLUSION

In this study of early-stage RA-ILD patients, only the usual interstitial pneumonia (UIP) pattern on baseline HRCT independently predicted disease progression. Neither semi-quantitative scores nor quantitative CT parameters were predictive of progression. However, quantitative CT metrics demonstrated strong correlations with traditional scoring systems, supporting their utility in objectively assessing disease extent.

Diagnosis of Fibrotic Interstitial Lung Diseases Based on the Combination of Label-Free Quantitative Multiphoton Fiber Histology and Machine Learning

Interstitial lung disease (ILD), characterized by inflammation and fibrosis, often suffers from low diagnostic accuracy and consistency. Traditional hematoxylin and eosin (H&E) staining primarily reveals cellular inflammation with limited detail on fibrosis. To address these issues, we introduce a pioneering label-free quantitative multiphoton fiber histology (MPFH) technique that delineates the intricate characteristics of collagen and elastin fibers for ILD diagnosis. We acquired colocated multiphoton and H&E-stained images from a single tissue slice. Multiphoton imaging was performed on the deparaffinized section to obtain fibrotic tissue information, followed by H&E staining to capture cellular information. This approach was tested in a blinded diagnostic trial among 7 pathologists involving 14 patients with relatively normal lung and 31 patients with ILD (11 idiopathic pulmonary fibrosis/usual interstitial pneumonia, 14 nonspecific interstitial pneumonia, and 6 pleuroparenchymal fibroelastosis). A customized algorithm extracted quantitative fiber indicators from multiphoton images. These indicators, combined with clinical and radiologic features, were used to develop an automatic multiclass ILD classifier. Using MPFH, we can acquire high-quality, colocalized images of collagen fibers, elastin fibers, and cells. We found that the type, distribution, and degree of fibrotic proliferation can effectively distinguish between different subtypes. The blind study showed that MPFH enhanced diagnostic consistency (κ values from 0.56 to 0.72) and accuracy (from 73.0% to 82.5%, P = .0090). The combination of quantitative fiber indicators effectively distinguished between different tissues, with areas under the receiver operating characteristic curves exceeding 0.92. The automatic classifier achieved 93.8% accuracy, closely paralleling the 92.2% accuracy of expert pathologists. The outcomes of our research underscore the transformative potential of MPFH in the field of fibrotic-ILD diagnostics. By integrating quantitative analysis of fiber characteristics with advanced machine learning algorithms, MPFH facilitates the automatic and accurate identification of various fibrotic disease subtypes, showcasing a significant leap forward in precision diagnostics.

Automated AI-based image analysis for quantification and prediction of interstitial lung disease in systemic sclerosis patients

BACKGROUND

Systemic sclerosis (SSc) is a rare connective tissue disease associated with rapidly evolving interstitial lung disease (ILD), driving its mortality. Specific imaging-based biomarkers associated with the evolution of lung disease are needed to help predict and quantify ILD.

METHODS

We evaluated the potential of an automated ILD quantification system (icolung®) from chest CT scans, to help in quantification and prediction of ILD progression in SSc-ILD. We used a retrospective cohort of 75 SSc-ILD patients to evaluate the potential of the AI-based quantification tool and to correlate image-based quantification with pulmonary function tests and their evolution over time.

RESULTS

We evaluated a group of 75 patients suffering from SSc-ILD, either limited or diffuse, of whom 30 presented progressive pulmonary fibrosis (PPF). The patients presenting PPF exhibited more extensive lesions (in % of total lung volume (TLV)) based on image analysis than those without PPF: 3.93 (0.36-8.12)* vs. 0.59 (0.09-3.53) respectively, whereas pulmonary functional test showed a reduction in Force Vital Capacity (FVC)(pred%) in patients with PPF compared to the others : 77 ± 20% vs. 87 ± 19% (p < 0.05). Modifications of FVC and diffusing capacity of the lungs for carbon monoxide (DLCO) over time were correlated with longitudinal radiological ILD modifications (r=-0.40, p < 0.01; r=-0.40, p < 0.01 respectively).

CONCLUSION

AI-based automatic quantification of lesions from chest-CT images in SSc-ILD is correlated with physiological parameters and can help in disease evaluation. Further clinical multicentric validation is necessary in order to confirm its potential in the prediction of patient's outcome and in treatment management.

Artificial intelligence-based quantification of pulmonary HRCT (AIqpHRCT) for the evaluation of interstitial lung disease in patients with inflammatory rheumatic diseases

High-resolution computed tomography (HRCT) is important for diagnosing interstitial lung disease (ILD) in inflammatory rheumatic disease (IRD) patients. However, visual ILD assessment via HRCT often has high inter-reader variability. Artificial intelligence (AI)-based techniques for quantitative image analysis promise more accurate diagnostic and prognostic information. This study evaluated the reliability of artificial intelligence-based quantification of pulmonary HRCT (AIqpHRCT) in IRD-ILD patients and verified IRD-ILD quantification using AIqpHRCT in the clinical setting. Reproducibility of AIqpHRCT was verified for each typical HRCT pattern (ground-glass opacity [GGO], non-specific interstitial pneumonia [NSIP], usual interstitial pneumonia [UIP], granuloma). Additional, 50 HRCT datasets from 50 IRD-ILD patients using AIqpHRCT were analysed and correlated with clinical data and pulmonary lung function parameters. AIqpHRCT presented 100% agreement (coefficient of variation = 0.00%, intraclass correlation coefficient = 1.000) regarding the detection of the different HRCT pattern. Furthermore, AIqpHRCT data showed an increase of ILD from 10.7 ± 28.3% (median = 1.3%) in GGO to 18.9 ± 12.4% (median = 18.0%) in UIP pattern. The extent of fibrosis negatively correlated with FVC (ρ=-0.501), TLC (ρ=-0.622), and DLCO (ρ=-0.693) (p < 0.001). GGO measured by AIqpHRCT also significant negatively correlated with DLCO (ρ=-0.699), TLC (ρ=-0.580) and FVC (ρ=-0.423). For the first time, the study demonstrates that AIpqHRCT provides a highly reliable method for quantifying lung parenchymal changes in HRCT images of IRD-ILD patients. Further, the AIqpHRCT method revealed significant correlations between the extent of ILD and lung function parameters. This highlights the potential of AIpqHRCT in enhancing the accuracy of ILD diagnosis and prognosis in clinical settings, ultimately improving patient management and outcomes.

Innovations in the care of childhood interstitial lung disease associated with connective tissue disease and immune-mediated disorders

Childhood interstitial lung disease (chILD) associated with connective tissue and immune mediated disorders is the second most common chILD diagnostic category. As knowledge of the molecular and genetic underpinnings of these rare disorders advances, the recognized clinical spectrum of associated pulmonary manifestations continues to expand. Pulmonary complications of these diseases, including ILD, confer increased risk for morbidity and mortality and contribute to increased complexity for providers tasked with managing the multiple organ systems that can be impacted in these systemic disorders. While pulmonologists play an important role in diagnosis and management of these conditions, thankfully they do not have to work alone. In collaboration with a multidisciplinary team of subspecialists, the pulmonary and other systemic manifestations of these conditions can be managed effectively together. The goal of this review is to familiarize the reader with the classic patterns of chILD and other pulmonary complications associated with primary immune-mediated disorders (monogenic inborn errors of immunity) and acquired systemic autoimmune and autoinflammatory diseases. In addition, this review will highlight current, emerging, and innovative therapeutic strategies and will underscore the important role of multidisciplinary management to improving outcomes for these patients.

Analysis of Validation Performance of a Machine Learning Classifier in Interstitial Lung Disease Cases Without Definite or Probable Usual Interstitial Pneumonia Pattern on CT Using Clinical and Pathology-Supported Diagnostic Labels

We previously validated Fibresolve, a machine learning classifier system that non-invasively predicts idiopathic pulmonary fibrosis (IPF) diagnosis. The system incorporates an automated deep learning algorithm that analyzes chest computed tomography (CT) imaging to assess for features associated with idiopathic pulmonary fibrosis. Here, we assess performance in assessment of patterns beyond those that are characteristic features of usual interstitial pneumonia (UIP) pattern. The machine learning classifier was previously developed and validated using standard training, validation, and test sets, with clinical plus pathologically determined ground truth. The multi-site 295-patient validation dataset was used for focused subgroup analysis in this investigation to evaluate the classifier's performance range in cases with and without radiologic UIP and probable UIP designations. Radiologic assessment of specific features for UIP including the presence and distribution of reticulation, ground glass, bronchiectasis, and honeycombing was used for assignment of radiologic pattern. Output from the classifier was assessed within various UIP subgroups. The machine learning classifier was able to classify cases not meeting the criteria for UIP or probable UIP as IPF with estimated sensitivity of 56-65% and estimated specificity of 92-94%. Example cases demonstrated non-basilar-predominant as well as ground glass patterns that were indeterminate for UIP by subjective imaging criteria but for which the classifier system was able to correctly identify the case as IPF as confirmed by multidisciplinary discussion generally inclusive of histopathology. The machine learning classifier Fibresolve may be helpful in the diagnosis of IPF in cases without radiological UIP and probable UIP patterns.

Role of Multidisciplinary Team Meetings in the Diagnosis and Management of Diffuse Parenchymal Lung Diseases in a Tertiary Care Hospital

Background  Decisions on the management of interstitial lung diseases (ILD) and prognostication require an accurate diagnosis. It has been proposed that multidisciplinary team (MDT) meetings for ILD (ILD-MDT) improve these decisions in challenging cases of ILD. However, most studies in this field have been based on the decisions of individual clinicians and there are few reports on the outcomes of the ILD-MDT approach. We therefore describe the experience of the ILD-MDT meetings at our institution. Methods  A single-center retrospective review of the electronic health care records of patients discussed in the ILD-MDT meetings at our institution from February 2016 to January 2021 was performed. At out institution, at each ILD-MDT meeting, the referring pulmonologist presents the clinical history and the results of all relevant investigations including serology, blood gas analyses, lung function tests, bronchoscopy, and bronchoalveolar lavage. A radiologist then describes the imaging including serial computed tomography (CT) scans. When available, the findings on lung biopsy are presented by a pathologist. Subsequent discussions lead to a consensus on the diagnosis and further management. Results  The study included 121 patients, comprising 71 (57%) males and 76 nonsmokers (62.8%), with a mean age of 65 years (range: 25-93 years). The average number of comorbidities was 2.4 (range: 0-7). Imaging-based diagnoses were usual interstitial pneumonia (UIP)/chronic hypersensitivity pneumonitis (CHP) in 32 (26%) patients, UIP in 20 (17%) patients, probable UIP in 27 (22%) patients, nonspecific interstitial pneumonia in 11 (9%) patients, and indeterminate interstitial lung abnormalities (ILA) in 10 (8%) patients. The most common consensus clinical diagnosis after an ILD-MDT discussion was chronic hypersensitivity pneumonitis/idiopathic pulmonary fibrosis in 17 patients (14%), followed by idiopathic pulmonary fibrosis and connective tissue disease associated interstitial lung disease in 16 patients (13%), CHP in 11 patients (9.1%), and ILA in 10 patients (8.4%). Only a 42 patients (35%) required surgical lung biopsy for confirmation of the diagnosis. Conclusion  This study describes the characteristics of the patients discussed in the ILD-MDT meetings with emphasis on their clinical, radiological, and laboratory data to reach a diagnosis and management plan. The decisions on commencement of antifibrotics or immunosuppressive therapy for patients with various ILDs are also made during these ILD-MDT meetings. This descriptive study could help other health care professionals regarding the structure of their ILD-MDT meetings and with discussions about diagnostic and care decisions for diffused parenchymal lung disease patients.

Generative Adversarial Network-Based Image Conversion Among Different Computed Tomography Protocols and Vendors: Effects on Accuracy and Variability in Quantifying Regional Disease Patterns of Interstitial Lung Disease

OBJECTIVE

To assess whether computed tomography (CT) conversion across different scan parameters and manufacturers using a routable generative adversarial network (RouteGAN) can improve the accuracy and variability in quantifying interstitial lung disease (ILD) using a deep learning-based automated software.

MATERIALS AND METHODS

This study included patients with ILD who underwent thin-section CT. Unmatched CT images obtained using scanners from four manufacturers (vendors A-D), standard- or low-radiation doses, and sharp or medium kernels were classified into groups 1-7 according to acquisition conditions. CT images in groups 2-7 were converted into the target CT style (Group 1: vendor A, standard dose, and sharp kernel) using a RouteGAN. ILD was quantified on original and converted CT images using a deep learning-based software (Aview, Coreline Soft). The accuracy of quantification was analyzed using the dice similarity coefficient (DSC) and pixel-wise overlap accuracy metrics against manual quantification by a radiologist. Five radiologists evaluated quantification accuracy using a 10-point visual scoring system.

RESULTS

Three hundred and fifty CT slices from 150 patients (mean age: 67.6 ± 10.7 years; 56 females) were included. The overlap accuracies for quantifying total abnormalities in groups 2-7 improved after CT conversion (original vs. converted: 0.63 vs. 0.68 for DSC, 0.66 vs. 0.70 for pixel-wise recall, and 0.68 vs. 0.73 for pixel-wise precision; P < 0.002 for all). The DSCs of fibrosis score, honeycombing, and reticulation significantly increased after CT conversion (0.32 vs. 0.64, 0.19 vs. 0.47, and 0.23 vs. 0.54, P < 0.002 for all), whereas those of ground-glass opacity, consolidation, and emphysema did not change significantly or decreased slightly. The radiologists' scores were significantly higher (P < 0.001) and less variable on converted CT.

CONCLUSION

CT conversion using a RouteGAN can improve the accuracy and variability of CT images obtained using different scan parameters and manufacturers in deep learning-based quantification of ILD.

The Evolving Concept of the Multidisciplinary Approach in the Diagnosis and Management of Interstitial Lung Diseases

BACKGROUND

Interstitial lung diseases (ILDs) are a group of heterogeneous diseases characterized by inflammation and/or fibrosis of the lung interstitium, leading to a wide range of clinical manifestations and outcomes. Over the years, the literature has demonstrated the increased diagnostic accuracy and confidence associated with a multidisciplinary approach (MDA) in assessing diseases involving lung parenchyma. This approach was recently emphasized by the latest guidelines from the American Thoracic Society, European Respiratory Society, Japanese Respiratory Society, and Latin American Thoracic Association for the diagnosis of ILDs.

METHODS

In this review, we will discuss the role, composition, and timing of multidisciplinary diagnosis (MDD) concerning idiopathic pulmonary fibrosis, connective tissue disease associated with ILDs, hypersensitive pneumonia, and idiopathic pneumonia with autoimmune features, based on the latest recommendations for their diagnosis.

RESULTS

The integration of clinical, radiological, histopathological, and, often, serological data is crucial in the early identification and management of ILDs, improving patient outcomes. Based on the recent endorsement of transbronchial cryo-biopsy in idiopathic pulmonary fibrosis guidelines, an MDA helps guide the choice of the sampling technique, obtaining the maximum diagnostic performance, and avoiding the execution of more invasive procedures such as a surgical lung biopsy. A multidisciplinary team should include pulmonologists, radiologists, pathologists, and, often, rheumatologists, being assembled regularly to achieve a consensus diagnosis and to review cases in light of new features.

CONCLUSIONS

The literature highlighted that an MDA is essential to improve the accuracy and reliability of ILD diagnosis, allowing for the early optimization of therapy and reducing the need for invasive procedures. The multidisciplinary diagnosis of ILDs is an ongoing and dynamic process, often referred to as a "working diagnosis", involving the progressive integration and re-evaluation of clinical, radiological, and histological features.

Influence of thoracic radiology training on classification of interstitial lung diseases

INTRODUCTION

Interpretation of high-resolution CT images plays an important role in the diagnosis and management of interstitial lung diseases. However, interreader variation may exist due to varying levels of training and expertise. This study aims to evaluate interreader variation and the role of thoracic radiology training in classifying interstitial lung disease (ILD).

METHODS

This is a retrospective study where seven physicians (radiologists, thoracic radiologists, and a pulmonologist) classified the subtypes of ILD of 128 patients from a tertiary referral center, all selected from the Interstitial Lung Disease Registry which consists of patients from November 2014 to January 2021. Each patient was diagnosed with a subtype of interstitial lung disease by a consensus diagnosis from pathology, radiology, and pulmonology. Each reader was provided with only clinical history, only CT images, or both. Reader sensitivity and specificity and interreader agreements using Cohen's κ were calculated.

RESULTS

Interreader agreement based only on clinical history, only on radiologic information, or combination of both was most consistent amongst readers with thoracic radiology training, ranging from fair (Cohen's κ: 0.2-0.46), moderate to almost perfect (Cohen's κ: 0.55-0.92), and moderate to almost perfect (Cohen's κ: 0.53-0.91) respectively. Radiologists with any thoracic training showed both increased sensitivity and specificity for NSIP as compared to other radiologists and the pulmonologist when using only clinical history, only CT information, or combination of both (p < 0.05).

CONCLUSIONS

Readers with thoracic radiology training showed the least interreader variation and were more sensitive and specific at classifying certain subtypes of ILD.

SUMMARY SENTENCE

Thoracic radiology training may improve sensitivity and specificity in classifying ILD based on HRCT images and clinical history.

Prognostic value of deep learning-based fibrosis quantification on chest CT in idiopathic pulmonary fibrosis

OBJECTIVE

To investigate the prognostic value of deep learning (DL)-driven CT fibrosis quantification in idiopathic pulmonary fibrosis (IPF).

METHODS

Patients diagnosed with IPF who underwent nonenhanced chest CT and spirometry between 2005 and 2009 were retrospectively collected. Proportions of normal (CT-Norm%) and fibrotic lung volume (CT-Fib%) were calculated on CT using the DL software. The correlations of CT-Norm% and CT-Fib% with forced vital capacity (FVC) and diffusion capacity of carbon monoxide (D_LCO) were evaluated. The multivariable-adjusted hazard ratios (HRs) of CT-Norm% and CT-Fib% for overall survival were calculated with clinical and physiologic variables as covariates using Cox regression. The feasibility of substituting CT-Norm% for D_LCO in the GAP index was investigated using time-dependent areas under the receiver operating characteristic curve (TD-AUCs) at 3 years.

RESULTS

In total, 161 patients (median age [IQR], 68 [62-73] years; 104 men) were evaluated. CT-Norm% and CT-Fib% showed significant correlations with FVC (Pearson's r, 0.40 for CT-Norm% and - 0.37 for CT-Fib%; both p < 0.001) and D_LCO (0.52 for CT-Norm% and - 0.46 for CT-Fib%; both p < 0.001). On multivariable Cox regression, both CT-Norm% and CT-Fib% were independent prognostic factors when adjusted to age, sex, smoking status, comorbid chronic diseases, FVC, and D_LCO (HRs, 0.98 [95% CI 0.97-0.99; p < 0.001] for CT-Norm% at 3 years and 1.03 [1.01-1.05; p = 0.01] for CT-Fib%). Substituting CT-Norm% for D_LCO showed comparable discrimination to the original GAP index (TD-AUC, 0.82 [0.78-0.85] vs. 0.82 [0.79-0.86]; p = 0.75).

CONCLUSION

CT-Norm% and CT-Fib% calculated using chest CT-based deep learning software were independent prognostic factors for overall survival in IPF.

KEY POINTS

• Normal and fibrotic lung volume proportions were automatically calculated using commercial deep learning software from chest CT taken from 161 patients diagnosed with idiopathic pulmonary fibrosis. • CT-quantified volumetric parameters from commercial deep learning software were correlated with forced vital capacity (Pearson's r, 0.40 for normal and - 0.37 for fibrotic lung volume proportions) and diffusion capacity of carbon monoxide (Pearson's r, 0.52 and - 0.46, respectively). • Normal and fibrotic lung volume proportions (hazard ratios, 0.98 and 1.04; both p < 0.001) independently predicted overall survival when adjusted for clinical and physiologic variables.

A multidisciplinary approach to the diagnosis of antisynthetase syndrome

Antisynthetase syndrome is a subtype of idiopathic inflammatory myopathy, strongly associated with the presence of interstitial lung disease. Diagnosis is made by identifying myositis-specific antibodies directed against aminoacyl tRNA synthetase, and relevant clinical and radiologic features. Given the multisystem nature of the disease, diagnosis requires the careful synthesis of subtle clinical and radiological features with the interpretation of specialized autoimmune serological testing. This is provided in a multidisciplinary environment with input from rheumatologists, respiratory physicians, and radiologists. Differentiation from other idiopathic interstitial lung diseases is key; treatment and prognosis differ between patients with antisynthetase syndrome and idiopathic interstitial lung disease. In this review article, we look at the role of the multidisciplinary team and its individual members in the initial diagnosis of the antisynthetase syndrome, including the role of physicians, radiologists, and the wider team.

Chest high-resolution computed tomography can make higher accurate stages for thoracic sarcoidosis than X-ray

Background

To explore if chest high-resolution computed tomography (HRCT) can make higher accurate stages for thoracic sarcoidosis stage than X-ray (CRX) only.

Methods

Clinical data from medical records of consecutive patients with a confirmed diagnosis of pulmonary sarcoidosis at Shanghai Pulmonary Hospital from January 1 2012 to December 31 2016 and consecutive patients treated at the Sarcoidosis Center of University of Cincinnati Medical Center, Ohio, USA from January 1 2010 to December 31 2015 were reviewed. The clinical records of 227 patients diagnosed with sarcoidosis (140 Chinese and 87 American) were reviewed. Their sarcoidosis stage was determined by three thoracic radiologists based on CXR and HRCT presentations, respectively. The stage determined from CXR was compared with that determined from HRCT.

Results

Overall, 50.2% patients showed discordant sarcoidosis stage between CXR and HRCT (52.9% in Chinese and 44.8% in American, respectively). The primary reason for inconsistent stage between CXR and HRCT was failure to detect mediastinal lymph node enlargement in the shadow of the heart in CXR (22.1%) and small nodules because of the limited resolution of CXR (56.6%). Stage determined from HRCT negatively correlated with carbon monoxide diffusing capacity (DLCO) significantly (P < .01) but stage determined from CXR did not. Pleural involvement was detected by HRCT in 58 (25.6%) patients but only in 17 patients (7.5%) by CXR. Patients with pleural involvement had significantly lower forced vital capacity and DLCO than patients without it (both P < .05).

Conclusion

Revised staging criteria based on HRCT presentations included 5 stages with subtypes in the presence of pleural involvement were proposed. Thoracic sarcoidosis can be staged more accurately based on chest HRCT presentations than based on CXR presentations. Pleural involvement can be detected more accurately by HRCT.

Artificial Intelligence for Interstitial Lung Disease Analysis on Chest Computed Tomography: A Systematic Review

RATIONALE AND OBJECTIVES

High-resolution computed tomography (HRCT) is paramount in the assessment of interstitial lung disease (ILD). Yet, HRCT interpretation of ILDs may be hampered by inter- and intra-observer variability. Recently, artificial intelligence (AI) has revolutionized medical image analysis. This technology has the potential to advance patient care in ILD. We aimed to systematically evaluate the application of AI for the analysis of ILD in HRCT.

MATERIALS AND METHODS

We searched MEDLINE/PubMed databases for original publications of deep learning for ILD analysis on chest CT. The search included studies published up to March 1, 2021. The risk of bias evaluation included tailored Quality Assessment of Diagnostic Accuracy Studies and the modified Joanna Briggs Institute Critical Appraisal checklist.

RESULTS

Data was extracted from 19 retrospective studies. Deep learning techniques included detection, segmentation, and classification of ILD on HRCT. Most studies focused on the classification of ILD into different morphological patterns. Accuracies of 78%-91% were achieved. Two studies demonstrated near-expert performance for the diagnosis of idiopathic pulmonary fibrosis (IPF). The Quality Assessment of Diagnostic Accuracy Studies tool identified a high risk of bias in 15/19 (78.9%) of the studies.

CONCLUSION

AI has the potential to contribute to the radiologic diagnosis and classification of ILD. However, the accuracy performance is still not satisfactory, and research is limited by a small number of retrospective studies. Hence, the existing published data may not be sufficiently reliable. Only well-designed prospective controlled studies can accurately assess the value of existing AI tools for ILD evaluation.

A CT Algorithm Can Elevate the Differential Diagnosis of Interstitial Lung Disease by Non-specialists to Equal That of Specialist Thoracic Radiologists

BACKGROUND

Diagnosis of diffuse parenchymal lung diseases (DPLD) on high resolution CT (HRCT) is difficult for non-expert radiologists due to varied presentation for any single disease and overlap in presentation between diseases.

RATIONALE AND OBJECTIVES

To evaluate whether a pattern-based training algorithm can improve the ability of non-experts to diagnosis of DPLD.

MATERIALS AND METHODS

Five experts (cardiothoracic-trained radiologists), and 25 non-experts (non-cardiothoracic-trained radiologists, radiology residents, and pulmonologists) were each assigned a semi-random subset of cases from a compiled database of DPLD HRCTs. Each reader was asked to create a top three differential for each case. The non-experts were then given a pattern-based training algorithm for identifying DPLDs. Following training, the non-experts were again asked to create a top three differential for each case that they had previously evaluated. Accuracy between groups was compared using Chi-Square analysis.

RESULTS

A total of 400 and 1450 studies were read by experts and non-experts, respectively. Experts correctly placed the diagnosis as the first item on the differential versus having the correct diagnosis as one of their top three diagnoses at an overall rate of 48 and 64.3%, respectively. Pre-training, non-experts achieved a correct diagnosis/top three of 32.5 and 49.7%, respectively. Post-training, non-experts demonstrated a correct diagnosis/top three of 41.2 and 65%, a statistically significant increase (p < 0.0001). In addition, post training, there was no difference between non-experts and experts in placing the correct diagnosis within their top three differential.

CONCLUSION

The diagnosis of DPLDs by HRCT imaging alone is relatively poor. However, use of a pattern-based teaching algorithm can improve non-expert interpretation and enable non-experts to include the correct diagnosis within their differential diagnoses at a rate comparable to expert cardiothoracic trained radiologists.

Machine learning for lung texture analysis on thin-section CT: Capability for assessments of disease severity and therapeutic effect for connective tissue disease patients in comparison with expert panel evaluations

BACKGROUND

The need for quantitative assessment of interstitial lung involvement on thin-section computed tomography (CT) has arisen in interstitial lung diseases including connective tissue disease (CTD).

PURPOSE

To evaluate the capability of machine learning (ML)-based CT texture analysis for disease severity and treatment response assessments in comparison with qualitatively assessed thin-section CT for patients with CTD.

MATERIAL AND METHODS

A total of 149 patients with CTD-related ILD (CTD-ILD) underwent initial and follow-up CT scans (total 364 paired serial CT examinations), pulmonary function tests, and serum KL-6 level tests. Based on all follow-up examination results, all paired serial CT examinations were assessed as "Stable" (n = 188), "Worse" (n = 98) and "Improved" (n = 78). Next, quantitative index changes were determined by software, and qualitative disease severity scores were assessed by consensus of two radiologists. To evaluate differences in each quantitative index as well as in disease severity score between paired serial CT examinations, Tukey's honestly significant difference (HSD) test was performed among the three statuses. Stepwise regression analyses were performed to determine changes in each pulmonary functional parameter and all quantitative indexes between paired serial CT scans.

RESULTS

Δ% normal lung, Δ% consolidation, Δ% ground glass opacity, Δ% reticulation, and Δdisease severity score showed significant differences among the three statuses (P < 0.05). All differences in pulmonary functional parameters were significantly affected by Δ% normal lung, Δ% reticulation, and Δ% honeycomb (0.16 ≤r² ≤0.42; P < 0.05).

CONCLUSION

ML-based CT texture analysis has better potential than qualitatively assessed thin-section CT for disease severity assessment and treatment response evaluation for CTD-ILD.

Radiographic Graft Surveillance in Lung Transplantation: Prognostic Role of Parametric Response Mapping

RATIONALE

Chronic lung allograft dysfunction (CLAD) results in significant morbidity following lung transplantation. Potential CLAD occurs when lung function declines to 80-90% of baseline. Better non-invasive tools to prognosticate at potential CLAD are needed.

OBJECTIVES

To determine if parametric response mapping (PRM), a CT voxel-wise methodology, applied to high resolution CT scans can identify patients at risk of progression to CLAD or death.

METHODS

Radiographic features and PRM-based CT metrics quantifying functional small airways disease (PRMfSAD) and parenchymal disease (PRMPD) were studied at potential CLAD (n=61). High PRMfSAD and high PRMPD were defined as ≥ 30%. Restricted mean modeling was performed to compare CLAD-free survival among groups.

MEASUREMENTS AND MAIN RESULTS

PRM metrics identified 3 unique signatures: high PRMfSAD (11.5%), high PRMPD (41%) and neither (PRMNormal; 47.5%). Patients with high PRMfSAD or PRMPD had shorter CLAD-free median survival times (0.46 years and 0.50 years) compared to patients with predominantly PRMNormal (2.03 years; p=0.004 and 0.007 compared to PRMfSAD and PRMPD groups, respectively). In multivariate modeling adjusting for single versus double lung transplant, age at transplant, BMI at potential CLAD, and time from transplant to CT, PRMfSAD or PRMPD ≥ 30% continue to be statistically significant predictors of shorter CLAD-free survival. Air trapping by radiologist interpretation was common (66%), similar across PRM groups, and was not predictive of CLAD-free survival. Ground glass opacities by radiologist read occurred in 16% of cases and was associated with decreased CLAD-free survival (p<0.001).

CONCLUSIONS

PRM analysis offers valuable prognostic information at potential CLAD, identifying patients most at risk of developing CLAD or death.

Essential Features of an Interstitial Lung Disease Multidisciplinary Meeting: An International Delphi Survey

RATIONALE

The interstitial lung disease (ILD) multidisciplinary meetings (MDM) composing of pulmonologists, radiologists and pathologists, is integral to the rendering of an accurate ILD diagnosis. However, there is significant heterogeneity in the conduct of ILD MDMs and questions regarding its best practice remain unanswered.

OBJECTIVE

To achieve consensus among ILD experts on essential components of an ILD MDM.

METHODS

Using a Delphi methodology, semi structured interviews with ILD experts were used to identify key themes and features of ILD MDMs. These items informed two subsequent rounds of online questionnaires that were used to achieve consensus among a broader, international panel of ILD experts. Experts were asked to rate their level of agreement on a five-point Likert scale. An a priori threshold for consensus was set at a median score 4 or 5 with an interquartile range of 0.

RESULTS

We interviewed 15 ILD experts and 102 ILD experts participated in the online questionnaires. Five items and two exploratory statements achieved consensus on being essential for an ILD MDM following two questionnaire rounds. There was consensus that the presence of at least one radiologist, a quiet setting with a visual projection system, a high-quality chest high resolution computed tomography and a standardized template summarising collated patient data are essential components of an ILD MDM. Experts also agreed that it would be useful for ILD MDMs to undergo an annual benchmarking process and a validation process by fulfilling a minimum number of cases annually. Twenty-seven additional features were considered to be either highly desirable or desirable features based on the degree of consensus. Although our findings on desirable features are similar to the current literature, several of these remain controversial and warrant further research. The study also showed an agreement among participants on several future concepts to improve the ILD MDM such as performing regular self-assessments and conducting research into shared practices to develop an international expert guideline statement on ILD MDMs.

CONCLUSION

This Delphi study showed consensus among international ILD experts on essential and desirable features of an ILD MDM. Our data represents a first step toward potential collaborative research into future standardisation of ILD MDMs.

Differentiation of Idiopathic Pulmonary Fibrosis from Connective Tissue Disease-Related Interstitial Lung Disease Using Quantitative Imaging

A usual interstitial pneumonia (UIP) imaging pattern can be seen in both idiopathic pulmonary fibrosis (IPF) and connective tissue disease-related interstitial lung disease (CTD-ILD). The purpose of this multicenter study was to assess whether quantitative imaging data differ between IPF and CTD-ILD in the setting of UIP. Patients evaluated at two medical centers with CTD-ILD or IPF and a UIP pattern on CT or pathology served as derivation and validation cohorts. Chest CT data were quantitatively analyzed including total volumes of honeycombing, reticulation, ground-glass opacity, normal lung, and vessel related structures (VRS). VRS was compared with forced vital capacity percent predicted (FVC%) and percent predicted diffusing capacity of the lungs for carbon monoxide (DLCO%). There were 296 subjects in total, with 40 CTD-ILD and 85 IPF subjects in the derivation cohort, and 62 CTD-ILD and 109 IPF subjects in the validation cohort. VRS was greater in IPF across the cohorts on univariate (p < 0.001) and multivariable (p < 0.001–0.047) analyses. VRS was inversely correlated with DLCO% in both cohorts on univariate (p < 0.001) and in the derivation cohort on multivariable analysis (p = 0.003) but not FVC%. Total volume of normal lung was associated with DLCO% (p < 0.001) and FVC% (p < 0.001–0.009) on multivariable analysis in both cohorts. VRS appears to have promise in differentiating CTD-ILD from IPF. The underlying pathophysiological relationship between VRS and ILD is complex and is likely not explained solely by lung fibrosis.

Vessel-related structures predict UIP pathology in those with a non-IPF pattern on CT

OBJECTIVES

To determine if a quantitative imaging variable (vessel-related structures [VRS]) could identify subjects with a non-IPF diagnosis CT pattern who were highly likely to have UIP histologically.

METHODS

Subjects with a multidisciplinary diagnosis of interstitial lung disease including surgical lung biopsy and chest CT within 1 year of each other were included in the study. Non-contrast CT scans were analyzed using the Computer-Aided Lung Informatics for Pathology Evaluation and Rating (CALIPER) program, which quantifies the amount of various abnormal CT patterns on chest CT. Quantitative data were analyzed relative to pathological diagnosis as well as the qualitative CT pattern.

RESULTS

CALIPER-derived volumes of reticulation (p = 0.012), honeycombing (p = 0.017), and VRS (p < 0.001) were associated with a UIP pattern on pathology on univariate analysis but only VRS was associated with a UIP pathology on multivariable analysis (p = 0.013). Using a VRS cut-off of 173 cm³, the sensitivity and specificity for pathological UIP were similar to those for standard qualitative CT assessment (55.9% and 80.4% compared to 60.6% and 80.4%, respectively). VRS differentiated pathological UIP cases in those with a non-IPF diagnosis CT category (p < 0.001) but not in other qualitative CT patterns (typical UIP, probable UIP, and indeterminate for UIP). The rate of pathological UIP in those with VRS greater than 173 cm³ (84.2%) was nearly identical to those who had a qualitative CT pattern of probable UIP (88.9%).

CONCLUSIONS

VRS may be an adjunct to CT in predicting pathology in patients with interstitial lung disease.

KEY POINTS

• Volume of vessel-related structures (VRS) was associated with usual interstitial pneumonia (UIP) on pathology. • This differentiation arose from those with CT scans with a non-IPF diagnosis imaging pattern. • Higher VRS has similar diagnostic ramifications for UIP as probable UIP, transitively suggesting in patients with high VRS, pathology may be obviated.

Several specific high-resolution computed tomography patterns correlate with survival in patients with idiopathic pulmonary fibrosis

Background

Evidence of honeycombing in high-resolution computed tomography (HRCT) is a recognized risk factor for shortened survival in patients with idiopathic pulmonary fibrosis (IPF), but few studies have evaluated the feasibility of exploiting other specific patterns for predicting survival. The aim of this study was to examine the extent of specific HRCT patterns in IPF and determine whether they correlate with clinical features, pulmonary function tests (PFT), and survival.

Methods

Both the presence and extent of specific HRCT patterns, such as traction bronchiectasis, honeycombing, architectural distortion, reticulation, emphysema, and ground glass opacity, in 129 HRCT examinations were scored semi-quantitatively in three zones of each lung. HRCT examinations were also re-classified according to the 2011 and 2018 international statements. Correlations were calculated between the scores of specific HRCT patterns, clinical features, PFT, and patient survival.

Results

The extent of traction bronchiectasis was found to be an independent risk factor of shortened survival (HR 1.227, P=0.001). Patients with a possible usual interstitial pneumonia (UIP) pattern had a better median survival than the patients with a definite UIP pattern (61 vs. 37 months, P=0.026). The extents of traction bronchiectasis, honeycombing, and architectural distortion displayed an inverse correlation with all PFT values at the time of diagnosis. There were few differences between the radiological classifications of the 2011 and 2018 international statements.

Conclusions

We conclude that several specific HRCT patterns displayed a correlation with shortened survival in IPF; these may help in evaluating the risk of death in IPF patients.

Comparison between the ATS/ERS/JRS/ALAT criteria of 2011 and 2018 for Usual Interstitial Pneumonia on HRCT: a cross-sectional study

OBJECTIVES

To determine whether the revised 2018 ATS/ERS/JRS/ALAT radiological criteria for usual interstitial pneumonia (UIP) provide better diagnostic agreement compared to the 2011 guidelines.

METHODS

Cohort for this cross-sectional study (single center, nonacademic) was recruited from a multidisciplinary team discussion (MDD) from July 2010 until November 2018, with clinical suspicion of fibrosing interstitial lung disease (n= 325). Exclusion criteria were technical HRCT issues, known connective tissue disease (rheumatoid arthritis, systemic sclerosis, poly-or dermatomyositis), exposure to pulmonary toxins or lack of working diagnosis after MDD. Four readers with varying degrees in HRCT interpretation independently categorized 192 HRCTs, according to both the previous and current ATS/ERS/JRS/ALAT radiological criteria. An inter-rater variability analysis (Gwet's second-order agreement coefficient, AC2) was performed.

RESULTS

The resulting Gwet's AC2 for the 2011 and 2018 ATS/ERS/JRS/ALAT radiological criteria is 0.62 (±0.05) and 0.65 (±0.05), respectively. We report only minor differences in agreement level among the readers. Distribution according to the 2011 guidelines is as follows: 57.3% 'UIP pattern', 24% 'possible UIP pattern', 18.8% 'inconsistent with UIP pattern' and for the 2018 guidelines: 59.6% 'UIP', 14.5% 'probable UIP', 15.9% 'indeterminate for UIP' and 10% 'alternative diagnosis'.

CONCLUSIONS

No statistically significant higher degree of diagnostic agreement is observed when applying the revised 2018 ATS/ERS/JRS/ALAT radiological criteria for UIP compared to those of 2011. The inter-rater variability for categorizing the HRCT patterns is moderate for both classification systems, independent of experience in HRCT interpretation. The major advantage of the current guidelines is the better subdivision in the categories with a lower diagnostic certainty for UIP.

ADVANCES IN KNOWLEDGE

- In 2018, a revision of the 2011 ATS/ERS/JRS/ALAT radiological criteria for UIP was published, part of diagnostic guidelines for idiopathic pulmonary fibrosis.- The inter-rater agreement among radiologist is moderate for both classification systems, without a significantly higher degree of agreement when applying the revised radiological criteria.

Incorporating External Information in Tissue Subtyping: A Topic Modeling Approach

Probabilistic topic models, have been widely deployed for various applications such as learning disease or tissue subtypes. Yet, learning the parameters of such models is usually an ill-posed problem and may result in losing valuable information about disease severity. A common approach is to add a discriminative loss term to the generative model's loss in order to learn a representation that is also predictive of disease severity. However, finding a balance between these two losses is not straightforward. We propose an alternative way in this paper. We develop a framework which allows for incorporating external covariates into the generative model's approximate posterior. These covariates can have more discriminative power for disease severity compared to the representation that we extract from the posterior distribution. For instance, they can be features extracted from a neural network which predicts disease severity from CT images. Effectively, we enforce the generative model's approximate posterior to reside in the subspace of these discriminative covariates. We illustrate our method's application on a large-scale lung CT study of Chronic Obstructive Pulmonary Disease (COPD), a highly heterogeneous disease. We aim at identifying tissue subtypes by using a variant of topic model as a generative model. We quantitatively evaluate the predictive performance of the inferred subtypes and demonstrate that our method outperforms or performs on par with some reasonable baselines. We also show that some of the discovered subtypes are correlated with genetic measurements, suggesting that the identified subtypes may characterize the disease's underlying etiology.

Interstitial Pneumonia with Autoimmune Features: Why Rheumatologist-Pulmonologist Collaboration Is Essential

In 2015 the European Respiratory Society (ERS) and the American Thoracic Society (ATS) “Task Force on Undifferentiated Forms of Connective Tissue Disease-associated Interstitial Lung Disease” proposed classification criteria for a new research category defined as “Interstitial Pneumonia with Autoimmune Features” (IPAF), to uniformly define patients with interstitial lung disease (ILD) and features of autoimmunity, without a definite connective tissue disease. These classification criteria were based on a variable combination of features obtained from three domains: a clinical domain consisting of extra-thoracic features, a serologic domain with specific autoantibodies, and a morphologic domain with imaging patterns, histopathological findings, or multicompartment involvement. Features suggesting a systemic vasculitis were excluded. Since publication of ERS/ATS IPAF research criteria, various retrospective studies have been published focusing on prevalence; clinical, morphological, and serological features; and prognosis of these patients showing a broad heterogeneity in the results. Recently, two prospective, cohort studies were performed, confirming the existence of some peculiarities for this clinical entity and the possible progression of IPAF to a defined connective tissue disease (CTD) in about 15% of cases. Moreover, a non-specific interstitial pneumonia pattern, an anti-nuclear antibody positivity, and a Raynaud phenomenon were the most common findings. In comparison with idiopathic pulmonary fibrosis (IPF), IPAF patients showed a better performance in pulmonary function tests and less necessity of oxygen delivery. However, at this stage of our knowledge, we believe that further prospective studies, possibly derived from multicenter cohorts and through randomized control trials, to further validate the proposed classification criteria are needed.

HRCT evaluation of patients with interstitial lung disease: comparison of the 2018 and 2011 diagnostic guidelines

Background and aims:

Chest high-resolution computed tomography (HRCT) is the central diagnostic tool in discerning idiopathic pulmonary fibrosis (IPF) from other interstitial lung disease (ILDs). In 2018, new guidelines were published and the nomenclature for HRCT interpretation was changed. We sought to evaluate how clinicians’ interpretation would change based on reading HRCTs under the framework of the old versus new categorization.

Materials and methods:

We collated HRCTs from 50 random cases evaluated in the Inova Fairfax ILD clinic. Six ILD experts were provided the deidentified HRCTs. They were all instructed to independently provide two reads of each HRCT, based on the old and the new guidelines.

Results:

The kappa statistic for concordance for HRCT reads under old guidelines was 0.5, while for the new guidelines it was 0.38. Under the framework of the old guidelines, there were 22 HRCTs with unanimous consensus reads, while only 15 with the new guidelines. There were 12 HRCTs read unanimously as usual interstitial pneumonia (UIP) pattern based on both the old and the new guidelines. Ten HRCTs were read as a possible UIP pattern based on the old guidelines and were classified in nine cases as probable UIP and one indeterminate based on the new guidelines. Of the 28 inconsistent UIP HRCTs (old guidelines), 25 were read as alternative diagnosis suggested, two were read as indeterminate and one as probable UIP.

Conclusion:

Implementation of the new guidelines to categorize HRCTs in ILD patients appears to be associated with greater inter-interpreter variability. How or whether new guidelines improve the care and management of ILD patients remains unclear.

The reviews of this paper are available via the supplemental material section.

Quantitative computed tomography assessment for systemic sclerosis-related interstitial lung disease: comparison of different methods

OBJECTIVES

To compare the previously defined six different histogram-based quantitative lung assessment (QLA) methods on high-resolution CT (HRCT) in patients with systemic sclerosis (SSc)-related interstitial lung disease (ILD).

METHODS

The HRCT images of SSc patients with ILD were reviewed, and the visual ILD score (semiquantitative) and the severity of ILD (limited or extensive) were calculated. The QLA score of ILD was evaluated using the previously defined six different methods and parameters (different lung attenuation ranges, skewness, kurtosis, mean lung attenuation, and standard deviation [SD]). Pulmonary function tests (PFTs) were also performed on all patients. Relationships among variables were evaluated using Spearman's correlation coefficient (r). Diagnostic performance of quantitative methods for the ability to differentiate the limited from extensive ILD was calculated using ROC analysis.

RESULTS

Fifty-five patients were included in the study. There was a significant correlation between all quantitative and semiquantitative measurement results (p < 0.0001). The QLA scores revealed a significant correlation with PFT results. The kurtosis value of the voxels between - 200 and - 1024 Hounsfield unit (HU) (Method-5) showed the best correlation with semiquantitative evaluation (r = - 0.740, p < 0.0001). The ROC analysis demonstrated the best performance of SD of the voxels between - 400 and - 950 HU (Method-6) for histogram analysis method and Method-3 (voxels between - 260 and - 600 HU were calculated as ILD) for CT density cutoff methods.

CONCLUSIONS

All the QLA methods are applicable in assessing the ILD score in SSc patients and have potential importance to differentiate limited from extensive ILD.

KEY POINTS

• Quantitative interstitial lung disease assessment helps clinicians to assess systemic sclerosis patients with interstitial lung disease. • Quantitative lung assessment methods are applicable in assessing the interstitial lung disease score in systemic sclerosis patients. • Quantitative lung assessment methods have potential importance in the management of patients.

Evaluation of inter-observer variation for computed tomography identification of childhood interstitial lung disease

Interstitial lung diseases (ILDs) that present in childhood (chILD) are seen far less frequently than ILDs presenting in adults which themselves constitute rare disorders [1]. Histopathological [2, 3] and imaging [4] characterisation of chILD disease subtypes therefore lags behind adult ILDs. The field has also been constrained by comparisons with disease morphology in adults, despite the developmental differences in terms of growth and healing in the paediatric lung, which may alter disease patterns and distributions. The American Thoracic Society [5] and European [1] chILD management guidelines both specify a pivotal role for computed tomography (CT) imaging in the work-up of chILD patients to: 1) determine whether a chILD is present or not; and 2) where possible, to make a specific diagnosis of the underlying cause. For the second aim to be achieved, diagnostic reviews need to be reproducible between experts. Our study uniquely examined agreement between observers of varying experience in the CT evaluation of chILD to inform whether the current status of CT imaging and knowledge can be diagnostic of specific chILDs. We hypothesised that observer agreement for chILD groups and diagnoses would be limited. The study was not designed to relate CT agreement to final diagnosis. As a secondary analysis, we examined how CT interpretation differed between observers in children under and over 2 years of age.

Making chILD diagnoses on CT is poorly reproducible, even amongst sub-specialists. CT might best improve diagnostic confidence in a multidisciplinary team setting when augmented with clinical, functional and haematological results.http://bit.ly/327jRCw

Thoracic high resolution CT using the modified VetMousetrap™ device is a feasible method for diagnosing canine idiopathic pulmonary fibrosis in awake West Highland White Terriers

Canine idiopathic pulmonary fibrosis is a chronic, progressive interstitial lung disease particularly prevalent in West Highland White Terriers. In the present prospective pilot study, we evaluated the feasibility of modified VetMousetrap™ device in high resolution CT to detect idiopathic pulmonary fibrosis in West Highland White Terriers. Twelve awake West Highland White Terriers with canine idiopathic pulmonary fibrosis and 24 clinically healthy West Highland White Terriers were scanned using a helical dual slice scanner utilizing VetMousetrap™ device without or with minimal chemical restraint with butorphanol. Three evaluators blindly assessed the images for image quality and the presence of canine idiopathic pulmonary fibrosis related imaging findings such as ground glass opacity and reticular opacities. Additionally, the attenuation of the lung was quantified with ImageJ software using histogram analysis of density over the lung fields. Computed tomography was successfully completed and motion artifact ranked in statistical analysis barely noticeable to mild in all dogs. The agreement between imaging findings and clinical status was very good with overall κ value 0.91 and percentage of agreement of 94%. There was also very good intraobserver (κ_range = 0.79-0.91) and interobserver agreement (κ = 0.94). Moderate to severe ground glass opacity was present in all affected dogs. In the ImageJ analysis, a significant difference in lung attenuation between the study groups was observed. We conclude that modified VetMousetrap™ device is applicable in diagnosing canine idiopathic pulmonary fibrosis in awake West Highland White Terriers avoiding anesthetic risk in these often severely hypoxic patients.

Impact of the pattern of interstitial lung disease on mortality in rheumatoid arthritis: A systematic literature review and meta-analysis

OBJECTIVE

An important extra-articular manifestation of rheumatoid arthritis (RA) is interstitial lung disease (ILD). The relationship between the usual interstitial pneumonia (UIP) pattern and mortality in patients with RA is unclear. The purpose of this study was to complete a systematic literature review and meta-analysis on the association between RA-ILD pattern and mortality risk.

METHODS

We performed a systematic literature review through December 12, 2018. Study characteristics, unadjusted and adjusted relative risks (RR) of mortality for ILD pattern were extracted from the identified studies and quality assessments were performed. RR for mortality (RA-UIP vs. other RA-ILD) was pooled using inverse variance weighting and random effects models.

RESULTS

Ten retrospective cohort studies met our eligibility criteria. A total of 1256 RA-ILD patients were included with 484 total deaths. Meta-analysis yielded a pooled RR of 1.66 (95% confidence interval1.07 to 2.56) for death among those with UIP RA-ILD compared with other patterns. In sub-group analysis when pooling studies comparing UIP to NSIP pattern of RA-ILD, the RR was 2.39 (95% CI 0.86-6.68).

CONCLUSION

Through a systematic literature review and meta-analysis, we found UIP pattern to be associated with a higher mortality risk in RA-ILD compared to other patterns of RA-ILD although more recent studies emphasize the importance of pulmonary physiology and the extent of lung involvement as significant predictors of mortality rather than the pattern of RA-ILD. Recognizing the small number of studies satisfying eligibility and inconsistent accounting for confounders, further study of mortality risk in RA-ILD is needed with standardized assessment of various RA, ILD, and patient-related factors.

Automated CT quantification methods for the assessment of interstitial lung disease in collagen vascular diseases: A systematic review

Interstitial lung disease (ILD) is highly prevalent in collagen vascular diseases and reduction of ILD is an important therapeutic target. To that end, reliable quantification of pulmonary disease severity is of great significance. This study systematically reviewed the literature on automated computed tomography (CT) quantification methods for assessing ILD in collagen vascular diseases. PRISMA-DTA guidelines for systematic reviews were used and 19 original research articles up to January 2018 were included based on a MEDLINE/Pubmed and Embase search. Quantitative CT methods were categorized as histogram assessment (12 studies) or pattern/texture recognition (7 studies). R² for correlation with visual ILD scoring ranged from 0.143 (p < 0.01) to 0.687 (p < 0.0001), for FVC from 0.048 (p < 0.0001) to 0.504 (p < 0.0001) and for DLCO from 0.015 (p = 0.61) to 0.449 (p < 0.0001). Automated CT methods are independent of reader's expertise and are a promising tool in the quantification of ILD in collagen vascular disease patients.

Role of imaging in progressive-fibrosing interstitial lung diseases

Imaging techniques are an essential component of the diagnostic process for interstitial lung diseases (ILDs). Chest radiography is frequently the initial indicator of an ILD, and comparison of radiographs taken at different time points can show the rate of disease progression. However, radiography provides only limited specificity and sensitivity and is primarily used to rule out other diseases, such as left heart failure. High-resolution computed tomography (HRCT) is a more sensitive method and is considered central in the diagnosis of ILDs. Abnormalities observed on HRCT can help identify specific ILDs. HRCT also can be used to evaluate the patient's prognosis, while disease progression can be assessed through serial imaging. Other imaging techniques such as positron emission tomography-computed tomography and magnetic resonance imaging have been investigated, but they are not commonly used to assess patients with ILDs. Disease severity may potentially be estimated using quantitative methods, as well as visual analysis of images. For example, comprehensive assessment of disease staging and progression in patients with ILDs requires visual analysis of pulmonary features that can be performed in parallel with quantitative analysis of the extent of fibrosis. New approaches to image analysis, including the application of machine learning, are being developed.

Imaging techniques, particularly HRCT, are the cornerstone for ILD diagnosis and new approaches to analysing HRCT images, including machine-learning technology, are being developedhttp://ow.ly/1R1e30mOqhn

Interobserver reliability in describing radiographic lung changes after stereotactic body radiation therapy

PURPOSE

Radiographic lung changes after stereotactic body radiation therapy (SBRT) vary widely between patients. Standardized descriptions of acute (≤6 months after treatment) and late (>6 months after treatment) benign lung changes have been proposed but the reliable application of these classification systems has not been demonstrated. Herein, we examine the interobserver reliability of classifying acute and late lung changes after SBRT.

METHODS AND MATERIALS

A total of 280 follow-up computed tomography scans at 3, 6, and 12 months post-treatment were analyzed in 100 patients undergoing thoracic SBRT. Standardized descriptions of acute lung changes (3- and 6-month scans) include diffuse consolidation, patchy consolidation and ground glass opacity (GGO), diffuse GGO, patchy GGO, and no change. Late lung change classifications (12-month scans) include modified conventional pattern, mass-like pattern, scar-like pattern, and no change. Five physicians scored the images independently in a blinded fashion. Fleiss' kappa scores quantified the interobserver agreement.

RESULTS

The Kappa scores were 0.30 at 3 months, 0.20 at 6 months, and 0.25 at 12 months. The proportion of patients in each category at 3 and 6 months was as follows: Diffuse consolidation 11% and 21%; patchy consolidation and GGO 15% and 28%; diffuse GGO 10% and 11%; patchy GGO 15% and 15%; and no change 49% and 25%, respectively. The percentage of patients in each category at 12 months was as follows: Modified conventional 46%; mass-like 16%; scar-like 26%; and no change 12%. Uniform scoring between the observers occurred in 26, 8, and 14 cases at 3, 6, and 12 months, respectively.

CONCLUSIONS

Interobserver reliability scores indicate a fair agreement to classify radiographic lung changes after SBRT. Qualitative descriptions are insufficient to categorize these findings because most patient scans do not fit clearly into a single classification. Categorization at 6 months may be the most difficult because late and acute lung changes can arise at that time.

Automated Lung Segmentation from HRCT Scans with Diffuse Parenchymal Lung Diseases

Performing accurate and fully automated lung segmentation of high-resolution computed tomography (HRCT) images affected by dense abnormalities is a challenging problem. This paper presents a novel algorithm for automated segmentation of lungs based on modified convex hull algorithm and mathematical morphology techniques. Sixty randomly selected lung HRCT scans with different abnormalities are used to test the proposed algorithm, and experimental results show that the proposed approach can accurately segment the lungs even in the presence of disease patterns, with some limitations in the apices and bases of lungs. The algorithm demonstrates a high segmentation accuracy (dice similarity coefficient = 98.62 and shape differentiation metrics dmean = 1.39 mm, and drms = 2.76 mm). Therefore, the developed automated lung segmentation algorithm is a good candidate for the first stage of a computer-aided diagnosis system for diffuse lung diseases.

The predictive prognostic factors for polymyositis/dermatomyositis-associated interstitial lung disease

BACKGROUND

Interstitial lung disease (ILD) is the principal cause of death in polymyositis/dermatomyositis (PM/DM). Here we investigated prognostic factors for death and serious infection in PM/DM-ILD using the multicenter database.

METHODS

We retrospectively reviewed baseline demographic, clinical and laboratory findings, treatment regimens and outcomes in patients with PM/DM-ILD. The distribution of ILD lesions was evaluated in four divided lung zones of high-resolution computed tomography images.

RESULTS

Of 116 patients with PM/DM-ILD, 14 died within 6 months from the diagnosis. As independent risk factors for early death, extended ILD lesions in upper lung fields (odds ratio (OR) 8.01, p = 0.016) and hypocapnia (OR 6.85, p = 0.038) were identified. Serious infection was found in 38 patients, including 11 patients who died of respiratory or multiple infections. The independent risk factors were high serum KL-6 (OR 3.68, p = 0.027), high initial dose of prednisolone (PSL) (OR 4.18, p = 0.013), and combination immunosuppressive therapies (OR 5.51, p < 0.001).

CONCLUSION

The present study shows the progression of ILD at baseline is the most critical for survival and that infection, especially respiratory infection, is an additive prognostic factor under the potent immunosuppressive treatment.

The interstitial lung disease multidisciplinary meeting: A position statement from the Thoracic Society of Australia and New Zealand and the Lung Foundation Australia

Interstitial lung diseases (ILD) are a diverse group of pulmonary diseases for which accurate diagnosis is critical for optimal treatment outcomes. Diagnosis of ILD can be challenging and a multidisciplinary approach is recommended in international guidelines. The purpose of this position paper is to review the evidence for the use of the multidisciplinary meeting (MDM) in ILD and suggest an approach to its governance and constitution, in an attempt to provide a standard methodology that could be applied across Australia and New Zealand. This position paper is endorsed by the Thoracic Society of Australia and New Zealand (TSANZ) and the Lung Foundation Australia (LFA).

Estimating the incidence of interstitial lung diseases in the Cree of Eeyou Istchee, northern Québec

BACKGROUND

Little is known about the epidemiology of interstitial lung disease (ILD) amongst Canada's Indigenous populations. Clinicians working in Eeyou Istchee (the Cree territory of the James Bay region of Québec, population 17, 956) suspected that ILD was more common in this area. We sought to identify all prevalent and incident cases of ILD in Eeyou Istchee between 2006 and 2013, to describe characteristics of affected patients, distribution of subtypes, and estimate disease incidence.

METHODS

Potential ILD cases amongst Eeyou Istchee residents were identified by searching hospitalization databases and lists of patients on long term home oxygen in the region's nine communities, and surveying physicians and nurses. Clinical, radiological and pathological data were reviewed. Potential cases were classified as 'Definite ILD' if an open lung biopsy demonstrated ILD or, in the absence of histopathologic confirmation, if their thoracic CT imaging was deemed consistent with ILD by a panel of two respirologists and a chest radiologist. Potential cases for whom CT images could not be retrieved for our review were not eligible for classification as Definite ILD, unless they had undergone open lung biopsy. The Definite ILD group was further categorized by subtype of ILD. For usual interstitial pneumonia and non-specific interstitial pneumonitis patterns, we assumed cases were idiopathic in the absence of documentation of connective tissue disease or occupational exposures in the medical chart. For Definite ILD and the most common subtype, we calculated the average annual incidence rates, age-standardized to the province of Quebec, for 2006 to 2013, using a gamma distribution to calculate 95% confidence intervals.

RESULTS

Of 167 potential cases, 52 were categorized as Definite ILD: 14 on the basis of histopathology and 38 on the basis of CT imaging alone. Six patients had a prior history of connective tissue disease. Information on occupation was recorded in the charts of 18/52 (35%) cases, and missing in the remainder. We found the most common subtype was idiopathic pulmonary fibrosis (27/52, 52%), followed by idiopathic non-specific interstitial pneumonia (13/52, 25%), and secondary usual interstitial pneumonia associated with connective tissue diseases (5/52, 10%). The age-standardized annual incidence between 2006-2013 was 80 per 100,000 person-years observed (PYO) for ILD, and 46 per 100,000 PYO for idiopathic pulmonary fibrosis.

INTERPRETATION

The incidence of ILD and of idiopathic pulmonary fibrosis in Eeyou Istchee may be higher than rates reported in other populations; however, cautious interpretation is required due to the lack of histopathological confirmation in the majority of cases, and our reliance on chart review to exclude secondary causes. A prospective study of incident cases with standardized assessments to establish the types of ILD and to assess for potential causes could overcome some of the limitations of the present analysis. Studies evaluating ILD incidence and subtype distribution in other Indigenous populations would also be of interest.

Diagnostic accuracy of a clinical diagnosis of idiopathic pulmonary fibrosis: an international case-cohort study

We conducted an international study of idiopathic pulmonary fibrosis (IPF) diagnosis among a large group of physicians and compared their diagnostic performance to a panel of IPF experts.A total of 1141 respiratory physicians and 34 IPF experts participated. Participants evaluated 60 cases of interstitial lung disease (ILD) without interdisciplinary consultation. Diagnostic agreement was measured using the weighted kappa coefficient (κw). Prognostic discrimination between IPF and other ILDs was used to validate diagnostic accuracy for first-choice diagnoses of IPF and were compared using the C-index.A total of 404 physicians completed the study. Agreement for IPF diagnosis was higher among expert physicians (κw=0.65, IQR 0.53-0.72, p<0.0001) than academic physicians (κw=0.56, IQR 0.45-0.65, p<0.0001) or physicians with access to multidisciplinary team (MDT) meetings (κw=0.54, IQR 0.45-0.64, p<0.0001). The prognostic accuracy of academic physicians with >20 years of experience (C-index=0.72, IQR 0.0-0.73, p=0.229) and non-university hospital physicians with more than 20 years of experience, attending weekly MDT meetings (C-index=0.72, IQR 0.70-0.72, p=0.052), did not differ significantly (p=0.229 and p=0.052 respectively) from the expert panel (C-index=0.74 IQR 0.72-0.75).Experienced respiratory physicians at university-based institutions diagnose IPF with similar prognostic accuracy to IPF experts. Regular MDT meeting attendance improves the prognostic accuracy of experienced non-university practitioners to levels achieved by IPF experts.

Correlation of pulmonary function and usual interstitial pneumonia computed tomography patterns in idiopathic pulmonary fibrosis

BACKGROUND

Little is known about presenting 'inconsistent' or 'possible' usual interstitial pneumonia (UIP) computed tomography (CT) patterns advancing to 'consistent' UIP as disease progresses in idiopathic pulmonary fibrosis (IPF). We hypothesized that if 'consistent' UIP represented more advanced disease, such a pattern on presentation should also correlate with more severe pulmonary function test (PFT) abnormalities.

MATERIAL AND METHODS

Consecutive IPF patients (2005-2013) diagnosed by international criteria with baseline PFT and CT were included. Presenting CTs were assessed by three expert radiologists for consensus UIP pattern ('consistent', 'possible', and 'inconsistent'). Approximation of individual and combined interstitial abnormalities was also performed with correlation of interstitial abnormalities and UIP CT pattern made with PFT findings and survival.

RESULTS

Three-hundred and fifty patients (70% male) were included with a mean age of 68.3 years. Mean percent predicted forced vital capacity (FVC%) and diffusion capacity (DLCO%) was 64% and 45.5% respectively. Older age and male gender correlated more with 'consistent' UIP CT pattern. FVC% was not associated with any UIP pattern but did correlate with total volume of radiologist assessed interstitial abnormalities. DLCO% was lower in those with 'consistent' UIP pattern. A 'consistent' UIP CT pattern was also not independently predictive of survival after correction for age, gender, FVC%, and DLCO%.

CONCLUSION

PFT findings appear to correlate with extent of radiologic disease but not specific morphologic patterns. Whether such UIP patterns represent different stages of disease severity or radiologic progression is not supported by coinciding pulmonary function decline.

Multidisciplinary evaluation of interstitial lung diseases: current insights: Number 1 in the Series "Radiology" Edited by Nicola Sverzellati and Sujal Desai

Multidisciplinary team (MDT) diagnosis is regarded as the diagnostic reference standard for interstitial lung disease (ILD). Several studies have reported that MDT diagnosis is associated with higher levels of diagnostic confidence and better interobserver agreement when compared to the individual components of the MDT in isolation. Although this recommendation is widely accepted, no guideline statement specifies what constitutes an MDT meeting and how its participants should govern it. Furthermore, the precise role of an MDT meeting in the setting of ILD may vary from one group to another. For example, in some cases, the meeting will confine its discussion to characterising the disease and formulating diagnosis. In others, management decisions may also be part of the discussion. Surprisingly, there is no consensus on how MDT diagnosis is validated. As multidisciplinary evaluation contains all the available clinical information on an individual patient, there is no reference standard against which the veracity of MDT diagnosis can be tested. Finally, many of these uncertainties surrounding MDT meeting practice are unlikely to be answered by traditional evidence-based studies, which create difficulties when generating guideline recommendations. There is clearly a need for expert consensus on what constitutes acceptable MDT meeting practice. This consensus will need to be flexible to accommodate the variability in resources available to fledgling MDT groups and the variable nature of patients requiring discussion.

Utility of precipitating antibody testing in the diagnostic evaluation of chronic hypersensitivity pneumonia

Background: Chronic hypersensitivity pneumonitis (HP), in its progressive fibrotic form, is difficult to distinguish from other fibrosing interstitial lung diseases (ILD), particularly idiopathic pulmonary fibrosis (IPF) and non-specific interstitial pneumonia (NSIP). The role of serum precipitating antibodies in the diagnosis of fibrosing ILD has not been discussed in recent clinical practice guidelines. Objectives: The aim of this study is to assess the role of precipitins in the diagnosis of non pre-selected cases of fibrosing ILD. Methods: Clinical records of 108 consecutive patients referred for presumptive fibrosing ILD to our institution were retrospectively assessed for exposure history, serum precipitins, other diagnostic examinations, and multidisciplinary diagnosis (MDD). Their high resolution computed tomography (HRCT) images were blindly and prospectively re-assessed. We estimated sensitivity and specificity of precipitins against MDD and, to account for incorporation bias, we used two composite reference standards (CRSs), having exposure history and HRCT as component tests. Results: Definitive diagnosis achieved through MDD were chronic HP (17% of cases), NSIP (42%), IPF (18%) and others (23%). For serum precipitins, we estimated a sensitivity of 72% and a specificity of 68% using MDD as the reference standard. Sensitivity against the AND-CRS was 55%, while specificity against the OR-CRS was 61%. On the basis of this results, we can expect true sensitivity of precipitins lying between 55 and 72% and specificity between 61 and 68%. Conclusions:Serum precipitating antibodies did not result as having a relevant role in the diagnostic approach to chronic HP (Sarcoidosis Vasc Diffuse Lung Dis 2017; 34: 149-155).