Decoupling Shape and Density for Liver Lesion Synthesis Using Conditional Generative Adversarial Networks
This work addresses a domain-specific issue for medical imaging researchers and practitioners by providing an incremental improvement in lesion synthesis for data augmentation and segmentation tasks.
The paper tackles the problem of limited quality and diversity in liver lesion synthesis by introducing a method to decouple shape and density using conditional generative adversarial networks, resulting in improved lesion segmentation performance when density information is embedded in the generator model.
Lesion synthesis received much attention with the rise of efficient generative models for augmenting training data, drawing lesion evolution scenarios, or aiding expert training. The quality and diversity of synthesized data are highly dependent on the annotated data used to train the models, which not rarely struggle to derive very different yet realistic samples from the training ones. That adds an inherent bias to lesion segmentation algorithms and limits synthesizing lesion evolution scenarios efficiently. This paper presents a method for decoupling shape and density for liver lesion synthesis, creating a framework that allows straight-forwardly driving the synthesis. We offer qualitative results that show the synthesis control by modifying shape and density individually, and quantitative results that demonstrate that embedding the density information in the generator model helps to increase lesion segmentation performance compared to using the shape solely.