Research Article: Predicting clinical outcome with phenotypic clusters using quantitative CT fibrosis and emphysema features in patients with idiopathic pulmonary fibrosis

Date Published: April 18, 2019

Publisher: Public Library of Science

Author(s): So Hyeon Bak, Hye Yun Park, Jin Hyun Nam, Ho Yun Lee, Jeong Hyun Lee, Insuk Sohn, Man Pyo Chung, Konstantinos Kostikas.


The clinical course of IPF varies. This study sought to identify phenotyping with quantitative computed tomography (CT) fibrosis and emphysema features using a cluster analysis and to assess prognostic impact among identified clusters in patient with idiopathic pulmonary fibrosis (IPF). Furthermore, we evaluated the impact of fibrosis and emphysema on lung function with development of a descriptive formula.

This retrospective study included 205 patients with IPF. A texture-based automated system was used to quantify areas of normal, emphysema, ground-glass opacity, reticulation, consolidation, and honeycombing. Emphysema index was obtained by calculating the percentage of low attenuation area lower than -950HU. We used quantitative CT features and clinical features for clusters and assessed the association with prognosis. A formula was derived using fibrotic score and emphysema index on quantitative CT.

Three clusters were identified in IPF patients using a quantitative CT score and clinical values. Prognosis was better in cluster1, with a low extent of fibrosis and emphysema with high forced vital capacity (FVC) than cluster2 and cluster3 with higher fibrotic score and emphysema (p = 0.046, and p = 0.026). In the developed formula [1.5670—fibrotic score(%)*0.04737—emphysema index*0.00304], a score greater ≥ 0 indicates coexisting of pulmonary fibrosis and emphysema at a significant extent despite of normal spirometric result.

Cluster analysis identified distinct phenotypes, which predicted prognosis of clinical outcome. Formula using quantitative CT values is useful to assess extent of pulmonary fibrosis and emphysema with normal lung function in patients with IPF.

Partial Text

Idiopathic pulmonary fibrosis (IPF) is the most common form of chronic, progressive, interstitial pneumonia with restrictive ventilator dysfunction and reduced gas exchange [1, 2]. The prognosis of IPF is poor overall, with mean survival ranging from 2.5 to 5 years after definite diagnosis [3]. However, the clinical course of IPF varies substantially [4]. Predicting the clinical course or outcome for an individual patient is important but difficult. Clinical variables correlated with survival include age, sex, smoking status, dyspnea, pulmonary functions, digital clubbing, body mass index, and pulmonary hypertension [5]. Computed tomography (CT) plays a central role in the systemic assessment of patients with suspected IPF [6]. The extent of lung fibrosis on CT correlates with disease severity and mortality in interstitial lung disease [4, 7, 8]. Visual scoring of IPF by radiologists is limited by the availability of specialist radiologists and high interobserver variability and is somewhat subjective. There is moderate interobserver agreement among radiologists in identifying honeycombing, which is a diagnostic criterion of IPF [9]. Compared with visual assessment, quantitative analysis of IPF offers an objective, detailed, and reproducible measurement of the extent of IPF [1, 10].

In the present study, quantitative CT features dealing both with fibrotic score and emphysema index were used for clustering of radiologic phenotyping in patients with IPF, yielding three clusters. The radiologic phenotypic subgroups identified using cluster analysis according quantitative CT features differed substantially in survival. Furthermore, we identified that the developed formula could provide important information about extent of fibrosis and emphysema with normal lung function in patients with IPF.

In conclusion, quantitative CT features related to both fibrosis and emphysema were used to classify cases into three discrete subgroups with unique radiologic phenotypes and different survival. Prognosis worsens as the extent of quantitative CT fibrosis increases, and the extent of GGO in patients with severe fibrosis may affect prognosis. In addition, cluster analysis showed that emphysema could affect FVC. The relative extent of quantitative emphysema and fibrosis on CT could help to predict lung function based on the developed formula.




Leave a Reply

Your email address will not be published.