Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels

NEUROCOMPUTING

卷:437

Article

Pham, Hieu H.^1,2  Le, Tung T.¹  Tran, Dat Q.¹  Ngo, Dat T.¹  Nguyen, Ha Q.^1,2 

[1] Vingrp Big Data Inst VinBigdata, Dept Med Imaging, Minh Khai St, Hanoi, Vietnam

[2] VinUniversity, Coll Engn & Comp Sci, Vinhomes Ocean Pk, Hanoi, Vietnam

关键词: Chest X-ray;    CheXpert;    Multi-label classification;    Uncertainty label;    Label smoothing;    Label dependency;    Hierarchical learning;   

DOI  :  10.1016/j.neucom.2020.03.127

来源: Elsevier

【 摘 要 】

Chest radiography is one of the most common types of diagnostic radiology exams, which is critical for screening and diagnosis of many different thoracic diseases. Specialized algorithms have been developed to detect several specific pathologies such as lung nodules or lung cancer. However, accurately detecting the presence of multiple diseases from chest X-rays (CXRs) is still a challenging task. This paper presents a supervised multi-label classification framework based on deep convolutional neural networks (CNNs) for predicting the presence of 14 common thoracic diseases and observations. We tackle this problem by training state-of-the-art CNNs that exploit hierarchical dependencies among abnormality labels. We also propose to use the label smoothing technique for a better handling of uncertain samples, which occupy a significant portion of almost every CXR dataset. Our model is trained on over 200,000 CXRs of the recently released CheXpert dataset and achieves a mean area under the curve (AUC) of 0.940 in predicting 5 selected pathologies from the validation set. This is the highest AUC score yet reported to date. The proposed method is also evaluated on the independent test set of the CheXpert competition, which is composed of 500 CXR studies annotated by a panel of 5 experienced radiologists. The performance is on average better than 2.6 out of 3 other individual radiologists with a mean AUC of 0.930, which ranks first on the CheXpert leaderboard at the time of writing this paper. (c) 2021 Elsevier B.V. All rights reserved.

【 授权许可】

Free