# Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols

arXiv: https://arxiv.org/abs/2608.30420 · HTML: https://mlsanity.com/paper/2608.30420/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Quilt-1M: One Million Image-Text Pairs for Histopathology](https://mlsanity.com/paper/2306.11207/) (2023)
- [Reviving Iterative Training with Mask Guidance for Interactive Segmentation](https://mlsanity.com/paper/2102.06583/) (2021)
- [Deep Interactive Object Selection](https://mlsanity.com/paper/1603.04042/) (2016)
- [BACH: Grand Challenge on Breast Cancer Histology Images](https://mlsanity.com/paper/1808.04277/) (2018)
- [SimpleClick: Interactive Image Segmentation with Simple Vision Transformers](https://mlsanity.com/paper/2210.11006/) (2022)
- [Low-Rank Few-Shot Adaptation of Vision-Language Models](https://mlsanity.com/paper/2405.18541/) (2024)
- [Iteratively Trained Interactive Segmentation](https://mlsanity.com/paper/1805.04398/) (2018)
- [Boosting Vision-Language Models with Transduction](https://mlsanity.com/paper/2406.01837/) (2024)
- [Transductive Zero-Shot and Few-Shot CLIP](https://mlsanity.com/paper/2405.18437/) (2024)
- [Label Propagation for Zero-shot Classification with Vision-Language Models](https://mlsanity.com/paper/2404.04072/) (2024)
- [Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2311.13964/) (2023)
- [Iterative annotation to ease neural network training: Specialized machine learning in medical image analysis](https://mlsanity.com/paper/1812.07509/) (2018)
- [Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset](https://mlsanity.com/paper/2201.11446/) (2022)
- [Benchmarking Pathology Foundation Models: Adaptation Strategies and Scenarios](https://mlsanity.com/paper/2410.16038/) (2024)
- [Weakly supervised segmentation with point annotations for histopathology images via contrast-based variational model](https://mlsanity.com/paper/2304.03572/) (2023)
- [Boosting Vision-Language Models for Histopathology Classification: Predict all at once](https://mlsanity.com/paper/2409.01883/) (2024)
- [Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model](https://mlsanity.com/paper/2412.18303/) (2024)
- [A transductive few-shot learning approach for classification of digital histopathological slides from liver cancer](https://mlsanity.com/paper/2311.17740/) (2023)
- [From Few to More: Scribble-based Medical Image Segmentation via Masked Context Modeling and Continuous Pseudo Labels](https://mlsanity.com/paper/2408.12814/) (2024)
- [Conditional Random Fields for Interactive Refinement of Histopathological Predictions](https://mlsanity.com/paper/2601.12082/) (2026)
- [Prompt learning with bounding box constraints for medical image segmentation](https://mlsanity.com/paper/2507.02743/) (2025)
- [VISTA-PATH: An interactive foundation model for pathology image segmentation and quantitative analysis in computational pathology](https://mlsanity.com/paper/2601.16451/) (2026)
- [Scribble-based fast weak-supervision and interactive corrections for segmenting whole slide images](https://mlsanity.com/paper/2402.08333/) (2024)
- [Revisiting 3D Medical Scribble Supervision: Benchmarking Beyond Cardiac Segmentation](https://mlsanity.com/paper/2403.12834/) (2024)

## Built on by (most cited first, 2 of 2)

- [Refining Cytology Predictions with Conditional Random Fields](https://mlsanity.com/paper/2609.31028/) (2026)
- [Exploiting Spatial Structure for Transductive Few-Shot Classification of Whole-Slide Images](https://mlsanity.com/paper/2609.31040/) (2026)

## Abstract (arXiv)

Automating the analysis of whole-slide images has high clinical value, since characterizing cancers requires examining them in detail. Such analysis increasingly relies on vision-language models that provide patch-level zero-shot predictions. However, these predictions remain noisy and must be refined with a few annotations. A promising paradigm for this refinement is few-shot transduction. Rather than treating each patch independently, these methods leverage the relations between patches, together with a few annotations, to refine all predictions jointly. However, current transductive methods are evaluated under conditions that overlook key properties of whole-slide images: (i) datasets consist of independent patches extracted from multiple slides, ignoring the complex tissue organization; (ii) datasets are mostly balanced, whereas a single whole-slide image exhibits severe class imbalance, with several classes absent; and (iii) annotations are sampled at random, without reflecting how a pathologist annotates a limited number of regions. To align the transduction paradigm to realistic whole-slide settings, we introduce the following contributions. First, we propose SlideCRF, which adapts conditional random fields for whole-slide images by combining spatial and biological cues while accounting for classes that may be absent from a given slide. Second, we provide a set of realistic annotation protocols, based on spatially localized clicks and scribbles, modeling different pathologist interactions, such as the iterative correction of model errors. Across four datasets, we show that SlideCRF outperforms current transductive methods in macro F1, improving over the zero-shot predictions by +24.2% and +37.5% with one and 16 clicks per present class, respectively.