Predicting Outcomes in Idiopathic Pulmonary Fibrosis Using Automated Computed Tomographic Analysis

Abstract

Short running head: IPF baseline outcome prediction Word count: 4310 wordsThis article has an online data supplement, which is accessible from this issue's table of content online at www.atsjournals.org At a Glance: Quantification of CT parenchymal patterns in idiopathic pulmonary fibrosis using computer tools has been suggested as a method that can improve on mortality prediction using visual CT scoring. As computer technology advances, it has now become possible to study CT parenchymal features that have no visual correlate. Our study demonstrates that computer-derived vessel-related structure scores can outperform current gold-standard measures of outcome in idiopathic pulmonary fibrosis such as forced vital capacity decline. Specifically, we demonstrate that using thresholds of computer-derived vessel-related structure scores for cohort enrichment can identify idiopathic pulmonary fibrosis patients that respond to antifibrotic medication with reduced FVC decline and improved survival.Importantly, the vessel-related structure thresholds would be able to reduce idiopathic pulmonary fibrosis drug-trial population sizes by 26% thereby dramatically reducing study costs. JJ and AUW were also involved in the conception and design of the study.BJB, RK and SR invented and developed CALIPER. They were involved in processing the raw CT scans and in generation of figures but were not involved with the analysis or interpretation of the data in the study. When used as a cohort enrichment tool, a CALIPER VRS score >4.4% of the lung was able to reduce the requisite sample size of an IPF drug trial by 26%. Conclusions:Our study has validated a new quantitative CT measure in IPF patients fulfilling drug trial entry criteria, the VRS scores, that outperformed current goldstandard measures of outcome. When used for cohort enrichment in an IPF drugtrial setting, VRS threshold scores can reduce a required IPF drug trial population size by 25%, thereby limiting prohibitive trial costs. Importantly VRS scores identify patients in whom antifibrotic medication prolongs life and reduces forced vital capacity decline. 6

Quantitative CT‐derived vessel metrics in idiopathic pulmonary fibrosis: A structure–function study

“…We identified relatively stronger inverse relationships between lung function indices and vessel volume in the upper/middle zones compared to the lower lung zones. These results are in line with previous reports of stronger links between FVC decline and mortality in baseline upper/middle zone VRS when compared to lower zone VRS in patients with IPF . MRI studies have demonstrated that fibrotic tissues show delayed contrast enhancement when compared to morphologically normal appearing lung in lung fibrosis patients .…”

“…Whilst the majority of automated parenchymal features reflect patterns scored visually by radiologists, there has been increasing focus on novel CT patterns that computer tools can recognize, but which cannot be quantified visually. An example is the vessel‐related structures (VRS) readout determined by CALIPER, which was able to powerfully predict outcome in patients with IPF . However, until now, CALIPER has been the only tool used to evaluate vasculature in patients with lung fibrosis.…”

The therapy of idiopathic pulmonary fibrosis: what is next?

“…Furthermore, CT densitometry, especially the area right of the inflexion point in HRCT histogram was reported to correlate with lung function decline [71]. JACOB et al [72] reported recently that a computer scoring based quantification of parenchymal patterns including vessel-related structure scores predicted IPF mortality and functional decline in IPF. Hyperpolarised xenon-129 magnetic resonance imaging could be a potential non-invasive method for estimating gas-exchange impairment in IPF, as this inert gas is able to image the distribution in airspaces as well as in the red blood cells of the vessels and in tissue of interstitial parenchyma [73].…”

Longitudinal prediction of outcome in idiopathic pulmonary fibrosis using automated CT analysis

“…IPF was diagnosed by multidisciplinary teams in patients receiving two non-contrast volumetric CT scans between 5 and 30 months apart as part of their clinical care. Previous baseline analyses of IPF patients 5 made it apparent that variable initiation time of antifibrotics and varied dosages, durations and types of antifibrotic medication in study participants had a profound confounding effect on mortality relationships. Specifically, patients not uncommonly began antifibrotics between the first and second CTs and in most cases after the second CT. Consequently, cardinal analyses in the current manuscript were restricted to patients not receiving any anti-fibrotic therapy (n=118).…”