Tunable CT Lung Nodule Synthesis Conditioned on Background Image and Semantic Features.

Synthetic CT image with artificially generated lung nodules has been shown to be useful as an augmentation method for certain tasks such as lung segmentation and nodule classification. Most conventional methods are designed as "inpainting" tasks by removing a region from background image and synthesizing the foreground nodule. To ensure natural blending with the background, existing method proposed loss function and separate shape/appearance generation. However, spatial discontinuity is still unavoidable for certain cases. Meanwhile, there is often little control over semantic features regarding the nodule characteristics, which may limit their capability of fine-grained augmentation in balancing the original data. In this work, we address these two challenges by developing a 3D multi-conditional generative adversarial network (GAN) that is conditioned on both background image and semantic features for lung nodule synthesis on CT image. Instead of removing part of the input image, we use a fusion block to blend object and background, ensuring more realistic appearance. Multiple discriminator scenarios are considered, and three outputs of image, segmentation, and feature are used to guide the synthesis process towards semantic feature control. We trained our method on public dataset, and showed promising results as a solution for tunable lung nodule synthesis.