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

Chest radiography is the most common clinical examination type. To improve the quality of patient care and to reduce workload, methods for automatic pathology classificationhave been developed. In this contribution we investigate theusefulness of two advanced image pre-processing techniques,initially developed for image reading by radiologists, for theperformance of Deep Learning methods. First, we use bonesuppression, 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 Op-erating Characteristic (ROC) statistics to evaluate the effect ofthe pre-processing approaches. Using a Convolutional NeuralNetwork (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.