Thoracic disease detection from chest radiographs using deep learning methods has been an active area of research in the last decade. Most previous methods attempt to focus on the diseased organs of the image by identifying spatial regions responsible for significant contributions to the model's prediction. In contrast, expert radiologists first locate the prominent anatomical structures before determining if those regions are anomalous. Therefore, integrating anatomical knowledge within deep learning models could bring substantial improvement in automatic disease classification. Motivated by this, we propose Anatomy-XNet, an anatomy-aware attention-based thoracic disease classification network that prioritizes the spatial features guided by the pre-identified anatomy regions. We adopt a semi-supervised learning method by utilizing available small-scale organ-level annotations to locate the anatomy regions in large-scale datasets where the organ-level annotations are absent. The proposed Anatomy-XNet uses the pre-trained DenseNet-121 as the backbone network with two corresponding structured modules, the Anatomy Aware Attention (A$^3$) and Probabilistic Weighted Average Pooling (PWAP), in a cohesive framework for anatomical attention learning. We experimentally show that our proposed method sets a new state-of-the-art benchmark by achieving an AUC score of 85.78%, 92.07%, and, 84.04% on three publicly available large-scale CXR datasets--NIH, Stanford CheXpert, and MIMIC-CXR, respectively. This not only proves the efficacy of utilizing the anatomy segmentation knowledge to improve the thoracic disease classification but also demonstrates the generalizability of the proposed framework.
翻译:在过去十年中,利用深层学习方法从胸腔射线仪中检测血清疾病一直是研究的一个积极领域。以往方法大多试图通过确定对模型预测做出重要贡献的空间区域,重点研究图像中的疾病器官。相比之下,专家放射学家在确定这些区域是否异常之前,先将显要的解剖结构定位在明显的解剖结构中。因此,将解剖学知识纳入深层学习模型可以大大改进自动疾病分类。为此,我们提议Anatomy-XNet(一个基于解剖-觉悟的心电图性疾病分类网络),在预先确定的解剖区域指导下,将空间功能作为优先事项。我们采用了一种半监督的学习方法,利用现有的小规模解剖结构图解结构结构将这些区域定位在缺乏器官水平总体说明的大型数据集中。提议Anatomical-XNet(一个经过预先训练的DensenseNet-121)作为主干网,有两个相应的结构模块,即解剖-认知性注意(A+3美元),以及预测-直径-直径-直径-直径-直径-直径-直径-直径-直径-直径C-直径-直径-直径-直径-直径-直径-直径-直径-直径-直径-直径-直径-直径-直-直-直径-直径-直径-直-直径-直径-直径-直径-直径-直-直-直径-轴-直-直径-直径-直-直-直-X-直径-直径-直径-直径-直径-直径-直径-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直径-直径-直径-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直径-直-直-直-直-直-直-直-直-直-直-直-直-直-直-直