Proto-Gaussian: MRI Modality Translation Based on Learnable Structural Prototypes and 2D Gaussian Splatting

Medical image modality translation is hindered by the entan-glement of geometry and modality-specific textures, often causing struc-tural distortions. Existing methods operate at the pixel or feature level,failing to separate geometry from appearance and yielding anatomicallyinconsistent results. We present Proto-Gaussian, a novel MRI modalitytranslation framework that explicitly disentangles structural geometryfrom modality-specific appearance using 2D Gaussian image representa-tion, surpassing conventional pixel or patch-based approaches in preserv-ing anatomical consistency. The framework operates in two stages: first, ashared Gaussian Bank captures modality-invariant geometric prototypesthrough 2D Gaussian primitives and self-supervised learning; second, aLabel-Adaptive Token Refinement module maps texture features acrossmodalities while leveraging the learned geometric structures, achievingclear structure-texture separation. Finally, a fully differentiable 2D Gaus-sian splatting renderer synthesizes high-fidelity target-modality images,maintaining both structural accuracy and visual realism. Extensive ex-periments on brain MRI datasets demonstrate the superiority of ourmethod through quantitative and qualitative comparisons with state-of-the-art approaches.