AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

MRGen: Segmentation Data Engine For Underrepresented MRI Modalities

Haoning Wu, Ziheng Zhao, Ya Zhang, Yanfeng Wang, Weidi Xie

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 5 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 MRGen synthetic target-domain data for trainingnnUNet · Average over 10 cross-modality pairsDSC: 10.48 -> 44.71Improved
add MRGen synthetic data for trainingUMamba · Average over 10 cross-modality pairsDSC: 8.41 -> 43.76Improved
use MRGen instead of CycleGAN translationnnUNet · Average over 10 cross-modality pairsDSC: 26.39 -> 44.71Improved
use MRGen instead of CycleGAN translationMRGen vs baselines · Cross-modality generationFID: 178.18 -> 82.18Improved
fine-tune SDM on MRGen-DB (ablation)SDM · MRGen-DB testFID: 249.24 -> 91.48Improved
add higher latent dimension and BiomedCLIP text encoder (MRGen-M) (ablation)SDM-ft · MRGen-DB testFID: 91.48 -> 41.82Improved
add templated text prompts with attributes, regions and organs (ablation)MRGen-M · MRGen-DB testFID: 41.82 -> 39.63Improved
add templated text prompts (ablation)MRGen-M · MRGen-DB testCLIP-I: 0.7512 -> 0.8457Improved
add AutoFilter sample selection (ablation)MRGen + nnUNet · CHAOS-MRI T1->T2-SPIRDSC: 16.53 -> 22.30Improved
add unannotated target-domain images (ablation)MRGen + nnUNet · CHAOS-MRI T1->T2-SPIRDSC: 16.53 -> 30.16Improved
add both AutoFilter and target-domain images (ablation)MRGen + nnUNet · CHAOS-MRI T1->T2-SPIRDSC: 16.53 -> 66.18Improved
add both AutoFilter and target-domain images (ablation)MRGen + nnUNet · MSD-Prostate ADC->T2DSC: 18.92 -> 61.95Improved

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