Chakravarty Arunava, Sarkar Tandra, Ghosh Nirmalya, Sethuraman Ramanathan, Sheet Debdoot
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:1234-1237. doi: 10.1109/EMBC44109.2020.9176693.
Chest radiographs are primarily employed for the screening of cardio, thoracic and pulmonary conditions. Machine learning based automated solutions are being developed to reduce the burden of routine screening on Radiologists, allowing them to focus on critical cases. While recent efforts demonstrate the use of ensemble of deep convolutional neural networks (CNN), they do not take disease comorbidity into consideration, thus lowering their screening performance. To address this issue, we propose a Graph Neural Network (GNN) based solution to obtain ensemble predictions which models the dependencies between different diseases. A comprehensive evaluation of the proposed method demonstrated its potential by improving the performance over standard ensembling technique across a wide range of ensemble constructions. The best performance was achieved using the GNN ensemble of DenseNet121 with an average AUC of 0.821 across thirteen disease comorbidities.
胸部X光片主要用于筛查心脏、胸部和肺部疾病。基于机器学习的自动化解决方案正在开发中，以减轻放射科医生常规筛查的负担，使他们能够专注于危急病例。虽然最近的研究表明可以使用深度卷积神经网络（CNN）的集成，但它们没有考虑疾病共病情况，从而降低了筛查性能。为了解决这个问题，我们提出了一种基于图神经网络（GNN）的解决方案，以获得对不同疾病之间的依赖性进行建模的集成预测。对所提出方法的全面评估表明，通过在广泛的集成结构中比标准集成技术提高性能，该方法具有潜力。使用DenseNet121的GNN集成实现了最佳性能，在13种疾病共病情况下的平均AUC为0.821。
