Research map / Label-efficient and robust learning / Domain adaptation and generalization
Semantic-Anchored Evidential Fusion for Domain-Robust Whole-Slide Survival Analysis
YUCHENG XING, Ling Huang, Pei Liu, Jingying Ma, Jiaxing Xu, Kai He, Mengling Feng
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 text-guided visual stream to WSI-only branch (ablation) | SAEFS · Avg 4 external cohorts | C-index: 0.5980 -> 0.6840 | Improved |
| Add global WSI branch to text-guided stream (ablation) | SAEFS · Avg 4 external cohorts | C-index: 0.6408 -> 0.6840 | Improved |
| Add visual evidence to text-only semantic features (ablation) | SAEFS · Avg 4 external cohorts | C-index: 0.5327 -> 0.6840 | Improved |
| Use evidential cautious fusion instead of concatenation (ablation) | SAEFS · Avg 4 external cohorts | C-index: 0.5310 -> 0.6840 | Improved |
| Use evidential cautious fusion instead of concatenation (ablation) | SAEFS · Avg 4 external cohorts | IBS: 0.2119 -> 0.3031 | Hurt |
| Use cautious conjunction rule instead of Dempster rule (ablation) | SAEFS · Avg 4 external cohorts | C-index: 0.5758 -> 0.6840 | Improved |
| Use meaningful VQA semantic anchors instead of random text (ablation) | SAEFS · CPTAC-UCEC | C-index: 0.504 -> 0.682 | Improved |
| Concatenate VQA features to unimodal OTSurv (ablation) | OTSurv · CPTAC-UCEC | C-index | No clear effect |
| Swap ALPaCA for SlideChat as VQA model (ablation) | SAEFS · CPTAC-UCEC | C-index: 0.682 -> 0.678 | No clear effect |
| Increase number of template questions (ablation) | SAEFS · CPTAC-UCEC | C-index: 0.633 (Q=4) -> 0.660 (Q=8) -> 0.682 (Q=12) | Improved |
| Use VQA semantic features instead of raw WSI features | feature space · TCGA vs external cohorts | MMD: 0.1988 -> 0.0532 | Improved |
| Text-guided aggregation of WSI features | WSI features · TCGA vs external cohorts | MMD: 0.1988 -> 0.2004 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TransMIL — TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification (NeurIPS 2021) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology (ICLR 2025 · similarity 0.88)
- MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding (CVPR 2026 · similarity 0.87)
- FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification (CVPR 2025 · similarity 0.87)
- Multimodal Prototyping for cancer survival prediction (ICML 2024 · similarity 0.86)
- Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction (CVPR 2024 · similarity 0.86)
- TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis (ICLR 2026 · similarity 0.86)
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.
