Interstitial lung disease in systemic sclerosis

Applicability of radiomics in interstitial lung disease associated with systemic sclerosis: proof of concept

Objective

To retrospectively evaluate if texture-based radiomics features are able to detect interstitial lung disease (ILD) and to distinguish between the different disease stages in patients with systemic sclerosis (SSc) in comparison with mere visual analysis of high-resolution computed tomography (HRCT).

Methods

Sixty patients (46 females, median age 56 years) with SSc who underwent HRCT of the thorax were retrospectively analyzed. Visual analysis was performed by two radiologists for the presence of ILD features. Gender, age, and pulmonary function (GAP) stage was calculated from clinical data (gender, age, pulmonary function test). Data augmentation was performed and the balanced dataset was split into a training (70%) and a testing dataset (30%). For selecting variables that allow classification of the GAP stage, single and multiple logistic regression models were fitted and compared by using the Akaike information criterion (AIC). Diagnostic accuracy was evaluated from the area under the curve (AUC) from receiver operating characteristic (ROC) analyses, and diagnostic sensitivity and specificity were calculated.

Results

Values for some radiomics features were significantly lower (p < 0.05) and those of other radiomics features were significantly higher (p = 0.001) in patients with GAP2 compared with those in patients with GAP1. The combination of two specific radiomics features in a multivariable model resulted in the lowest AIC of 10.73 with an AUC of 0.96, 84% sensitivity, and 99% specificity. Visual assessment of fibrosis was inferior in predicting individual GAP stages (AUC 0.86; 83% sensitivity; 74% specificity).

Conclusion

The correlation of radiomics with GAP stage, but not with the visually defined features of ILD-HRCT, implies that radiomics might capture features indicating severity of SSc-ILD on HRCT, which are not recognized by visual analysis.

Key Points

• Radiomics features can predict GAP stage with a sensitivity of 84% and a specificity of almost 100%.

• Extent of fibrosis on HRCT and a combined model of different visual HRCT-ILD features perform worse in predicting GAP stage.

• The correlation of radiomics with GAP stage, but not with the visually defined features of ILD-HRCT, implies that radiomics might capture features on HRCT, which are not recognized by visual analysis.

Electronic supplementary material

The online version of this article (10.1007/s00330-020-07293-8) contains supplementary material, which is available to authorized users.

Cross-sectional study of soluble selectins, fractions of circulating microparticles and their relationship to lung and skin involvement in systemic sclerosis

Background

Endothelial damage and activation may play central roles in the pathogenesis of systemic sclerosis (SSc) and are reflected by microparticles (MPs) and soluble selectins. The objective of this study was to determine if these potential biomarkers are associated with specific organ involvements or cutaneous subgroups of SSc patients.

Method

MPs in platelet-poor plasma from 121 patients with SSc, 79 and 42 with limited and diffuse cutaneous disease, respectively, were characterized by flow cytometry for their capacity to bind annexin V in combination with surface markers of either platelets (PMPs), leukocytes (LMPs) or endothelial cells (EMPs). Soluble E- and P-selectin levels were determined in plasma. By correlation analyses, this was held against involvement of skin, lung function, lung fibrosis, pulmonary artery hypertension, and serology.

Results

None of the markers were associated with cutaneous subgroups of SSc. Concentrations of annexin V non-binding EMPs and annexin V non-binding LMPs were negatively correlated to pulmonary diffusing capacity (DL_CO) (r = -0.28; p = 0.003; r = -0.26; p = 0.005) and forced vital capacity (FVC) (r = -0.24; p = 0.009; r = -0.29; p = 0.002), driven by patients with limited and diffuse cutaneous disease, respectively. Soluble E-selectin levels correlated negatively to DL_CO (r = -0.21, p = 0.03) and FVC (r = -0.25; p = 0.007); and soluble P-selectin correlated negatively to DL_CO (r = -0.23, p = 0.01).

Conclusion

Negative correlations between annexin V non-binding EMP and LMP concentrations with lung function parameters (DL_CO and FVC) differed between limited and diffuse cutaneous subsets of SSc, indicative of various pathogeneses of lung involvement in SSc, possibly with a differential role of MPs.

HRCT and pulmonary function tests in monitoring of lung involvement in juvenile systemic sclerosis

OBJECTIVE

To investigate the role of high-resolution computed tomography (HRCT) and pulmonary function tests (PFTs) in staging pulmonary involvement in juvenile systemic sclerosis (JSS).

METHODS

Clinical charts of 17 JSS patients (pts) were reviewed and high-resolution CT (HRCT) scans and PFTs performed at first and last visit were examined. Forced expiratory volume in 1 sec (FEV(1)), forced vital capacity (FVC) and carbon monoxide diffusing capacity [DL(CO)] were measured (% pred. values) while HRCT changes were graded according to the Schurawitzki method (min-max score: 0-18).

RESULTS

At initial assessment, 10 pts (58.8%) had pulmonary involvement (HRCT score >0 and/or PFTs <80% pred. values). PTFs abnormalities were consistent with a restrictive defect, with low FEV(1), FVC and DL(CO) values and normal FEV(1)/FVC ratio. At first visit HRCT scores were inversely correlated with FEV(1) (r = -0.75; P = 0.02), FVC (r = -0.685; P = 0.035), and DL(CO) values (r = -0.71; P = 0.03), but not with the FEV(1)/FVC ratio (r = -0.36; P = 0.31). Stronger inverse correlations were detected at last visit (median time interval: 4.3 years; min-max: 1-10 years) between HRCT and FEV(1) (r = -0.86; P = 0.002), FVC (r = -0.79; P = 0.009) and DL(CO) (r = -0.79; P = 0.009), but not with the FEV(1)/FVC ratio (r = -0.33; P = 0.35). Changes in HRCT scores between first and last visit were correlated with changes in FEV(1) (r = -0.74; P = 0.02), FVC (r = -0.81; P = 0.007), but not in DL(CO) values (r = 0.07;P = 0.84). At the last visit, of the 10 pts with pulmonary involvement at initial assessment 5 showed worsening of lung involvement and 5 either no significant changes in PFTs and HRCT or mild improvement.

CONCLUSIONS

PFTs, namely lung volumes, represent a reliable "monitoring" tool in children with JSS to identify pts that need to undergo an HRCT to rule out initial pulmonary involvement and to monitor the course of ILD over time. The weaker clinical value of DL(CO) may relate to poor lung function technique in some younger children.