Academy of Engineering and Technology, Fudan University, Shanghai, China.
Department of Radiology, The Second Affiliated Hospital Zhejiang University School of Medicine, Hangzhou, China.
Med Phys. 2022 Jan;49(1):231-243. doi: 10.1002/mp.15328. Epub 2021 Dec 7.
Pneumothorax is a life-threatening emergency that requires immediate treatment. Frontal-view chest X-ray images are typically used for pneumothorax detection in clinical practice. However, manual review of radiographs is time-consuming, labor-intensive, and highly dependent on the experience of radiologists, which may lead to misdiagnosis. Here, we aim to develop a reliable automatic classification method to assist radiologists in rapidly and accurately diagnosing pneumothorax in frontal chest radiographs.
A novel residual neural network (ResNet)-based two-stage deep-learning strategy is proposed for pneumothorax identification: local feature learning (LFL) followed by global multi-instance learning (GMIL). Most of the nonlesion regions in the images are removed for learning discriminative features. Two datasets are used for large-scale validation: a private dataset (27 955 frontal-view chest X-ray images) and a public dataset (the National Institutes of Health [NIH] ChestX-ray14; 112 120 frontal-view X-ray images). The model performance of the identification was evaluated using the accuracy, precision, recall, specificity, F1-score, receiver operating characteristic (ROC), and area under ROC curve (AUC). Fivefold cross-validation is conducted on the datasets, and then the mean and standard deviation of the above-mentioned metrics are calculated to assess the overall performance of the model.
The experimental results demonstrate that the proposed learning strategy can achieve state-of-the-art performance on the NIH dataset with an accuracy, AUC, precision, recall, specificity, and F1-score of 94.4% ± 0.7%, 97.3% ± 0.5%, 94.2% ± 0.3%, 94.6% ± 1.5%, 94.2% ± 0.4%, and 94.4% ± 0.7%, respectively.
The experimental results demonstrate that our proposed CAD system is an efficient assistive tool in the identification of pneumothorax.
气胸是一种危及生命的紧急情况，需要立即治疗。临床实践中通常使用正位胸片图像来检测气胸。然而，放射影像的人工审查既费时费力，又高度依赖放射科医生的经验，这可能导致误诊。在这里，我们旨在开发一种可靠的自动分类方法，以帮助放射科医生快速准确地诊断正位胸片中的气胸。
提出了一种基于新型残差神经网络（ResNet）的两阶段深度学习策略来进行气胸识别：局部特征学习（LFL） followed by 全局多实例学习（GMIL）。为了学习判别特征，去除了图像中大部分无病变区域。使用两个数据集进行了大规模验证：一个私有数据集（27955 张正位胸片图像）和一个公共数据集（美国国立卫生研究院[NIH]ChestX-ray14；112120 张正位 X 射线图像）。使用准确性、精确性、召回率、特异性、F1 分数、接收器操作特征（ROC）和 ROC 曲线下面积（AUC）评估识别模型的性能。在数据集上进行五折交叉验证，然后计算上述指标的平均值和标准差，以评估模型的整体性能。
实验结果表明，所提出的学习策略在 NIH 数据集上可以达到最先进的性能，准确率、AUC、精确率、召回率、特异性和 F1 分数分别为 94.4% ± 0.7%、97.3% ± 0.5%、94.2% ± 0.3%、94.6% ± 1.5%、94.2% ± 0.4%和 94.4% ± 0.7%。
实验结果表明，我们提出的 CAD 系统是气胸识别的有效辅助工具。
