mlsanityData to 14 Oct 2026

Semantic-Anchored Evidential Fusion for Domain-Robust Whole-Slide Survival Analysis

arXiv 2606.19966 ↗First posted 18 Jun 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Whole-slide images (WSIs) are widely used for computational cancer prognosis. However, most existing methods primarily focus on in-domain performance and fail to generalize across clinical centers. This limitation stems from their reliance on pixel-derived representations that are highly susceptible to domain-specific artifacts caused by staining protocols and scanner hardware. We hypothesize that high-level pathology semantics, such as tumor grade and micro-environmental architecture, provide a domain-invariant semantic representation that mirrors the robust diagnostic logic of human pathologists. Therefore, we propose a Semantic-Anchored Evidential Fusion Survival (SAEFS) framework, where SAEFS derives semantic anchors from WSIs via Visual Question Answering (VQA), employs a dual-stream WSI evidence extraction architecture, uses Dirichlet-based Subjective Logic to model uncertainty, and fuses semantic and visual evidence through a cautious conjunction rule to avoid overconfident fusion from correlated sources. Trained exclusively on one source domain and evaluated zero-shot across four unseen domains, SAEFS consistently outperforms state-of-the-art models both in prediction accuracy and reliability, improving the average C-index by 10.2%. Quantitative analyses further show that VQA-derived semantic features exhibit significantly lower cross-center divergence than pixel-derived features, highlighting their robustness for cross-center clinical applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 64 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

33 of 64 references.

References · 33

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  6. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  7. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  8. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
  9. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  10. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
  11. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  12. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
21 more
  1. 2023Quilt-1M: One Million Image-Text Pairs for Histopathologycited by 194
  2. 2021Generalized Source-free Domain Adaptationcited by 175
  3. 2019Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathologycited by 173
  4. 2022Trusted Multi-View Classification with Dynamic Evidential Fusioncited by 168
  5. 2023Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Imagescited by 134
  6. 2023Artificial Intelligence for Digital and Computational Pathologycited by 108
  7. 2023Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Predictioncited by 92
  8. 2023Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Predictioncited by 86
  9. 2023Attention-Challenging Multiple Instance Learning for Whole Slide Image Classificationcited by 61
  10. 2024SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understandingcited by 57
  11. 2023A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methodscited by 39
  12. 2025Current Pathology Foundation Models are unrobust to Medical Center Differencescited by 39
  13. 2024Graph Domain Adaptation with Dual-branch Encoder and Two-level Alignment for Whole Slide Image-based Survival Predictioncited by 20
  14. 2025OTSurv: A Novel Multiple Instance Learning Framework for Survival Prediction with Heterogeneity-aware Optimal Transportcited by 8
  15. 2024Evidential time-to-event prediction with calibrated uncertainty quantificationcited by 7
  16. 2025HASD: Hierarchical Adaption for pathology Slide-level Domain-shiftcited by 6
  17. 2025DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Predictioncited by 6
  18. 2024An evidential time-to-event prediction model based on Gaussian random fuzzy numberscited by 5
  19. 2025PS3: A Multimodal Transformer Integrating Pathology Reports with Histology Images and Biological Pathways for Cancer Survival Predictioncited by 3
  20. 2026Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosiscited by 2
  21. 2026Bridging the Modality Bottleneck in Pathology MIL through Virtual Molecular Stainingcited by 2

Built on by

Not cited yet.