Idiopathic Pulmonary Fibrosis: Data-driven Textural Analysis of Extent of Fibrosis at Baseline and 15-Month Follow-up

Abstract

Purpose To evaluate associations between pulmonary function and both quantitative analysis and visual assessment of thin-section computed tomography (CT) images at baseline and at 15-month follow-up in subjects with idiopathic pulmonary fibrosis (IPF). Materials and Methods This retrospective analysis of preexisting anonymized data, collected prospectively between 2007 and 2013 in a HIPAA-compliant study, was exempt from additional institutional review board approval. The extent of lung fibrosis at baseline inspiratory chest CT in 280 subjects enrolled in the IPF Network was evaluated. Visual analysis was performed by using a semiquantitative scoring system. Computer-based quantitative analysis included CT histogram-based measurements and a data-driven textural analysis (DTA). Follow-up CT images in 72 of these subjects were also analyzed. Univariate comparisons were performed by using Spearman rank correlation. Multivariate and longitudinal analyses were performed by using a linear mixed model approach, in which models were compared by using asymptotic χ tests. Results At baseline, all CT-derived measures showed moderate significant correlation (P < .001) with pulmonary function. At follow-up CT, changes in DTA scores showed significant correlation with changes in both forced vital capacity percentage predicted (ρ = -0.41, P < .001) and diffusing capacity for carbon monoxide percentage predicted (ρ = -0.40, P < .001). Asymptotic χ tests showed that inclusion of DTA score significantly improved fit of both baseline and longitudinal linear mixed models in the prediction of pulmonary function (P < .001 for both). Conclusion When compared with semiquantitative visual assessment and CT histogram-based measurements, DTA score provides additional information that can be used to predict diminished function. Automatic quantification of lung fibrosis at CT yields an index of severity that correlates with visual assessment and functional change in subjects with IPF. RSNA, 2017.

Presentation, diagnosis and clinical course of the spectrum of progressive-fibrosing interstitial lung diseases

“…In nearly all cases, high-resolution computed tomography (HRCT) is the primary tool for diagnosis [5]. HRCT (in particular, the fibrosis score) can also help determine the prognosis in ILDs, and quantitative computed tomography (CT) analysis may be useful for evaluating disease progression [17][18][19] (the article by WALSH et al [20] in this issue of the European Respiratory Review provides more detail on imaging in fibrosing ILDs that may present a progressive phenotype). ILD diagnoses should be categorised as confident, provisional or unclassifiable depending on the level of diagnostic confidence.…”

When Machines Think: Radiology’s Next Frontier

“…In chess, ML is valuable in any setting that will benefit from efficiently detecting patterns in complex data. In radiology, for example, ML has been used to predict genetic variations in low-grade gliomas (4), to identify genetic phenotypes in small-cell lung carcinoma (5), to decrease false-positive results in screening mammography CAD (6), to improve pathologic mediastinal lymph node detection (7), to automatically perform bone age assessment (8), and to quantify lung fibrosis on computed tomographic (CT) images (9).…”

Optimization of a secondary VOI protocol for lung imaging in a clinical CT scanner

“…For example, in interstitial lung disease, early signs of disease which manifest as interstitial lung abnormalities (ILA) on chest CT scans have been associated with numerous risk factors for disease . A recent clinical study also concluded that changes in CT texture measures are significantly correlated with changes of pulmonary function in patients with idiopathic pulmonary fibrosis, and can be used to predict diminished function in these patients . Therefore, a detailed view of such features would allow for earlier diagnoses, faster determination and better monitoring of treatment.…”