Function Follows Form: Regression from Complete Thoracic Computed Tomography Scans

TL;DR

This paper introduces a convolutional neural network that predicts emphysema scores and lung function outcomes directly from complete thoracic CT scans, achieving state-of-the-art accuracy without prior domain-specific encoding.

Contribution

The proposed end-to-end CNN method does not rely on prior knowledge and outperforms previous approaches in predicting COPD-related metrics from full CT scans.

Findings

Emphysema scores comparable to expert assessments

COPD diagnosis accuracy with AUC of 0.94

Method generalizes to other scan summarization tasks

Abstract

Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of morbidity and mortality. While COPD diagnosis is based on lung function tests, early stages and progression of different aspects of the disease can be visible and quantitatively assessed on computed tomography (CT) scans. Many studies have been published that quantify imaging biomarkers related to COPD. In this paper we present a convolutional neural network that directly computes visual emphysema scores and predicts the outcome of lung function tests for 195 CT scans from the COPDGene study. Contrary to previous work, the proposed method does not encode any specific prior knowledge about what to quantify, but it is trained end-to-end with a set of 1424 CT scans for which the output parameters were available. The network provided state-of-the-art results for these tasks: Visual emphysema scores are comparable to those assessed by trained human observers; COPD diagnosis from estimated lung function reaches an area under the ROC curve of 0.94, outperforming prior art. The method is easily generalizable to other situations where information from whole scans needs to be summarized in single quantities.