Energy-Based Prior Latent Space Diffusion model for Reconstruction of Lumbar Vertebrae from Thick Slice MRI
This addresses the need for faster, radiation-free lumbar spine imaging for treatment planning, though it appears incremental as it builds on existing segmentation and reconstruction pipelines.
The paper tackles the problem of reconstructing high-quality 3D lumbar vertebrae images from thick-slice MRI scans, which have low through-plane resolution, by proposing a latent space diffusion model with an energy-based prior. The method outperforms existing approaches, achieving higher Dice and VS scores while better capturing 3D features.
Lumbar spine problems are ubiquitous, motivating research into targeted imaging for treatment planning and guided interventions. While high resolution and high contrast CT has been the modality of choice, MRI can capture both bone and soft tissue without the ionizing radiation of CT albeit longer acquisition time. The critical trade-off between contrast quality and acquisition time has motivated 'thick slice MRI', which prioritises faster imaging with high in-plane resolution but variable contrast and low through-plane resolution. We investigate a recently developed post-acquisition pipeline which segments vertebrae from thick-slice acquisitions and uses a variational autoencoder to enhance quality after an initial 3D reconstruction. We instead propose a latent space diffusion energy-based prior to leverage diffusion models, which exhibit high-quality image generation. Crucially, we mitigate their high computational cost and low sample efficiency by learning an energy-based latent representation to perform the diffusion processes. Our resulting method outperforms existing approaches across metrics including Dice and VS scores, and more faithfully captures 3D features.