Interpreting Chest X-rays via CNNs that Exploit Hierarchical Disease Dependencies and Uncertainty Labels

TL;DR

This paper introduces a CNN-based multi-label classification framework for thoracic diseases in chest X-rays, leveraging label dependencies and uncertainty handling, achieving state-of-the-art accuracy on the CheXpert dataset.

Contribution

The authors develop a novel CNN ensemble that exploits label dependencies and uses label smoothing, setting new performance benchmarks on large-scale CXR datasets.

Findings

Achieved a mean AUC of 0.940 on validation set

Outperformed 2.6 out of 3 radiologists on test set

Set new state-of-the-art results on CheXpert dataset

Abstract

The chest X-rays (CXRs) is one of the views most commonly ordered by radiologists (NHS),which is critical for diagnosis of many different thoracic diseases. Accurately detecting thepresence of multiple diseases from CXRs is still a challenging task. We present a multi-labelclassification framework based on deep convolutional neural networks (CNNs) for diagnos-ing the presence of 14 common thoracic diseases and observations. Specifically, we trained astrong set of CNNs that exploit dependencies among abnormality labels and used the labelsmoothing regularization (LSR) for a better handling of uncertain samples. Our deep net-works were trained on over 200,000 CXRs of the recently released CheXpert dataset (Irvinandal., 2019) and the final model, which was an ensemble of the best performing networks,achieved a mean area under the curve (AUC) of 0.940 in predicting 5 selected pathologiesfrom the validation set. To the best of our knowledge, this is the highest AUC score yetreported to date. More importantly, the proposed method was also evaluated on an inde-pendent test set of the CheXpert competition, containing 500 CXR studies annotated by apanel of 5 experienced radiologists. The reported performance was on average better than2.6 out of 3 other individual radiologists with a mean AUC of 0.930, which had led to thecurrent state-of-the-art performance on the CheXpert test set.