论文标题
通过CNN解释胸部X射线，以利用分层疾病依赖性和不确定性标签
Interpreting Chest X-rays via CNNs that Exploit Hierarchical Disease Dependencies and Uncertainty Labels
论文作者
论文摘要
胸部X射线（CXR）是放射科医生（NHS）最常见的观点之一，这对于诊断许多不同的胸部疾病至关重要。准确地检测来自CXR的多种疾病的存在仍然是一项具有挑战性的任务。我们提出了一个基于深层卷积神经网络（CNN）的多标记级化框架，用于诊断14种常见的胸部疾病和观察结果。具体而言，我们训练了在异常标签之间利用依赖性的CNN集合，并使用了标签平滑的正则化（LSR）来更好地处理不确定的样本。我们对最近发布的CHEXPERT数据集（Irvinandal。，2019年）的20万CXR进行了培训，最终模型是最佳性能网络的合奏，在预测5个选定的PethologiesFrom veryation from验证设置时，在曲线（AUC）下达到了平均面积（AUC）。据我们所知，这是迄今为止迄今为止迄今为止迄今为止迄今为止的最高AUC分数。更重要的是，还对CHEXPERT竞争的原始测试集进行了评估，该方法包含500个经验丰富的放射科医生的Apanel注释的500个CXR研究。报告的性能平均要大于其他3位放射科医生中的2.6，平均AUC为0.930，这导致了CHEXPERT测试集的最新性能。
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.
