Baseline High-resolution Computed Tomography Research Articles

How accurate is high-resolution computed tomography of the chest in differentiating between pulmonary invasive fungal infections and other pulmonary infections in children with cancer?

Pulmonary invasive fungal infections pose a serious risk for immunocompromised patients. Although diagnostic imaging plays an important role in the early detection of pulmonary invasive fungal infections, radiological differentiation between invasive fungal infection and other pulmonary infections is challenging. The aim of this study was to assess the accuracy of chest high-resolution computed tomography (HRCT) in the differentiation between pulmonary invasive fungal infections and other pulmonary infections in paediatric cancer patients. In this retrospective study, baseline HRCTs of patients with probable or proven invasive fungal infections and other pulmonary infections were blindly assessed by two radiologists, followed by a consensus reading. The scoring form included imaging characteristics and radiological invasive fungal infection probability assessment. Inter-rater reliability was determined with Cohen's kappa. Chest HRCTs (n = 77) of paediatric cancer patients with pulmonary invasive fungal infections (n = 45) and with other pulmonary infections (n = 32) were evaluated. In the consensus reading, nodules with halo sign and wedge-shaped consolidations were observed significantly more in pulmonary invasive fungal infections than in other pulmonary infections (86.7% vs. 34.4% and 28.9% vs. 9.4%), and ground-glass opacities were observed less frequently (61.4% vs. 87.5%). The kappa values for the individual imaging characteristics ranged from 0.121 to 0.408. Sensitivity of the HRCT to diagnose a pulmonary invasive fungal infection ranged from 0.78 to 0.80, and specificity from 0.66 to 0.88. The accuracy of chest HRCTs in differentiating between invasive fungal infections and other pulmonary infections is poor. There are two main reasons for this: no individual imaging characteristic was found to be able to fully distinguish between invasive fungal infections and other pulmonary infections, and the agreement between radiologists was only moderate.

Progression of radiographic fibrosis in rheumatoid arthritis-associated interstitial lung disease.

Preclinical interstitial lung disease (pILD) may represent the early stages of rheumatoid arthritis-associated interstitial lung disease (RA-ILD). However, the characteristics, clinical outcomes, and risk factors associated with fibrosis progression in RA-ILD, including pILD and ILD, remain poorly understood. Baseline data were compared between patients with RA-ILD and those with RA alone. Multivariate logistic regression and Cox regression analyses were performed to identify risk factors associated with the prevalence and imaging progression of RA-ILD, respectively. Among the 371 enrolled RA patients, 32.3% had RA-ILD. Multiple logistic regression analyses identified age over 60.0 years (OR 2.22), smoking (OR 2.09), diabetes mellitus (DM) (OR 3.09), mixed connective tissue disease (MCTD) (OR 2.98), serum lactate dehydrogenase (LDH) levels exceeding 250.0 U/L (OR 6.73), and positive anti-cyclic citrullinated peptide (anti-CCP) antibody (OR 2.06) as independent risk factors for RA-ILD (p< 0.05 or 0.01). Among the 98 RA-ILD patients who underwent follow-up for a median duration of 19.1 months, 51.0% demonstrated fibrotic progression on high-resolution computed tomography (HRCT). Multiple Cox regression analysis identified DM (HR 2.03), Disease Activity Score in 28 joints-Erythrocyte Sedimentation Rate (DAS28-ESR) greater than 5.1 (HR 2.21), and baseline HRCT scores exceeding 5.0 (HR 2.30) as independent risk factors for fibrosis progression in RA-ILD (p< 0.05 or 0.01). Nearly one-third of RA patients in this cohort had prevalent pILD or ILD, and half of them demonstrated imaging progression during follow-up. DM, higher DAS28-ESR, and advanced HRCT scores were identified as independent risk factors for progressive fibrosis in RA-ILD.

Weak to no correlation between quantitative high-resolution computed tomography metrics and lung function change in fibrotic diseases.

Identifying systemic sclerosis (SSc) and idiopathic pulmonary fibrosis (IPF) patients at risk of more rapid forced vital capacity (FVC) decline could improve trial design. The purpose of the present study was to explore the prognostic value of quantitative high-resolution computed tomography (HRCT) metrics derived by Imbio lung texture analysis (LTA) tool in predicting FVC slope. This retrospective study used data from patients who were not treated with investigational drugs with and without background antifibrotic therapies in tocilizumab phase 3 SSc, lebrikizumab phase 2 IPF, and zinpentraxin alfa phase 2 IPF studies conducted from 2015 to 2021. Controlled HRCT axial volumetric multidetector computed tomography scans were evaluated using the Imbio LTA tool. Associations between HRCT metrics and FVC slope were assessed through the Spearman correlation coefficient and adjusted R2 in a linear regression model adjusted by demographics and baseline clinical characteristics. A total of 271 SSc and IPF patients were analysed. Correlation coefficients of highest magnitude were observed in the SSc study between the extent of ground glass, normal volume, quantification of interstitial lung disease, reticular pattern, and FVC slope (-0.25, 0.28, -0.28, and -0.33, respectively), while the correlation coefficients observed in IPF studies were in general <0.2. The incremental prognostic value of the baseline HRCT metrics was marginal after adjusting baseline characteristics and was inconsistent across study arms. Data from the SSc and IPF studies suggested weak to no and inconsistent correlation between quantitative HRCT metrics derived by the Imbio LTA tool and FVC slope in the studied SSc and IPF population.

The efficacy and safety of systemic corticosteroids as first line treatment for granulomatous lymphocytic interstitial lung disease

Granulomatous and lymphocytic interstitial lung disease (gl-ILD) is a major cause of morbidity and mortality among patients with common variable immunodeficiency. Corticosteroids are recommended as first-line treatment for gl-ILD, but evidence for their efficacy is lacking. This study analyzed the effect of high-dose corticosteroids (≥0.3 mg/kg prednisone equivalent) on gl-ILD, measured by high-resolution computed tomography (HRCT) scans, and pulmonary function test (PFT) results. Patients who had received high-dose corticosteroids but no other immunosuppressive therapy at the time (n= 56) and who underwent repeated HRCT scanning or PFT (n = 39) during the retrospective and/or prospective phase of the Study of Interstitial Lung Disease in Primary Antibody Deficiency (STILPAD) were included in the analysis. Patients without any immunosuppressive treatment were selected as controls (n= 23). HRCT scans were blinded, randomized, and scored using the Hartman score. Differences between the baseline and follow-up HRCT scans and PFT were analyzed. Treatment with high-dose corticosteroids significantly improved HRCT scores and forced vital capacity. Carbon monoxide diffusion capacity significantly improved in both groups. Of 18 patients, for whom extended follow-up data was available, 13 achieved a long-term, maintenance therapy independent remission. All patients with relapse were retreated with corticosteroids, but only one-fifth of them responded. Two opportunistic infections were found in the corticosteroid treatment group, while overall infection rate was similar between cohorts. Induction therapy with high-dose corticosteroids improved HRCT scans and PFT results of patients with gl-ILD and achieved long-term remission in 42% of patients. It was not associated with major side effects. Low-dose maintenance therapy provided no benefit and efficacy was poor in relapsing disease.

Quantitative chest CT assessment of pulmonary alveolar proteinosis with deep learning: a real-world longitudinal study

High-resolution computed tomography (HRCT) plays an important role in accessing the severity of pulmonary alveolar proteinosis (PAP). Visual evaluation of changes between two HRCT scans is subjective. This study was conducted to quantitatively evaluate lung burden changes in patients with PAP using HRCT-based automated deep-learning method following 12 months of statin therapy. In this prospective real-world observational study, patients with PAP who underwent chest HRCT were evaluated from November 28, 2018, to April 12, 2021. Oral statin administration was initiated as therapy for these PAP patients with 12 months of follow-up. HRCT-derived lung ground-glass opacification percentage of the whole lung and 5 lobes and the percentage of different densities of ground glass were automatically quantified with deep-learning software. Longitudinal changes of the HRCT quantitative parameter were also compared. The study enrolled 50 patients with PAP, including 25 mild-moderate PAP cases and 25 severe PAP cases. The percentage of lung ground-glass opacification of the whole lung and 5 lobes and the percentage of different densities of ground glass were significantly different among the 2 different clinical types at baseline (all P values <0.05). Overall, the percentage of whole-lung ground-glass opacification significantly decreased between the baseline HRCT and the HRCT results after 12 months of follow-up (P=0.023; 95% CI: 1.384-18.684). Changes in the total opacification of the whole lung were positively correlated with changes in partial pressure of arterial oxygen (PaO2; r=0.716; P<0.001) and percentage of predicted diffusion capacity for carbon monoxide (DLCO%pred; r=0.664; P<0.001). A quantitative image parameter automatically generated by a deep-learning tool from chest HRCT scans may be used to evaluate the severity of PAP and may help to evaluate and quantify the response to statin therapy.

Lung shrinking assessment on HRCT with elastic registration technique for monitoring idiopathic pulmonary fibrosis

ObjectivesEvaluation and follow-up of idiopathic pulmonary fibrosis (IPF) mainly rely on high-resolution computed tomography (HRCT) and pulmonary function tests (PFTs). The elastic registration technique can quantitatively assess lung shrinkage. We aimed to investigate the correlation between lung shrinkage and morphological and functional deterioration in IPF.MethodsPatients with IPF who underwent at least two HRCT scans and PFTs were retrospectively included. Elastic registration was performed on the baseline and follow-up HRCTs to obtain deformation maps of the whole lung. Jacobian determinants were calculated from the deformation fields and after logarithm transformation, log_jac values were represented on color maps to describe morphological deterioration, and to assess the correlation between log_jac values and PFTs.ResultsA total of 69 patients with IPF (male 66) were included. Jacobian maps demonstrated constriction of the lung parenchyma marked at the lung base in patients who were deteriorated on visual and PFT assessment. The log_jac values were significantly reduced in the deteriorated patients compared to the stable patients. Mean log_jac values showed positive correlation with baseline percentage of predicted vital capacity (VC%) (r = 0.394, p < 0.05) and percentage of predicted forced vital capacity (FVC%) (r = 0.395, p < 0.05). Additionally, the mean log_jac values were positively correlated with pulmonary vascular volume (r = 0.438, p < 0.01) and the number of pulmonary vascular branches (r = 0.326, p < 0.01).ConclusionsElastic registration between baseline and follow-up HRCT was helpful to quantitatively assess the morphological deterioration of lung shrinkage in IPF, and the quantitative indicator log_jac values were significantly correlated with PFTs.Key Points• The elastic registration on HRCT was helpful to quantitatively assess the deterioration of IPF.• Jacobian logarithm was significantly reduced in deteriorated patients and mean log_jac values were correlated with PFTs.• The mean log_jac values were related to the changes of pulmonary vascular volume and the number of vascular branches.

High-resolution computed tomography of the chest for the screening, re-screening and follow-up of systemic sclerosis-associated interstitial lung disease: a EUSTAR-SCTC survey.

High-resolution computed tomography (HRCT) of the chest is the gold standard to diagnose interstitial lung disease (ILD). A prior survey reported that fewer than 60% of SSc-treating rheumatologists order an HRCT for ILD screening in newly diagnosed SSc patients. Since then, efforts were initiated to increase awareness of HRCT as a screening tool. Aim of the present study was to assess efficacy of these awareness programs. European Scleroderma Trials and Research (EUSTAR) and Scleroderma Clinical Trials Consortium (SCTC) members answered a survey about the use of HRCT at diagnosis, the re-screening of patients with a negative baseline HRCT, and the follow-up of HRCT positive SSc-ILD patients. When HRCT was not routinely requested, additional details were collected. Among 205 physician responders, 95.6% would perform an HRCT at SSc diagnosis: 64.9% as routine screening for ILD (65.4% of SSc referral and 63.6% of non-referral physicians) and 30.7% upon clinical suspicion (95.2% in case of crackles on auscultation). Among non-screening physicians, clinical and ethical concerns were major driving factors for not ordering HRCTs. During follow-up, 79.0% of responders would repeat HRCTs in baseline negative cases: 14.1% as routine screening and 64.9% for diagnostic purposes. Finally, 93.2% of responders would repeat a chest HRCT after SSc-ILD diagnosis: 36.6% as yearly routine and 56.6% according to clinical evaluation. The use of baseline HRCT for the screening of SSc-ILD has slightly increased, but awareness programs should be adapted for further improvement. HRCT use in re-screening and follow-up may benefit from validated algorithms.

The disconnect between visual assessment of air trapping and lung physiology for assessment of small airway disease in scleroderma-related interstitial lung disease: An observation from the Scleroderma Lung Study II Cohort.

To explore the presence of small airway disease (SAD) and emphysema in scleroderma-related interstitial lung disease (SSc-ILD) and to evaluate the physiologic and clinical correlates of SAD in SSc-ILD. Thoracic high-resolution computed tomography (HRCT) images obtained from the Scleroderma Lung Study II (SLSII) participants were reviewed by a group of thoracic radiologists. The presence of SAD was assessed by visual assessment for air trapping. HRCT scans were also evaluated for the presence of emphysema. The association of the presence of air trapping and emphysema with physiological measures of airway disease and clinical variables was evaluated. A total of 155 baseline HRCT scans were reviewed. For assessment of air trapping, images needed to be adequate end-expiratory examinations, leaving 123 scans. Air trapping was seen in 13/123 (10.6%) of the SSc-ILD cohort and was independent of smoking history, asthma or the presence of gastroesophageal reflux. Air trapping on HRCT was not associated with physiologic evidence of SAD. We also identified 8/155 (5.2%) patients with emphysema on HRCT, which was independent of SAD and found mostly in prior smokers. We report the first study of air trapping on standardized, high-quality HRCT images as a reflection of SAD in a relatively large, well characterized SSc-ILD cohort. The presence of SAD in non-smoking SSc-ILD patients supports that SSc may cause not only restrictive lung disease (SSc-ILD), but also, to a lesser extent, obstructive disease. Physiologic measures alone may be inadequate to detect airway disease in patients with SSc-ILD.

Radiomics-based machine learning differentiates \u201cground-glass\u201d opacities due to COVID-19 from acute non-COVID-19 lung disease

Ground-glass opacities (GGOs) are a non-specific high-resolution computed tomography (HRCT) finding tipically observed in early Coronavirus disesase 19 (COVID-19) pneumonia. However, GGOs are also seen in other acute lung diseases, thus making challenging the differential diagnosis. To this aim, we investigated the performance of a radiomics-based machine learning method to discriminate GGOs due to COVID-19 from those due to other acute lung diseases. Two sets of patients were included: a first set of 28 patients (COVID) diagnosed with COVID-19 infection confirmed by real-time polymerase chain reaction (RT-PCR) between March and April 2020 having (a) baseline HRCT at hospital admission and (b) predominant GGOs pattern on HRCT; a second set of 30 patients (nCOVID) showing (a) predominant GGOs pattern on HRCT performed between August 2019 and April 2020 and (b) availability of final diagnosis. Two readers independently segmented GGOs on HRCTs using a semi-automated approach, and radiomics features were extracted using a standard open source software (PyRadiomics). Partial least square (PLS) regression was used as the multivariate machine-learning algorithm. A leave-one-out nested cross-validation was implemented. PLS β-weights of radiomics features, including the 5% features with the largest β-weights in magnitude (top 5%), were obtained. The diagnostic performance of the radiomics model was assessed through receiver operating characteristic (ROC) analysis. The Youden’s test assessed sensitivity and specificity of the classification. A null hypothesis probability threshold of 5% was chosen (p < 0.05). The predictive model delivered an AUC of 0.868 (Youden’s index = 0.68, sensitivity = 93%, specificity 75%, p = 4.2 × 10–7). Of the seven features included in the top 5% features, five were texture-related. A radiomics-based machine learning signature showed the potential to accurately differentiate GGOs due to COVID-19 pneumonia from those due to other acute lung diseases. Most of the discriminant radiomics features were texture-related. This approach may assist clinician to adopt the appropriate management early, while improving the triage of patients.

AB0413 HIGH-RESOLUTION COMPUTED TOMOGRAPHY FOR THE SCREENING, RE-SCREENING AND FOLLOW-UP OF SYSTEMIC SCLEROSIS RELATED INTERSTITIAL LUNG DISEASE: RESULTS OF A EUSTAR-SCTC SURVEY

Background:High-resolution computed tomography (HRCT) is the gold standard diagnostic test for Interstitial lung disease (ILD), a significant cause of morbidity and mortality in systemic sclerosis (SSc). Different algorithms have been proposed for the screening of SSc-ILD, including the use of pulmonary function tests (Forced Vital Capacity - FVC, Lung Diffusion of Carbone Monoxyde - DLCO). A prior survey reported that 50-66% of general rheumatologists and SSc experts ordered HRCT for ILD screening in newly diagnosed SSc patients (1).Objectives:Given the recent availability of on-label treatment for SSc-ILD (2), the publication of consensus recommendations for the identification of SSc-ILD (3) and recent awareness programs for the use of HRCT to detect SSc-ILD, we aimed to re-evaluate the use of HRCT for screening, re-screening and follow-up of SSc-ILD.Methods:An invitation was sent to the European Scleroderma Trials and Research (EUSTAR) and Scleroderma Clinical Trials Consortium (SCTC) members, also advertised through social media. Answers were recorded between Nov 25th and Dec 31st 2020. Questions were asked on the use of chest HRCT at baseline, the re-screening of patients with a negative baseline HRCT and the follow-up of HRCT positive SSc-ILD patients. When HRCT was not routinely requested, additional details were collected about the parameters guiding its use. The results of the survey were tested for association with geographical origin, medical specialty, working environment, SSc referral institute and scientific group membership of the responders, using Chi-squared test.Results:205/630 (32.5%) physicians replied to the survey. Participants were widely distributed in terms of geographical origin (130 Europe, 23 Asia, 23 North America, 31 other continents), medical specialty (156 rheumatology, 21 internal medicine, 14 clinical immunology, 14 other), working environment (176 University Hospital, 12 community hospital, 17 other), SSc dedicated clinic (179 referral and 26 non-referral) and scientific group membership (98 EUSTAR, 42 SCTC, 42 EUSTAR and SCTC, 23 not declared).At SSc diagnosis, 95.7% of responders would perform HRCT: 66.7% as routine screening for ILD (67,4% of SSc referral and 62% for non-referral physicians) and 29% for diagnostic purposes (among the latter, if crackles on auscultation – 92.5%, FVC&lt;80% predicted - 86.6%, FVC±DLCO relative decline reaching the current definition of ILD progression, 86.6% or dyspnea at rest/exercise - 85.1/83.3%).During follow-up, 78.8% of responders would repeat an HRCT in baseline negative cases: 20.3% as a yearly routine screening and 64.5% for diagnostic aims (decision on the latter group was more frequently driven by FVC±DLCO relative decline indicative of ILD progression– 90.6%, new onset or worsening of dyspnoea at rest/exercise – 80.5/86.6%, new onset or worsening of lung crackles on auscultation – 82.6%).Finally, 94.5% of responders would repeat a chest HRCT after SSc-ILD diagnosis: 36.8% as a yearly routine and 56.7% according to clinical evaluation (driven by new FVC±DLCO relative decline based ILD progression – 90.8%, new onset or worsening of dyspnoea at rest/exercise – 83.2/81.7%; 5.2% to evaluate treatment effects). We found no difference in the distribution of answers among groups.Conclusion:The use of baseline HRCT for the screening of SSc-ILD has slightly increased in non-referral and remained stable in referral centers compared to previous surveys, indicating that the implementation of guidelines might be successful and awareness programs should be continued. In addition, we provide new data on use of HRCT in re-screening and follow-up. The development of validated algorithms to further support the appropriate application of HRCT at follow-up is highly needed.

POS1419 PREDICTIVE FACTORS FOR PULMONARY PROGRESSION IN PATIENTS WITH CONNECTIVE TISSUE DISEASE AND INTERSTITIAL LUNG DISEASE

Background:Interstitial lung disease (ILD) is associated with decreased quality of life and higher mortality risk in patients with connective tissue disease (CTD). Outcome and treatment response to immunosuppressive therapies is unpredictable, and therefore the management of CTD-ILD can be challenging.Objectives:Our study aimed to identify clinical and imaging factors that are predictive for outcome in patients with CTD-ILD.Methods:We performed a retrospective cohort study in patients with CTD-ILD who were treated in our centre between 2004 and 2018. Clinical, biochemical data as well as pulmonary function test (PFT) and high-resolution computed tomography (HRCT) results were recorded. Two experienced chest radiologists independently and blindly reviewed the HRCT’s. When the two chest radiologists assessed the ILD pattern differently, a diagnosis was made by consultation of a third expert. The ILD patterns were classified as fibrotic or inflammatory. Overall survival and progressive fibrosing interstitial lung disease (PF-ILD, defined as a significant decline of PFT and HRCT) after two years of treatment were assessed using a Kaplan-Meier plot. Multivariable Cox regression was including for treatment, comorbidity, and age as variables. Factors with a p value &lt; 0.2 in the univariate analysis were included in the multivariate analysis. The correlation between the variation of serum markers and PFT over-time was evaluated with Spearman’s Rho.Results:In total, 150 patients with CTD-ILD were included, of which 53 (35.3%) had systemic sclerosis, 19 (12.7%) Sjogren’s syndrome, 29 (19.3%) inflammatory myopathy, 24 (16%) rheumatoid arthritis, 5 (3.3%) systemic lupus erythematosus, 4 (2.7%) mixed connective tissue disease, and 16 (10.7%) undifferentiated connective tissue disease patients. Median disease duration of CTD was 14 months (IQR 2–73) in patients with CTD diagnosis before ILD onset. The median follow-up duration was 40 months (IQR 27.3–60.8). Thirty (20%) deaths occurred, in which the cause of death was a pulmonary infection in 6 (4%) patients and a respiratory failure due to ILD in 10 (6.7%) patients. PF-ILD occurred in 82 (54.7%) patients, which was associated with poor overall survival (HR 3.03, 95%CI 1.15–7.98) (Figure 1). Age, smoking, and steroid usage were associated with increased mortality risk as well (Table 1). There was no dose-related effect of smoking on mortality.Figure 1.The Kaplan-Meier plot for progressive fibrosing interstitial lung diseases (PF-ILD). PF-ILF was defined as pulmonary function decline or high-resolution computed tomography progression after two years of treatment.Inflammatory patterns on baseline HRCT were correlated with a lower risk of FVC decline than fibrotic patterns (OR 0.24, 95%CI 0.09–0.64). The increase in CA15.3 level was associated with the decline in FVC (Rho -0.308, p=0.037). Besides, the elevation in CRP was associated with the reduction in FVC (Rho -0.302, p=0.006) and DLCO (Rho -0.268, p=0.019).Conclusion:Our study identified several factors associated with outcomes. Age, smoking, and steroid treatment increased the risk of mortality in patient with CTD-ILD. Inflammatory HRCT pattern at baseline revealed a better pulmonary outcome than a fibrotic pattern. The patients having PF-ILD after two years of treatment showed a higher mortality risk.Table 1.Multivariable Cox-regression for the clinical risk of mortality.Clinical factorCrude HR (95%CI)PAdjusted HR (95%CI)pAge1.11 (1.06–1.15)1.7*10-61.12 (1.07–1.17)3.54*10-6Smoking1.64 (0.79–3.43)0.1872.53 (1.11–5.78)0.028Congestive heart failure1.86 (0.75–4.58)0.1791.17 (0.47–2.91)0.737MMF0.55 (0.23–1.35)0.1950.73 (0.29–1.85)0.512Steroid4.37 (1.67–11.45)0.0034.96 (1.84–13.40)0.002MMF, mycophenolate mofetil; HR, hazard ratio.Acknowledgements:We want to thank Marieke Vianen for the support in data management, Lieke Wintermans and Lisa Hessels for collecting the clinical data.Disclosure of Interests:None declared

A study design for statistical learning technique to predict radiological progression with an application of idiopathic pulmonary fibrosis using chest CT images

BackgroundIdiopathic pulmonary fibrosis (IPF) is a fatal interstitial lung disease characterized by an unpredictable decline in lung function. Predicting IPF progression from the early changes in lung function tests have known to be a challenge due to acute exacerbation. Although it is unpredictable, the neighboring regions of fibrotic reticulation increase during IPF's progression. With this clinical information, quantitative characteristics of high-resolution computed tomography (HRCT) and a statistical learning paradigm, the aim is to build a model to predict IPF progression. DesignA paired set of anonymized 193 HRCT images from IPF subjects with 6–12 month intervals were collected retrospectively. The study was conducted in two parts: (1) Part A collects the ground truth in small regions of interest (ROIs) with labels of “expected to progress” or “expected to be stable” at baseline HRCT and develop a statistical learning model to classify voxels in the ROIs. (2) Part B uses the voxel-level classifier from Part A to produce whole-lung level scores of a single-scan total probability's (STP) baseline. MethodsUsing annotated ROIs from 71 subjects' HRCT scans in Part A, we applied Quantum Particle Swarm Optimization–Random Forest (QPSO-RF) to build the classifier. Then, 122 subjects' HRCT scans were used to test the prediction. Using Spearman rank correlations and survival analyses, we ascertained STP associations with 6–12 month changes in quantitative lung fibrosis and forced vital capacity. ConclusionThis study can serve as a reference for collecting ground truth, and developing statistical learning techniques to predict progression in medical imaging.

Stratification of long-term outcome in stable idiopathic pulmonary fibrosis by combining longitudinal computed tomography and forced vital capacity.

To test HRCT with either visual or quantitative analysis in both short-term and long-term follow-up of stable IPF against long-term (transplant-free) survival, beyond 2years of disease stability. Fifty-eight IPF patients had FVC measurements and HRCTs at baseline (HRCT0), 10-14months (HRCT1) and 22-26months (HRCT2). Visual scoring, CALIPER quantitative analysis of HRCT measures, and their deltas were evaluated against combined all-cause mortality and lung transplantation by adjusted Cox proportional hazard models at each time interval. At HRCT1, a ≥ 20% relative increase in CALIPER-total lung fibrosis yielded the highest radiological association with outcome (C-statistic 0.62). Moreover, the model combining FVC% drop ≥ 10% and ≥ 20% relative increase of CALIPER-total lung fibrosis improved the stratification of outcome (C-statistic 0.69, high-risk category HR 12.1; landmark analysis at HRCT1 C-statistic 0.66, HR 14.9 and at HRCT2 C-statistic 0.61, HR 21.8). Likewise, at HRCT2, the model combining FVC% decrease trend and ≥ 20% relative increase of CALIPER-pulmonary vessel-related volume (VRS) improved the stratification of outcome (C-statistic 0.65, HR 11.0; landmark analysis at HRCT1 C-statistic 0.62, HR 13.8 and at HRCT2 C-statistic 0.58, HR 12.6). A less robust stratification of outcome distinction was also demonstrated with the categorical visual scoring of disease change. Annual combined CALIPER -FVC changes showed the greatest stratification of long-term outcome in stable IPF patients, beyond 2years. • Longitudinal high-resolution computed tomography (HRCT) data is more helpful than baseline HRCT alone for stratification of long-term outcome in IPF. • HRCT changes by visual or quantitative analysis can be added with benefit to the current spirometric reference standard to improve stratification of long-term outcome in IPF. • HRCT follow-up at 12-14months is more helpful than HRCT follow-up at 23-26months in clinically stable subjects with IPF.

Assessment of Lung Cancer Development in Idiopathic Pulmonary Fibrosis Patients Using Quantitative High-Resolution Computed Tomography: A Retrospective Analysis.

The purpose of this study was to investigate histogram-based quantitative high-resolution computed tomography (HRCT) indexes in the assessment of lung cancer (LC) development in idiopathic pulmonary fibrosis (IPF) patients. From IPF databases of 2 national respiratory centers, we retrospectively studied patients with and without LC development-respectively, divided into Group A (n=16) and Group B (n=33). The extent of fibrotic disease was quantified on baseline and follow-up HRCT examinations using kurtosis, skewness, percentage of high attenuation area (HAA%), and percentage of fibrotic area (FA%). These indexes were compared between the 2 groups using the Mann-Whitney U test. In the prediction of LC development, receiver operating characteristic analysis was performed to assess threshold values of HRCT indexes. At baseline, no difference was reported among groups for kurtosis, skewness, HAA%, and FA%, with P-values of 0.0881, 0.0606, 0.0578, and 0.0606, respectively. On follow-up, significant differences were reported, with P-values of 0.0174 for kurtosis, 0.0313 for skewness, 0.0297 for HAA%, and 0.0407 for FA%.On baseline HRCT, in the prediction of LC development, receiver operating characteristic analysis reported sensibility and specificity of 87.5% and 45.45% for kurtosis, 68.75% and 63.64% for skewness, 81.25% and 54.55% for FA%, and 75% and 60.61% for HAA%. LC development is associated with progression of fibrosis; at baseline, FA% and HAA% reported more convenient sensitivity/specificity ratios in the prediction of LC development.

Interstitial lung abnormalities in patients with early rheumatoid arthritis: A pilot study evaluating prevalence and progression.

Pulmonary disease is a leading cause of morbidity and mortality in rheumatoid arthritis (RA). In this study, we investigated the prevalence and progression of interstitial lung abnormalities (ILA) in a prospective cohort study of 18 subjects with early RA. Eighteen adults diagnosed with anti-citrullinated protein-antibody-positive RA within the prior year underwent baseline high-resolution computed tomography (HRCT), symptom assessment, and pulmonary function and laboratory testing. The follow-up HRCT and clinical assessment were completed after 1 year. Seven of the 18 patients (39%) had baseline HRCT abnormalities including septal thickening, honeycombing, ground glass opacities, and/or traction bronchiectasis. At follow-up, 6 out of the 7 subjects (86%) with ILAs at baseline exhibited progression, while 10 out of 11 (91%) without ILAs at baseline remained stable. A higher Clinical Chronic Obstructive Pulmonary Disease Questionnaire score was associated with both the presence and progression of HRCT abnormalities (10 vs 2, p=0.045; 10 vs 2, p=0.009, respectively). C-reactive protein (CRP) trended higher in patients with radiologic abnormalities (3.5 mg/L vs 1.1 mg/L, p=0.08) and was significantly higher in those with progression (3.5 mg/L vs 1 mg/L, p=0.024). Smoking, pulmonary function, and autoantibodies were not associated with HRCT abnormalities. ILAs are prevalent in patients with early RA. If identified at baseline, radiographic progression of ILAs after 1 year is likely, while those without ILAs at baseline are unlikely to develop new ILAs. In addition, early respiratory symptoms and higher CRP levels may correlate with the presence and progression of underlying ILAs.

Prediction of progression in idiopathic pulmonary fibrosis using CT scans at baseline: A quantum particle swarm optimization - Random forest approach.

Idiopathic pulmonary fibrosis (IPF) is a fatal lung disease characterized by an unpredictable progressive decline in lung function. Natural history of IPF is unknown and the prediction of disease progression at the time of diagnosis is notoriously difficult. High resolution computed tomography (HRCT) has been used for the diagnosis of IPF, but not generally for monitoring purpose. The objective of this work is to develop a novel predictive model for the radiological progression pattern at voxel-wise level using only baseline HRCT scans. Mainly, there are two challenges: (a) obtaining a data set of features for region of interest (ROI) on baseline HRCT scans and their follow-up status; and (b) simultaneously selecting important features from high-dimensional space, and optimizing the prediction performance. We resolved the first challenge by implementing a study design and having an expert radiologist contour ROIs at baseline scans, depending on its progression status in follow-up visits. For the second challenge, we integrated the feature selection with prediction by developing an algorithm using a wrapper method that combines quantum particle swarm optimization to select a small number of features with random forest to classify early patterns of progression. We applied our proposed algorithm to analyze anonymized HRCT images from 50 IPF subjects from a multi-center clinical trial. We showed that it yields a parsimonious model with 81.8% sensitivity, 82.2% specificity and an overall accuracy rate of 82.1% at the ROI level. These results are superior to other popular feature selections and classification methods, in that our method produces higher accuracy in prediction of progression and more balanced sensitivity and specificity with a smaller number of selected features. Our work is the first approach to show that it is possible to use only baseline HRCT scans to predict progressive ROIs at 6 months to 1year follow-ups using artificial intelligence.

Mycophenolate mofetil versus oral cyclophosphamide in scleroderma-related interstitial lung disease (SLS II): a randomised controlled, double-blind, parallel group trial

SummaryBACKGROUNDTwelve months of oral cyclophosphamide (CYC) has been shown to alter the progression of scleroderma-related interstitial lung disease (SSc-ILD) when compared to placebo. However, toxicity was a concern and without continued treatment the efficacy disappeared by 24 months. We hypothesized that a two-year course of mycophenolate mofetil (MMF) would be safer, better tolerated and produce longer lasting improvements than CYC.METHODSPatients with SSc-ILD meeting defined dyspnea, pulmonary function and high-resolution computed tomography (HRCT) criteria were randomized in a double-blind, two-arm trial at 14 medical centers. MMF (target dose 1500 mg twice daily) was administered for 24 months in one arm and oral CYC (target dose 2·0 mg/kg/day) administered for 12 months followed by placebo for 12 months in the other arm. The primary endpoint, change in forced vital capacity as a percent of the predicted normal value (FVC %) over the course of 24 months, was assessed in a modified intention-to-treat analysis using an inferential joint model combining a mixed effects model for longitudinal outcomes and a survival model to handle non-ignorable missing data. The study was registered with ClinicalTrials.gov, number NCT00883129, and is closed.RESULTSBetween November, 2009, and January, 2013, 142 patients were randomized. 126 patients (63 MMF; 63 CYC) with acceptable baseline HRCT studies and at least one outcome measure were included in the analysis. The adjusted FVC % (primary endpoint) improved from baseline to 24 months by 2.17 in the MMF arm (95% CI, 0.53–3.84) and 2·86 in the CYC arm (95% confidence interval 1·19–4·58) with no significant between-treatment difference (p=0·24), indicating that the trial was negative for the primary endpoint. However, in a post-hoc analysis of the primary endpoint, within-treatment improvements from baseline to 24 months were noted in both the CYC and MMF arms. A greater number of patients on CYC than on MMF prematurely withdrew from study drug (32 vs 20) and failed treatment (2 vs 0), and the time to stopping treatment was significantly shorter in the CYC arm (p=0·019). Sixteen deaths occurred (11 CYC; 5 MMF) with most due to progressive ILD. Leukopenia (30 vs 4 patients) and thrombocytopenia (4 vs 0 patients) occurred more often in patients treated with CYC. In post-hoc analyses, within- (but not between-) treatment improvements were also noted in defined secondary outcomes including skin score, dyspnea and whole-lung HRCT scores.INTERPRETATIONTreatment of SSc-ILD with MMF for two years or CYC for one year both resulted in significant improvements in pre-specified measures of lung function, dyspnea, lung imaging, and skin disease over the 2-year course of the study. While MMF was better tolerated and associated with less toxicity, the hypothesis that it would have greater efficacy at 24 months than CYC was not confirmed. These findings support the potential clinical impact of both CYC and MMF for progressive SSc-ILD, as well as the current preference for MMF due to its better tolerability and toxicity profile.FUNDINGNational Heart, Lung and Blood Institute/National Institutes of Health with drug supply provided by Hoffmann-La Roche/Genentech.

Role of HRCT Chest in Post Stem Cell Transplant Recipients Suspected of Pulmonary Complications.

Stem cell transplantation is today's procedure of choice for management of various hematopoietic malignant and severe immunogenic disorders. High Resolution Computed Tomography (HRCT) is a common technique for the diagnosis of pulmonary complications in stem cell transplant recipients. There are a large number of complications which can complicate the post-transplant period. To study the role of HRCT chest in stem cell transplant patients developing pulmonary complications, detect any evidence of infection, detect clinical signs of lung infections, Graft versus Host Disease (GvHD) or other regimen related toxicities outlined earlier, detect any evidence of GvHD and correlate these clinical signs with radiological changes in the lungs. The study was a prospective study of 52 participants with indication of stem cell transplantation. The study included recipients of HSCT transplant and the exclusion criteria was patients who failed for engraftment and having an associated history of pulmonary embolism. Patients were screened for pre-transplant chemotherapy, clinical examination, laboratory investigations including blood and biochemical examinations, imaging by ultrasound, chest radiography, baseline HRCT and a follow-up for post-transplant infections and complications with 16 slice Siemens CT scan. Statistical analysis was done using Pearson's chi-squared test. Four patients among the total 56 were excluded due to non-engraftment. The most common associated findings in decreasing order are (these patients died): consolidation, pancytopenia and gastrointestinal tract symptoms with VOD (Veno-Occlusive Disease). These findings were seen on HRCT as consolidation, cavities, ground glass opacities, fibrotic changes, bronchiectatic changes and tree in bud appearance. The study highlights the significant positive findings on the HRCT which were missed on routine chest radiograph and can be used for early diagnoses. Thus, HRCT helped in decreasing the mortality. The abnormal vitals and TLC counts showed a significant relation between the numbers of death in the study.

Predictors of clinical outcome in emphysema patients with atelectasis following endoscopic valve therapy

Background: The aim of endoscopic valve therapy in emphysema patients is a complete lobar atelectasis of the most emphysematous destroyed lobe. Despite radiological advent of atelectasis, a great variability in the clinical outcome can be observed. Objective: Baseline lung function, exercise test and high resolution computed tomography (HRCT) variables were analysed to identify predictors of clinical outcome following valve therapy. Methods: Baseline clinical measures (VC, FEV 1 , RV, 6-MWT) and HRCT variables (low attenuation volume (LAV) of target lobe, LAV% of target and of ipsilateral untreated lobe, LAV of target lobe to LAV of target lung and to LAV of total lung) of 77 patients with complete lobar atelectasis after valve therapy were examined for their impact on outcome (changes of VC, FEV 1 , RV, 6-MWT from baseline to time point of atelectasis). Results: LAV of target lobe to LAV of target lung predicts significantly FEV 1 improvement in patients with complete lobar atelectasis following valve therapy. A 10% difference in that CT predictor was associated with a 82ml improvement in FEV 1 at the time of atelectasis (p=0.006). For 6-MWT, LAV% of target lobe (p=0.064) was found to be a predictor. A 10% difference in the LAV% of target lobe was associated with a 7.7meters improvement. Worse 6-MWT, low VC and high RV at baseline were associated significantly with greater improvement for the respective parameter (all p Conclusion: LAV of target lobe to LAV of target lung and baseline clinical measures seem to predict significantly clinical outcome in patients with complete lobar atelectasis following valve treatment. Data have to be confirmed in a larger prospective study.

Predictive value of serial high-resolution computed tomography analyses and concurrent lung function tests in systemic sclerosis.

Systemic sclerosis (SSc) carries a high risk of progressive interstitial lung disease (ILD), but tools for stratifying individual risk are scarce. The purpose of this study was to assess detailed data from serial lung fibrosis measurements and paired pulmonary function tests (PFTs) as outcome prediction tools in a prospective cohort of SSc patients. Paired PFTs and high-resolution computed tomography (HRCT) scans were obtained at baseline and at followup in 305 SSc patients who met the American College of Rheumatology/European League Against Rheumatism 2013 classification criteria. The extent of fibrosis was scored on 10 sections from every HRCT scan and expressed as the percentage of the total lung volume. Baseline HRCT analyses revealed 3 SSc subgroups: those with >20% lung fibrosis (n = 40), those with 1-20% fibrosis (n = 157), and those with no fibrosis (n = 108). At followup HRCT (mean of 3.1 years later), all 108 group 3 patients were still free of fibrosis. In group 2 patients, 146 continued to have 1-20% fibrosis (group 2a), whereas 11 (marked by short disease duration of 1.3 years) had experienced progression to >20% fibrosis (group 2b). The annual fibrosis progression rate differed across the 4 groups: 0.9% in group 1, 0.7% in group 2a, 5.9% in group 2b, and 0% in group 3. The annual fibrosis progression rate correlated with the total decline in the forced vital capacity (FVC) (7.1%, 5.7%, 8.7%, and 2.9% in groups 1, 2a, 2b, and 3, respectively), but not the diffusing capacity for carbon monoxide (DLco) (8.4%, 7.7%, 7.7%, and 8.6%, respectively). Multivariate analyses identified anticentromere antibodies (odds ratio [OR] 4.7) and baseline DLco (OR 1.04) as predictors of no fibrosis at followup and baseline fibrosis (OR 1.3) and FVC (OR 0.96) as predictors of >20% fibrosis at followup. These prospective cohort data suggest that HRCT performed at baseline predicts the development of fibrosis, the rate of progression of fibrosis, and the decline in pulmonary function in SSc.