Evaluation of computer-based computer tomography stratification against outcome models in connective tissue disease-related interstitial lung disease: a patient outcome study

Abstract

BackgroundTo evaluate computer-based computer tomography (CT) analysis (CALIPER) against visual CT scoring and pulmonary function tests (PFTs) when predicting mortality in patients with connective tissue disease-related interstitial lung disease (CTD-ILD). To identify outcome differences between distinct CTD-ILD groups derived following automated stratification of CALIPER variables.MethodsA total of 203 consecutive patients with assorted CTD-ILDs had CT parenchymal patterns evaluated by CALIPER and visual CT scoring: honeycombing, reticular pattern, ground glass opacities, pulmonary vessel volume, emphysema, and traction bronchiectasis. CT scores were evaluated against pulmonary function tests: forced vital capacity, diffusing capacity for carbon monoxide, carbon monoxide transfer coefficient, and composite physiologic index for mortality analysis. Automated stratification of CALIPER-CT variables was evaluated in place of and alongside forced vital capacity and diffusing capacity for carbon monoxide in the ILD gender, age physiology (ILD-GAP) model using receiver operating characteristic curve analysis.ResultsCox regression analyses identified four independent predictors of mortality: patient age (P < 0.0001), smoking history (P = 0.0003), carbon monoxide transfer coefficient (P = 0.003), and pulmonary vessel volume (P < 0.0001). Automated stratification of CALIPER variables identified three morphologically distinct groups which were stronger predictors of mortality than all CT and functional indices. The Stratified-CT model substituted automated stratified groups for functional indices in the ILD-GAP model and maintained model strength (area under curve (AUC) = 0.74, P < 0.0001), ILD-GAP (AUC = 0.72, P < 0.0001). Combining automated stratified groups with the ILD-GAP model (stratified CT-GAP model) strengthened predictions of 1- and 2-year mortality: ILD-GAP (AUC = 0.87 and 0.86, respectively); stratified CT-GAP (AUC = 0.89 and 0.88, respectively).ConclusionsCALIPER-derived pulmonary vessel volume is an independent predictor of mortality across all CTD-ILD patients. Furthermore, automated stratification of CALIPER CT variables represents a novel method of prognostication at least as robust as PFTs in CTD-ILD patients.Electronic supplementary materialThe online version of this article (doi:10.1186/s12916-016-0739-7) contains supplementary material, which is available to authorized users.

Evaluation of visual and computer‐based CT analysis for the identification of functional patterns of obstruction and restriction in hypersensitivity pneumonitis

“…In the current study, PVV and ILD extent, scored visually and with CALIPER, were independently predictive of FVC, DL CO and CPI, replicating findings in IPF . Whilst the pathophysiological basis of the CALIPER PVV signal is unclear, the results of the current study support previous findings in IPF and connective tissue disease‐related ILD, which suggested that the PVV signal may reflect a combination of both interstitial extent and vascular damage. As previously stated, whilst the majority of the PVV signal arises from the vasculature, in cases with more extensive fibrosis, the PVV measure may capture some perivascular fibrosis or peripheral reticulation, which may be reduced with refinement of the tool.…”

“…with 5 and 7 years of thoracic imaging experience, respectively, blinded to all clinical information. Visual CT scoring and consensus derivation have been previously described . CT patterns scored visually on a lobar basis included ground‐glass opacities, reticular pattern, honeycombing, consolidation, gas trapping (which comprised separate scores of emphysema and mosaic attenuation (the decreased attenuation component)) and traction bronchiectasis …”

Predicting Outcomes in Idiopathic Pulmonary Fibrosis Using Automated Computed Tomographic Analysis

“…New computer algorithms utilising three-dimensional volumetric CT datasets, can quantify parenchymal pattern extents (27,28) and have been shown to better predict survival in various fibrosing lung diseases at baseline, than visual CT scores (29,30). Computer analysis also has the potential to uncover CT features hitherto under-recognised by visual CT analysis that predict mortality in IPF.…”

Hypersensitivity pneumonitis: A protean and challenging disease

“…evaluated the utility of CALIPER (Computer‐Aided Lung Informatics for Pathology Evaluation and Rating) compared with visual scoring for quantitating radiological patterns in HP against functional indices of pulmonary disease. In previous reports, the authors have shown CALIPER correlated better with physiological measures of lung disease (forced expiratory volume in 1 s, FEV 1 , and forced vital capacity, FVC) in IPF patients and for mortality prediction in connective tissue disease associated ILD (CTD‐ILD) compared with visual scores …”