Despite the success of deep neural networks in chest X-ray (CXR) diagnosis, supervised learning only allows the prediction of disease classes that were seen during training. At inference, these networks cannot predict an unseen disease class. Incorporating a new class requires the collection of labeled data, which is not a trivial task, especially for less frequently-occurring diseases. As a result, it becomes inconceivable to build a model that can diagnose all possible disease classes. Here, we propose a multi-label generalized zero shot learning (CXR-ML-GZSL) network that can simultaneously predict multiple seen and unseen diseases in CXR images. Given an input image, CXR-ML-GZSL learns a visual representation guided by the input's corresponding semantics extracted from a rich medical text corpus. Towards this ambitious goal, we propose to map both visual and semantic modalities to a latent feature space using a novel learning objective. The objective ensures that (i) the most relevant labels for the query image are ranked higher than irrelevant labels, (ii) the network learns a visual representation that is aligned with its semantics in the latent feature space, and (iii) the mapped semantics preserve their original inter-class representation. The network is end-to-end trainable and requires no independent pre-training for the offline feature extractor. Experiments on the NIH Chest X-ray dataset show that our network outperforms two strong baselines in terms of recall, precision, f1 score, and area under the receiver operating characteristic curve. Our code is publicly available at: https://github.com/nyuad-cai/CXR-ML-GZSL.git
翻译:尽管在胸前X射线(CXR)诊断中,深层神经网络成功,但监督学习只能预测培训期间看到的疾病类别。根据推断,这些网络无法预测一个看不见的疾病类别。纳入一个新类别需要收集标签数据,这不是一个微不足道的任务,特别是对于较不常见的疾病。因此,建立能够诊断所有可能的疾病类别的模式变得不可想象。在这里,我们提议建立一个多标签通用的通用零射线学习(CXR-ML-GZSL)网络,它能够同时预测CXR图像中看到的和不见的疾病类别。根据输入图像,CXR-ML-GZSL无法预测一个看不见的疾病类别。根据输入的图像图像,CXR-ML-GZSL学习了一种视觉表达方式。为了这个雄心勃勃勃的目标,我们建议用一个新学习目标将视觉和语系模式的方式绘制到潜伏地空间空间域。目标确保(i)用于查询图像的最相关的标签比不相关标签高,(ii)网络在视觉中学习一个坚固的表示方式,而其原始的直观表示,在正轨的轨道上显示其正轨系统,在Sloeval-real-real-real-real-realmaxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx。需要显示其原始的内,需要显示其原始的内,需要先的内,在原始的缩缩缩缩图图图图图图图图中, 。