AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Unified Cross-Modal Medical Image Synthesis With Hierarchical Mixture of Product-of-Experts

Reuben Dorent, Nazim Haouchine, Alexandra J. Golby, Sarah F. Frisken, Tina Kapur, William M. Wells

TPAMI 2025 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add hierarchical latent variables (L=2 instead of 1) (ablation)MMHVAE · ReMIND T2 synthesisPSNR: 21.6 -> 22.6Improved
add hierarchical latent variables (L=2 instead of 1) (ablation)MMHVAE · ReMIND FLAIR synthesisPSNR: 19.2 -> 21.1Improved
increase latent variables to L=5 (ablation)MMHVAE · ReMIND T2 and FLAIR synthesisPSNR: 27.8 dB and 26.8 dBImproved
increase latent variables to L=7 (ablation)MMHVAE · ReMIND synthesis (iUS, T2, ceT1, FLAIR)PSNR: 27.0 dB for iUS, 28.6 dB for T2, 29.8 dB for ceT1, 27.4 dB for FLAIRImproved
replace concatenation with zero imputation by probabilistic fusion (ablation)MMHVAE · ReMIND iUS synthesisPSNR: 26.1 -> 27.0Improved
replace concatenation with zero imputation by probabilistic fusion (ablation)MMHVAE · ReMIND FLAIR synthesisLPIPS: 8.7 -> 6.7Improved
replace feature averaging by probabilistic fusion (ablation)MMHVAE · ReMIND T2 synthesisPSNR: 27.0 -> 28.6Improved
replace feature averaging by probabilistic fusion (ablation)MMHVAE · ReMIND T2 synthesisSSIM: 89.0 -> 90.7Improved
add GAN loss (lambda_GAN=0.025) (ablation)MMHVAE · ReMIND iUS synthesisLPIPS: 20.6 -> 14.6Improved
add GAN loss (lambda_GAN=0.025) (ablation)MMHVAE · ReMIND T2 synthesisPSNR: 30.1 -> 28.8Hurt
add GAN loss (lambda_GAN=0.025) (ablation)MMHVAE · ReMIND iUS synthesisSSIM: 81.4 -> 79.7Hurt
MMHVAE instead of ResViTMMHVAE vs ResViT · Computational costMACs / parameters: 13G vs. 274G MACs; 14M vs. 293M parametersImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy