Research map / Vision-language and multimodal / CLIP and zero-shot
Pathology-knowledge Enhanced Multi-instance Prompt Learning for Few-shot Whole Slide Image Classification
Linhao Qu, Dingkang Yang, Dan Huang, Qinhao Guo, rongkui luo, Shaoting Zhang, Xiaosong 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 visual and textual pathology examples to prompts (PEMP vs CoOp) (ablation) | PEMP · Survival prognosis, in-house (2-shot) | C-index: 0.490 -> 0.562 | Improved |
| add Summary (attention-pooling) layer instead of average pooling (ablation) | PEMP · Survival prognosis, in-house (32-shot) | C-index: 0.632 -> 0.667 | Improved |
| add Messenger self-attention layer (ablation) | PEMP · Survival prognosis, in-house (32-shot) | C-index: 0.664 -> 0.667 | Improved |
| add Messenger self-attention layer (ablation) | PEMP · Survival prognosis, in-house (2-shot) | C-index: 0.554 -> 0.562 | Improved |
| add text examples alongside vision examples (ablation) | PEMP · Survival prognosis, in-house (2-shot) | C-index: 0.527 -> 0.562 | Improved |
| add vision examples alongside text examples (ablation) | PEMP · Survival prognosis, in-house (2-shot) | C-index: 0.511 -> 0.562 | Improved |
| add slide-level prompts (ablation) | PEMP · Survival prognosis, in-house (2-shot) | C-index: 0.525 -> 0.562 | Improved |
| add alignment contrastive loss on example features (ablation) | PEMP · Survival prognosis, in-house (2-shot) | C-index: 0.549 -> 0.562 | Improved |
| PEMP versus TOP (text-only prior prompts) in few-shot round cell diagnosis | PEMP · Round cell subtype, in-house | AUC: 0.682 -> 0.751 (32-shot) | Improved |
| PEMP versus TOP on lymph node metastasis | PEMP · Lymph node metastasis, TCGA-CESC | AUC: 0.799 -> 0.818 (32-shot) | Improved |
Closest papers by meaning
- FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification (CVPR 2025 · similarity 0.92)
- MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image Classification (NeurIPS 2025 · similarity 0.90)
- PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization (NeurIPS 2025 · similarity 0.90)
- CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology (CVPR 2025 · similarity 0.89)
- SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding (CVPR 2025 · similarity 0.88)
- ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification (CVPR 2024 · 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.
