Research map / Image generation / Image restoration
Content-aware Information Compression and Selection for Whole Slide Image Analysis
Tingting Zheng, Hongxun Yao, Sicheng Zhao, Yi Xiao
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 CICS plug-in | MambaMIL · TCGA-ESCA | accuracy: 0.821 -> 0.898 | Improved |
| add CICS plug-in | TransMIL · TCGA-BRCA survival | C-index: 0.618 -> 0.669 | Improved |
| add CICS plug-in | ILRA · TCGA-BRCA | AUC: 0.886 -> 0.879 | Hurt |
| add CICS plug-in | MambaMIL · TCGA-BRCA | accuracy: 0.868 -> 0.872 | No clear effect |
| add CICS plug-in | TransMIL · BRACS (ResNet18) | accuracy: 0.706 -> 0.717 | Improved |
| add CICS plug-in | MeanMIL · TCGA-BLCA survival | C-index: 0.592 -> 0.595 | No clear effect |
| add proximity attention (PSA) alongside global attention (ablation) | ABMIL+CICS · BRACS | accuracy: 0.691 -> 0.728 | Improved |
| add global-memory attention only (GSA) (ablation) | ABMIL+CICS · BRACS | AUC: 0.816 -> 0.804 | Hurt |
| add Lcac loss (ablation) | ABMIL+CICS · TCGA-ESCA | F1: 0.870 -> 0.885 | Improved |
| compress with content-aware CAC instead of random masking (ablation) | ABMIL+CICS · TCGA-ESCA | accuracy: 0.801 -> 0.859 | Improved |
| compress with content-aware CAC instead of top-K (ablation) | ABMIL+CICS · TCGA-ESCA | accuracy: 0.821 -> 0.859 | Improved |
| enlarge global memory M from 2 to 5 with Z=4x4 (ablation) | ABMIL+CICS · TCGA-ESCA | accuracy: 0.802 -> 0.872 | Improved |
Closest papers by meaning
- Boosting Multiple Instance Learning Models for Whole Slide Image Classification: A Model-Agnostic Framework Based on Counterfactual Inference (AAAI 2024 · similarity 0.88)
- Advancing Multiple Instance Learning with Continual Learning for Whole Slide Imaging (CVPR 2025 · similarity 0.86)
- M3amba: Memory Mamba is All You Need for Whole Slide Image Classification (CVPR 2025 · similarity 0.86)
- Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification (CVPR 2024 · similarity 0.86)
- CaMIL: Causal Multiple Instance Learning for Whole Slide Image Classification (AAAI 2024 · similarity 0.86)
- Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification (AAAI 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.
