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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add 5 synthetic images per prompt as augmentation | UniPath · Hemorrhage (2-class) | weighted AUC: 75.27 -> 79.03 | Improved |
| add 5 synthetic images per prompt as augmentation | UniPath · Cytology type (4-class) | weighted AUC: 84.05 -> 85.29 | Improved |
| add 5 synthetic images per prompt as augmentation | UniPath · Hemorrhage (2-class) | weighted F1: 74.96 -> 77.02 | Improved |
| add HISTAI 1.03M patches to TCGA 1.62M pretraining data (ablation) | UniPath · Fidelity vs alignment | FID and CLIP-Score | Improved |
| add 50K high-quality fine-tuning stage (ablation) | UniPath · Fidelity vs alignment | FID and CLIP-Score | Improved |
| add HLS stream to RTS-only (ablation) | UniPath MSC · Fidelity vs alignment | alignment | Improved |
| add prototype stream to RTS+HLS (ablation) | UniPath MSC · Fidelity vs alignment | fidelity and alignment | Improved |
| remove RTS stream (HLS+PS only) (ablation) | UniPath MSC · Fidelity vs alignment | alignment | Hurt |
| use UniPath instead of second-best on Patho-FID | UniPath · 10K test set | Patho-FID: 163.44 -> 80.86 | Improved |
| use UniPath instead of Show-o2 | UniPath · 10K test set | CLIP-Score: 0.357 -> 0.348 | Hurt |
| use UniPath instead of Show-o2 | UniPath · Virchow2 FID | FID: 1398.52 -> 484.38 | Improved |
| add UniPath synthetic data to few-shot real data | Kather-CRC-2016 few-shot · Kather-CRC-2016 | F1-weighted | Improved |
Closest papers by meaning
- PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration (ICLR 2025 · similarity 0.88)
- Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology (NeurIPS 2025 · similarity 0.88)
- PathAsst: A Generative Foundation AI Assistant towards Artificial General Intelligence of Pathology (AAAI 2024 · similarity 0.87)
- FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification (CVPR 2025 · similarity 0.87)
- Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner (AAAI 2026 · similarity 0.87)
- PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images? (NeurIPS 2026 · similarity 0.87)
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.
