Research map / Detection and segmentation / CNN features
Histocomponent-driven Universal Model for Virtual Immunohistochemistry Multiplex Staining via Joint Manifold Evolution
Jiajun Cen, Siyuan Xu, Lili Gao, Yan Wang
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 Joint Manifold Anchoring (H&E concatenated as scaffold) (ablation) | HUSE · Orion-CRC (AVG over 16 markers) | SSIM: 0.449 -> 0.818 | Improved |
| add Joint Manifold Anchoring (ablation) | HUSE · Orion-CRC (AVG over 16 markers) | KID: 90.58 -> 23.33 | Improved |
| add Hi-MoE on top of JMA (ablation) | HUSE · Orion-CRC (AVG over 16 markers) | PSNR: +1.01dB PSNR | Improved |
| add RCG gating (ablation) | HUSE · Orion-CRC (AVG over 16 markers) | KID: -42.59 KID | Improved |
| add full HUSE modules on MIST (ablation) | HUSE · MIST (AVG over 4 markers) | KID: 165.63 -> 54.78 | Improved |
| learnable instead of random expert prototypes (ablation) | Hi-MoE · Orion-CRC (AVG over 16 markers) | PSNR: 20.69 -> 22.81 | Improved |
| learnable instead of random expert prototypes (ablation) | Hi-MoE · MIST (AVG over 4 markers) | KID: 155.78 -> 54.78 | Improved |
| learnable instead of frozen prototypes (ablation) | Hi-MoE · Orion-CRC (AVG over 16 markers) | PSNR: 21.70 -> 22.81 | Improved |
| sigmoid instead of identity activation in RCG (ablation) | RCG · Orion-CRC (AVG over 16 markers) | KID: 32.84 -> 19.33 | Improved |
| sigmoid instead of tanh activation in RCG (ablation) | RCG · MIST (AVG over 4 markers) | KID: 71.81 -> 54.78 | Improved |
| HUSE universal model vs best universal baseline PDUnist | HUSE · Orion-CRC (AVG over 16 markers) | PSNR: 22.28 -> 22.81 | Improved |
| HUSE single universal network vs single-marker models | HUSE · Orion-CRC (AVG over 16 markers) | SSIM: -0.037 | Mixed |
Closest papers by meaning
- OT-StainNet: Optimal Transport Driven Semantic Matching for Weakly Paired H&E-to-IHC Stain Transfer (AAAI 2025 · similarity 0.90)
- SheafStain: Sheaf-Theoretic Schr\"odinger Bridge for Spatially and Biologically Coherent Virtual Staining (NeurIPS 2026 · similarity 0.89)
- ODA-GAN: Orthogonal Decoupling Alignment GAN Assisted by Weakly-supervised Learning for Virtual Immunohistochemistry Staining (CVPR 2025 · similarity 0.88)
- BioX-CPath: Biologically-driven Explainable Diagnostics for Multistain IHC Computational Pathology (CVPR 2025 · similarity 0.86)
- Virtual Immunohistochemistry Staining for Histological Images Assisted by Weakly-supervised Learning (CVPR 2024 · similarity 0.86)
- Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation (CVPR 2025 · similarity 0.85)
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.
