Explicit Temporal Embedding in Deep Generative Latent Models for Longitudinal Medical Image Synthesis
This addresses the challenge of acquiring large medical datasets for deep learning by enabling synthetic longitudinal image generation, though it is incremental as it builds on existing latent space-based editing methods.
The paper tackles the problem of synthesizing longitudinal volumetric medical images by proposing a novel joint learning scheme that explicitly embeds temporal dependencies in GAN latent spaces, enabling continuous, smooth, and high-quality synthesis with limited supervision across three datasets including tumor regression.
Medical imaging plays a vital role in modern diagnostics and treatment. The temporal nature of disease or treatment progression often results in longitudinal data. Due to the cost and potential harm, acquiring large medical datasets necessary for deep learning can be difficult. Medical image synthesis could help mitigate this problem. However, until now, the availability of GANs capable of synthesizing longitudinal volumetric data has been limited. To address this, we use the recent advances in latent space-based image editing to propose a novel joint learning scheme to explicitly embed temporal dependencies in the latent space of GANs. This, in contrast to previous methods, allows us to synthesize continuous, smooth, and high-quality longitudinal volumetric data with limited supervision. We show the effectiveness of our approach on three datasets containing different longitudinal dependencies. Namely, modeling a simple image transformation, breathing motion, and tumor regression, all while showing minimal disentanglement. The implementation is made available online at https://github.com/julschoen/Temp-GAN.