3D conditional generative adversarial network-based synthetic medical image augmentation for lung nodule detection

A computer-aided detection (CADe) scheme, relying on a large number of high-quality images with annotations, could help radiologists effectively detect lung nodules. However, such medical data are generally difficult to obtain. To address this issue, this paper proposes a novel method based on a conditional generative adversarial network (CGAN) to generate new samples for data augmentation (DA). This method employs a 3D CGAN based on a squeeze-and-excitation mechanism and residual learning to synthesize realistic and diverse lung nodules in chest computed tomography (CT) images to improve the performance of the CADe system. To evaluate the proposed method, this paper uses synthetic samples for DA to train the lung nodule detection network. The results indicate that these synthetic samples, which cover a part of the data distribution unfilled by the original data, can boost the overall performance of the nodule detection network at fixed false positive (FP) rates.