# From Patches to Evidence Balls: Class-Conditioned Evidence Retrieval for Few-Shot Whole Slide Image Classification

arXiv: https://arxiv.org/abs/2608.01104 · HTML: https://mlsanity.com/paper/2608.01104/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks](https://mlsanity.com/paper/2009.11169/) (2020)
- [Multimodal Whole Slide Foundation Model for Pathology](https://mlsanity.com/paper/2411.19666/) (2024)
- [Artificial Intelligence for Digital and Computational Pathology](https://mlsanity.com/paper/2401.06148/) (2023)
- [A graph-transformer for whole slide image classification](https://mlsanity.com/paper/2205.09671/) (2022)
- [Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology](https://mlsanity.com/paper/2402.17228/) (2024)
- [Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides](https://mlsanity.com/paper/2112.02222/) (2021)
- [ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2502.08391/) (2025)
- [Evidence-based diagnostic reasoning with multi-agent copilot for human pathology](https://mlsanity.com/paper/2506.20964/) (2025)
- [Development and Evaluation of a Deep Neural Network for Histologic Classification of Renal Cell Carcinoma on Biopsy and Surgical Resection Slides](https://mlsanity.com/paper/2010.16380/) (2020)
- [FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification](https://mlsanity.com/paper/2411.14743/) (2024)
- [From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification](https://mlsanity.com/paper/2408.09449/) (2024)
- [CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysis](https://mlsanity.com/paper/2602.21637/) (2026)
- [Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling](https://mlsanity.com/paper/2505.17982/) (2025)
- [LLM-Guided Diagnostic Evidence Alignment for Medical Vision-Language Pretraining under Limited Pairing](https://mlsanity.com/paper/2602.07540/) (2026)
- [MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classification](https://mlsanity.com/paper/2602.20873/) (2026)
- [AGE-MIL: Anchor-Guided Evidence Learning for Patient-Level Prediction](https://mlsanity.com/paper/2606.12126/) (2026)

## Abstract (arXiv)

Whole slide image (WSI) classification is an evidence-driven task, where diagnostic cues are often sparse, spatially organized, and class-dependent. Existing MIL and vision-language methods aggregate a large pool of patch features into a single global slide representation. Under few-shot supervision, limited slide-level labels make it difficult to learn a reliable aggregation mechanism that organizes sparse local cues into compact and coherent diagnostic evidence. Moreover, a shared slide representation compresses evidence supporting a candidate class and its alternatives into the same feature, limiting class-specific reasoning and interpretability. To address these issues, we propose EviBall, a class-conditioned evidence retrieval framework for few-shot WSI classification. EviBall organizes local patches into Evidence Balls through semantic-spatial assignment and center refinement, yielding compact and spatially coherent evidence units under weak supervision. It then uses task-specific class queries, including language-guided queries for morphology-oriented tasks and molecular-guided queries for molecular endpoint prediction, to retrieve supporting evidence balls and produce class-conditioned evidence representations for direct class-wise prediction. By introducing structured evidence units and task-relevant semantic guidance, EviBall reduces the reliance on learning an unconstrained global aggregation mechanism from scarce slide-level labels. It therefore reformulates few-shot WSI classification as structured evidence retrieval and competition among candidate classes. Extensive experiments across four morphology-oriented and molecular endpoint WSI tasks demonstrate that EviBall consistently outperforms conventional and vision-language MIL baselines under diverse few-shot settings, while providing spatially localized and class-specific evidence for each prediction.