Synthesis of Late Gadolinium Enhancement Images via Implicit Neural Representations for Cardiac Scar Segmentation
This addresses data scarcity in medical imaging for automated cardiac scar assessment, offering an incremental improvement in segmentation performance.
The paper tackles the problem of limited annotated datasets for cardiac scar segmentation by proposing a framework that synthesizes LGE images and masks using implicit neural representations and diffusion models, resulting in improved fibrosis segmentation with Dice scores increasing from 0.509 to 0.524 when augmenting training data with synthetic volumes.
Late gadolinium enhancement (LGE) imaging is the clinical standard for myocardial scar assessment, but limited annotated datasets hinder the development of automated segmentation methods. We propose a novel framework that synthesises both LGE images and their corresponding segmentation masks using implicit neural representations (INRs) combined with denoising diffusion models. Our approach first trains INRs to capture continuous spatial representations of LGE data and associated myocardium and fibrosis masks. These INRs are then compressed into compact latent embeddings, preserving essential anatomical information. A diffusion model operates on this latent space to generate new representations, which are decoded into synthetic LGE images with anatomically consistent segmentation masks. Experiments on 133 cardiac MRI scans suggest that augmenting training data with 200 synthetic volumes contributes to improved fibrosis segmentation performance, with the Dice score showing an increase from 0.509 to 0.524. Our approach provides an annotation-free method to help mitigate data scarcity.The code for this research is publicly available.