Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study

TL;DR

This study introduces an unsupervised learning approach to identify and interpret radiological emphysema subtypes from CT scans, enabling more detailed and automated lung tissue analysis without relying on labeled data.

Contribution

It demonstrates that unsupervised texture prototypes can accurately classify emphysema subtypes and facilitate automated lung labeling, advancing radiological analysis methods.

Findings

Texture prototypes are visually homogeneous and distinct.

Prototypes are reproducible across subjects.

Accurate prediction of emphysema subtypes.

Abstract

Pulmonary emphysema is traditionally subcategorized into three subtypes, which have distinct radiological appearances on computed tomography (CT) and can help with the diagnosis of chronic obstructive pulmonary disease (COPD). Automated texture-based quantification of emphysema subtypes has been successfully implemented via supervised learning of these three emphysema subtypes. In this work, we demonstrate that unsupervised learning on a large heterogeneous database of CT scans can generate texture prototypes that are visually homogeneous and distinct, reproducible across subjects, and capable of predicting accurately the three standard radiological subtypes. These texture prototypes enable automated labeling of lung volumes, and open the way to new interpretations of lung CT scans with finer subtyping of emphysema.