CT-based body composition analysis and pulmonary fat attenuation volume as biomarkers to predict overall survival in patients with non-specific interstitial pneumonia

Abstract

Background: Non-specific interstitial pneumonia (NSIP) is an interstitial lung disease that can result in end-stage fibrosis. We investigated the influence of body composition and pulmonary fat attenuation volume (CTpfav) on overall survival (OS) in NSIP patients.

Methods: In this retrospective single-center study, 71 NSIP patients with a median age of 65 years (interquartile range 21.5), 39 females (55%), who had a computed tomography from August 2009 to February 2018, were included, of whom 38 (54%) died during follow-up. Body composition analysis was performed using an open-source nnU-Net-based framework. Features were combined into: Sarcopenia (muscle/bone); Fat (total adipose tissue/bone); Myosteatosis (inter-/intra-muscular adipose tissue/total adipose tissue); Mediastinal (mediastinal adipose tissue/bone); and Pulmonary fat index (CTpfav/lung volume). Kaplan-Meier analysis with a log-rank test and multivariate Cox regression were used for survival analyses.

Results: Patients with a higher (> median) Sarcopenia and lower (< median) Mediastinal Fat index had a significantly better survival probability (2-year survival rate: 83% versus 71% for high versus low Sarcopenia index, p = 0.023; 83% versus 72% for low versus high Mediastinal fat index, p = 0.006). In univariate analysis, individuals with a higher Pulmonary fat index exhibited significantly worse survival probability (2-year survival rate: 61% versus 94% for high versus low, p = 0.003). Additionally, it was an independent risk predictor for death (hazard ratio 2.37, 95% confidence interval 1.03-5.48, p = 0.043).

Conclusion: Fully automated body composition analysis offers interesting perspectives in patients with NSIP. Pulmonary fat index was an independent predictor of OS.

Relevance statement: The Pulmonary fat index is an independent predictor of OS in patients with NSIP and demonstrates the potential of fully automated, deep-learning-driven body composition analysis as a biomarker for prognosis estimation.

Key points: This is the first study assessing the potential of CT-based body composition analysis in patients with non-specific interstitial pneumonia (NSIP). A single-center analysis of 71 patients with board-certified diagnosis of NSIP is presented Indices related to muscle, mediastinal fat, and pulmonary fat attenuation volume were significantly associated with survival at univariate analysis. CT pulmonary fat attenuation volume, normalized by lung volume, resulted as an independent predictor for death.

Keywords: Body composition; Deep learning; Lung diseases (interstitial); Survival analysis; Tomography (x-ray computed).

Fig. 1

Visualization of the body composition analysis feature extraction and index aggregation. The Body and Organ analysis (BOA) network detects the different features within the thoracic computed tomography scan with the exclusion of the limbs. A combination of those raw features is defined as the Sarcopenia, Myosteatosis, Fat, Mediastinal fat, and Pulmonary fat indices. For better comprehensibility, the tissues were coded in color as follows: pink, bone; yellow, muscle; orange, subcutaneous adipose tissue; green, visceral adipose tissue; light blue, mediastinal adipose tissue; purple, epicardial adipose tissue

Fig. 2

Visualization of the CTpfav and lung segmentation. Illustration of the fully automated lung segmentation and the CTpfav coded in colors: light yellow, lung; pink, CTpfav. a Axial CT slice. b Axial CT slice combined with the CTpfav segmentation. c Axial CT slice combined with the lung segmentation. d Three-dimensional illustration of the CTpfav. CT, Computed tomography; CTpfav, CT Pulmonary fat attenuation volume

Fig. 3

Flow chart of the cohort extraction process. Initially, 87 patients were included in the base cohort. After filtering out patients without a thoracic computed tomography scan, with lung transplantation, and missing lung function data, 71 patients remained as the final cohort

Fig. 4

Expression of the BCA indices based on the overall survival of more or less than 5 years. The expression of the BCA-derived imaging indices was studied in two groups: those who survived more or less than 5 years of the CT scan. There were no statistically significant differences between those two groups for the Sarcopenia (a, mean for survival < 5 years, 1.82 versus > 5 years, 1.97), Fat (c, mean for survival < 5 years, 4.47 versus > 5 years, 4.40) and Myosteatosis index (b, mean for survival < 5 years, 15.55 versus > 5 years, 15.26). Patients with a survival of less than 5 years had significantly higher Mediastinal Fat (d, mean for survival < 5 years, 0.22 versus > 5 years, 0.17, p = 0.015) and Pulmonary fat index (e, mean for survival < 5 years, 3.12% versus > 5 years, 2.19%, p = 0.001). The whiskers represent the 10th and 90th percentile. (*p < 0.05; **p < 0.01). BCA, Body composition analysis; CT, Computed tomography

Fig. 5

Kaplan–Meier analysis of the OS of all NSIP patients in dependency on the BCA indices. Illustration of the OS of patients with NSIP using the Kaplan–Meier method within a time range of 60 months based on their body composition concerning the BCA indices. The blue curve represents patients with a low expression of the index, and the red curve stands for patients with a high index. Patients with a higher Sarcopenia index demonstrated significantly higher survival probability compared to those with a lower Sarcopenia index (a, p = 0.023). In contrast, patients with a higher Mediastinal Fat index (d, p = 0.006) and Pulmonary Fat index (e, p = 0.003) showed a significantly lower survival probability. No significant differences were observed for the Fat (b) and Myosteatosis (c) index. BCA, Body composition analysis; NSIP, Non-specific interstitial pneumonia; OS, Overall survival