Corrigendum to “Improving the performance of lung nodule classification by fusing structured and unstructured data”

•Proposing an idea of fusing structured and unstructured data for classifying lung nodules.•Constructing two novel models fusing structured features and image features learned by 3D CNN.•Explaining how and why the addition of structured features can improve the performance.•Achieving competitive results with a small-scale dataset and without a sophisticated network.•Outperforming several state-of-the-art nodule classification approaches.