Classification of Interstitial Lung Abnormality Patterns with an Ensemble of Deep Convolutional Neural Networks

David Bermejo-Peláez,Samuel Y Ash,George R Washko,María J Ledesma-Carbayo,Raúl San José Estépar

doi:10.1038/s41598-019-56989-5

Abstract

Subtle interstitial changes in the lung parenchyma of smokers, known as Interstitial Lung Abnormalities (ILA), have been associated with clinical outcomes, including mortality, even in the absence of Interstitial Lung Disease (ILD). Although several methods have been proposed for the automatic identification of more advanced Interstitial Lung Disease (ILD) patterns, few have tackled ILA, which likely precedes the development ILD in some cases. In this context, we propose a novel methodology for automated identification and classification of ILA patterns in computed tomography (CT) images. The proposed method is an ensemble of deep convolutional neural networks (CNNs) that detect more discriminative features by incorporating two, two-and-a-half and three- dimensional architectures, thereby enabling more accurate classification. This technique is implemented by first training each individual CNN, and then combining its output responses to form the overall ensemble output. To train and test the system we used 37424 radiographic tissue samples corresponding to eight different parenchymal feature classes from 208 CT scans. The resulting ensemble performance including an average sensitivity of 91,41% and average specificity of 98,18% suggests it is potentially a viable method to identify radiographic patterns that precede the development of ILD.

Highlights

Interstitial Lung Diseases (ILD) are a heterogeneous group of more than 200 lung disorders that largely affect the lung parenchyma but which may present airway or vascular manifestations as well
In this work we propose the first deep learning-based method to identify and classify radiographic patterns of Interstitial Lung Abnormalities (ILA), which likely represents early or subtle ILD in some cases, that implies the characterization of 8 different parenchymal features types
Of the two available images per scan, the dataset was built with Regions of Interest (ROIs) extracted from the computed tomography (CT) images reconstructed with the B50 filter

Summary

Introduction

Interstitial Lung Diseases (ILD) are a heterogeneous group of more than 200 lung disorders that largely affect the lung parenchyma but which may present airway or vascular manifestations as well. There is a growing acceptance that some forms of ILD, especially idiopathic pulmonary fibrosis (IPF) may be preceded by early or subtle radiographic findings seen on computed tomography (CT) scans of the chest[1,2]. The visual presence of these findings, often termed interstitial lung abnormalities (ILA) has been shown to be associated with reduced lung volume, increased mortality and a genetic polymorphism that is associated with IPF3–7.

Methods

Results

Conclusion