AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Beyond Pixel Simulation: Pathology Image Generation via Diagnostic Semantic Tokens and Prototype Control

Minghao Han, Yichen Liu, Yizhou Liu, Zizhi Chen, Jingqun Tang, Xuecheng Wu, Dingkang Yang, Lihua Zhang

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 3 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 5 synthetic images per prompt as augmentationUniPath · Hemorrhage (2-class)weighted AUC: 75.27 -> 79.03Improved
add 5 synthetic images per prompt as augmentationUniPath · Cytology type (4-class)weighted AUC: 84.05 -> 85.29Improved
add 5 synthetic images per prompt as augmentationUniPath · Hemorrhage (2-class)weighted F1: 74.96 -> 77.02Improved
add HISTAI 1.03M patches to TCGA 1.62M pretraining data (ablation)UniPath · Fidelity vs alignmentFID and CLIP-ScoreImproved
add 50K high-quality fine-tuning stage (ablation)UniPath · Fidelity vs alignmentFID and CLIP-ScoreImproved
add HLS stream to RTS-only (ablation)UniPath MSC · Fidelity vs alignmentalignmentImproved
add prototype stream to RTS+HLS (ablation)UniPath MSC · Fidelity vs alignmentfidelity and alignmentImproved
remove RTS stream (HLS+PS only) (ablation)UniPath MSC · Fidelity vs alignmentalignmentHurt
use UniPath instead of second-best on Patho-FIDUniPath · 10K test setPatho-FID: 163.44 -> 80.86Improved
use UniPath instead of Show-o2UniPath · 10K test setCLIP-Score: 0.357 -> 0.348Hurt
use UniPath instead of Show-o2UniPath · Virchow2 FIDFID: 1398.52 -> 484.38Improved
add UniPath synthetic data to few-shot real dataKather-CRC-2016 few-shot · Kather-CRC-2016F1-weightedImproved

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