When does Bone Suppression and Lung Field Segmentation Improve Chest X-Ray Disease Classification?

TL;DR

This study evaluates how bone suppression and lung field segmentation techniques enhance deep learning-based chest X-ray disease classification, demonstrating improved accuracy especially when combined in an ensemble approach.

Contribution

It introduces the application of bone suppression and lung segmentation as pre-processing steps to improve CNN performance in chest X-ray pathology classification.

Findings

Pre-processing improves ROC AUC for certain pathologies, e.g., mass by 9.95%.

Ensemble models with pre-processing outperform individual models.

Pre-processing techniques are effective for enhancing deep learning diagnostics.

Abstract

Chest radiography is the most common clinical examination type. To improve the quality of patient care and to reduce workload, methods for automatic pathology classification have been developed. In this contribution we investigate the usefulness of two advanced image pre-processing techniques, initially developed for image reading by radiologists, for the performance of Deep Learning methods. First, we use bone suppression, an algorithm to artificially remove the rib cage. Secondly, we employ an automatic lung field detection to crop the image to the lung area. Furthermore, we consider the combination of both in the context of an ensemble approach. In a five-times re-sampling scheme, we use Receiver Operating Characteristic (ROC) statistics to evaluate the effect of the pre-processing approaches. Using a Convolutional Neural Network (CNN), optimized for X-ray analysis, we achieve a good performance with respect to all pathologies on average. Superior results are obtained for selected pathologies when using pre-processing, i.e. for mass the area under the ROC curve increased by 9.95%. The ensemble with pre-processed trained models yields the best overall results.