English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Cross-modality medical image synthesis is a critical topic and has thepotential to facilitate numerous applications in the medical imaging field.Despite recent successes in deep-learning-based generative models, most currentmedical image synthesis methods rely on generative adversarial networks andsuffer from notorious mode collapse and unstable training. Moreover, the 2Dbackbone-driven approaches would easily result in volumetric inconsistency,while 3D backbones are challenging and impractical due to the tremendous memorycost and training difficulty. In this paper, we introduce a new paradigm forvolumetric medical data synthesis by leveraging 2D backbones and present adiffusion-based framework, Make-A-Volume, for cross-modality 3D medical imagesynthesis. To learn the cross-modality slice-wise mapping, we employ a latentdiffusion model and learn a low-dimensional latent space, resulting in highcomputational efficiency. To enable the 3D image synthesis and mitigatevolumetric inconsistency, we further insert a series of volumetric layers inthe 2D slice-mapping model and fine-tune them with paired 3D data. Thisparadigm extends the 2D image diffusion model to a volumetric version with aslightly increasing number of parameters and computation, offering a principledsolution for generic cross-modality 3D medical image synthesis. We showcase theeffectiveness of our Make-A-Volume framework on an in-house SWI-MRA brain MRIdataset and a public T1-T2 brain MRI dataset. Experimental results demonstratethat our framework achieves superior synthesis results with volumetricconsistency.

Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis