mlsanityData to 7 Oct 2026

Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology

arXiv 2405.11643 ↗First posted 19 May 2024cs.CV cs.LG stat.APcited by 70

Not on the map. Why?

Abstract (arXiv)

Representation learning of pathology whole-slide images (WSIs) has been has primarily relied on weak supervision with Multiple Instance Learning (MIL). However, the slide representations resulting from this approach are highly tailored to specific clinical tasks, which limits their expressivity and generalization, particularly in scenarios with limited data. Instead, we hypothesize that morphological redundancy in tissue can be leveraged to build a task-agnostic slide representation in an unsupervised fashion. To this end, we introduce PANTHER, a prototype-based approach rooted in the Gaussian mixture model that summarizes the set of WSI patches into a much smaller set of morphological prototypes. Specifically, each patch is assumed to have been generated from a mixture distribution, where each mixture component represents a morphological exemplar. Utilizing the estimated mixture parameters, we then construct a compact slide representation that can be readily used for a wide range of downstream tasks. By performing an extensive evaluation of PANTHER on subtyping and survival tasks using 13 datasets, we show that 1) PANTHER outperforms or is on par with supervised MIL baselines and 2) the analysis of morphological prototypes brings new qualitative and quantitative insights into model interpretability.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). Builds on 41 of its 100 references that are in the map. First posted on arXiv 19 May 2024.

Builds on

41 of 100 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  6. 2017Deep Setscited by 1,394
  7. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  8. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
  9. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  10. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
  11. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
  12. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 357
29 more
  1. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 254
  2. 2020Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networkscited by 178
  3. 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
  4. 2022Benchmarking Self-Supervised Learning on Diverse Pathology Datasetscited by 148
  5. 2020Self supervised contrastive learning for digital histopathologycited by 146
  6. 2023Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Imagescited by 132
  7. 2023Artificial Intelligence for Digital and Computational Pathologycited by 106
  8. 2023Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Predictioncited by 92
  9. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
  10. 2023Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Predictioncited by 86
  11. 2020Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Imagescited by 81
  12. 2019Automated Gleason Grading of Prostate Biopsies using Deep Learningcited by 69
  13. 2022Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathologycited by 58
  14. 2023Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classificationcited by 58
  15. 2022Differentiable Zooming for Multiple Instance Learning on Whole-Slide Imagescited by 43
  16. 2019Yottixel -- An Image Search Engine for Large Archives of Histopathology Whole Slide Imagescited by 41
  17. 2022Handcrafted Histological Transformer (H2T): Unsupervised Representation of Whole Slide Imagescited by 32
  18. 2022Giga-SSL: Self-Supervised Learning for Gigapixel Imagescited by 24
  19. 2022VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignmentcited by 20
  20. 2021Learning Prototype-oriented Set Representations for Meta-Learningcited by 19
  21. 2023Hierarchical discriminative learning improves visual representations of biomedical microscopycited by 12
  22. 2022Incorporating intratumoral heterogeneity into weakly-supervised deep learning models via variance poolingcited by 11
  23. 2022Human-machine Interactive Tissue Prototype Learning for Label-efficient Histopathology Image Segmentationcited by 9
  24. 2015Histopathological Image Classification using Discriminative Feature-oriented Dictionary Learningcited by 6
  25. 2022Hierarchical Optimal Transport for Comparing Histopathology Datasetscited by 6
  26. 2023TPMIL: Trainable Prototype Enhanced Multiple Instance Learning for Whole Slide Image Classificationcited by 5
  27. 2018Learning to rank for censored survival datacited by 4
  28. 2023Domain adaptation using optimal transport for invariant learning using histopathology datasetscited by 4
  29. 2022Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unlabeled, unannotated pathology slidescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 12; 2025: 37; 2026: 21.

70 papers.

Sort:

By area:

  1. 2024Multimodal Prototyping for cancer survival predictioncited by 47
  2. 2024PathAlign: A vision-language model for whole slide images in histopathologycited by 29
  3. 2025Do Multiple Instance Learning Models Transfer?cited by 28
  4. 2024Multistain Pretraining for Slide Representation Learning in Pathologycited by 27
  5. 2024FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classificationcited by 20
  6. 2024Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathologycited by 14
  7. 2024Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classificationcited by 10
  8. 2025GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathologycited by 8
  9. 2025OTSurv: A Novel Multiple Instance Learning Framework for Survival Prediction with Heterogeneity-aware Optimal Transportcited by 8
  10. 2025Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representationcited by 6
  11. 2025DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Predictioncited by 6
  12. 2025SurvAgent: Hierarchical CoT-Enhanced Case Banking and Dichotomy-Based Multi-Agent System for Multimodal Survival Predictioncited by 5
38 more
  1. 2026ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imagingcited by 5
  2. 2024Mamba2MIL: State Space Duality Based Multiple Instance Learning for Computational Pathologycited by 4
  3. 2024Diagnostic Text-guided Representation Learning in Hierarchical Classification for Pathological Whole Slide Imagecited by 4
  4. 2025Disentangled and Interpretable Multimodal Attention Fusion for Cancer Survival Predictioncited by 4
  5. 2025This looks like what? Challenges and Future Research Directions for Part-Prototype Modelscited by 3
  6. 2025Can We Simplify Slide-level Fine-tuning of Pathology Foundation Models?cited by 3
  7. 2025Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysiscited by 3
  8. 2025PS3: A Multimodal Transformer Integrating Pathology Reports with Histology Images and Biological Pathways for Cancer Survival Predictioncited by 3
  9. 2026QCAgent: An agentic framework for quality-controllable pathology report generation from whole slide imagecited by 3
  10. 2026Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learningcited by 3
  11. 2024Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learningcited by 2
  12. 2024Slide-based Graph Collaborative Training for Histopathology Whole Slide Image Analysiscited by 2
  13. 2024From Histopathology Images to Cell Clouds: Learning Slide Representations with Hierarchical Cell Transformercited by 2
  14. 2025PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantizationcited by 2
  15. 2025HySurvPred: Multimodal Hyperbolic Embedding with Angle-Aware Hierarchical Contrastive Learning and Uncertainty Constraints for Survival Predictioncited by 2
  16. 2025Agglomerating Large Vision Encoders via Distillation for VFSS Segmentationcited by 2
  17. 2025Prototype-Guided Diffusion for Digital Pathology: Achieving Foundation Model Performance with Minimal Clinical Datacited by 2
  18. 2025SGPMIL: Sparse Gaussian Process Multiple Instance Learningcited by 2
  19. 2025PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysiscited by 2
  20. 2025Efficient Multi-Slide Visual-Language Feature Fusion for Placental Disease Classificationcited by 2
  21. 2025Disentangled Multi-modal Learning of Histology and Transcriptomics for Cancer Characterizationcited by 2
  22. 2025ME-Mamba: Multi-Expert Mamba with Efficient Knowledge Capture and Fusion for Multimodal Survival Analysiscited by 2
  23. 2026Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosiscited by 2
  24. 2026Bridging the Modality Bottleneck in Pathology MIL through Virtual Molecular Stainingcited by 2
  25. 2025Slide-Level Prompt Learning with Vision Language Models for Few-Shot Multiple Instance Learning in Histopathologycited by 1
  26. 2025MVHybrid: Improving Spatial Transcriptomics Prediction with Hybrid State Space-Vision Transformer Backbone in Pathology Vision Foundation Modelscited by 1
  27. 2025Cross-Cancer Knowledge Transfer in WSI-based Prognosis Predictioncited by 1
  28. 2025Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysiscited by 1
  29. 2025MMAP: A Multi-Magnification and Prototype-Aware Architecture for Predicting Spatial Gene Expressioncited by 1
  30. 2025Together, Then Apart: Balancing Alignment and Distinctiveness for Multimodal Survival Analysiscited by 1
  31. 2026CTIS-QA: Clinical Template-Informed Slide-level Question Answering for Pathologycited by 1
  32. 2026Prototype-driven fusion of pathology and spatial transcriptomics for interpretable survival predictioncited by 1
  33. 2026Hepato-LLaVA: An Expert MLLM with Sparse Topo-Pack Attention for Hepatocellular Pathology Analysis on Whole Slide Imagescited by 1
  34. 2026Benchmarking Pathology Foundation Models for Breast Cancer Survival Predictioncited by 1
  35. 2024Multimodal Outer Arithmetic Block Dual Fusion of Whole Slide Images and Omics Data for Precision Oncologycited by 0
  36. 2025Histomorphology-Guided Prototypical Multi-Instance Learning for Breast Cancer WSI Classificationcited by 0
  37. 2025VGAT: A Cancer Survival Analysis Framework Transitioning from Generative Visual Question Answering to Genomic Reconstructioncited by 0
  38. 2025A Prototype-Guided Coarse Annotations Refining Approach for Whole Slide Imagescited by 0

50 most cited of 70 All 70 (JSON)