mlsanityData to 7 Oct 2026

Handcrafted Histological Transformer (H2T): Unsupervised Representation of Whole Slide Images

arXiv 2202.07001 ↗First posted 14 Feb 2022eess.IV cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Diagnostic, prognostic and therapeutic decision-making of cancer in pathology clinics can now be carried out based on analysis of multi-gigapixel tissue images, also known as whole-slide images (WSIs). Recently, deep convolutional neural networks (CNNs) have been proposed to derive unsupervised WSI representations; these are attractive as they rely less on expert annotation which is cumbersome. However, a major trade-off is that higher predictive power generally comes at the cost of interpretability, posing a challenge to their clinical use where transparency in decision-making is generally expected. To address this challenge, we present a handcrafted framework based on deep CNN for constructing holistic WSI-level representations. Building on recent findings about the internal working of the Transformer in the domain of natural language processing, we break down its processes and handcraft them into a more transparent framework that we term as the Handcrafted Histological Transformer or H2T. Based on our experiments involving various datasets consisting of a total of 5,306 WSIs, the results demonstrate that H2T based holistic WSI-level representations offer competitive performance compared to recent state-of-the-art methods and can be readily utilized for various downstream analysis tasks. Finally, our results demonstrate that the H2T framework can be up to 14 times faster than the Transformer models.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 33 of its 68 references that are in the map. First posted on arXiv 14 Feb 2022.

Builds on

33 of 68 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  9. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  10. 2019Natural Adversarial Examplescited by 1,401
  11. 2016Colorful Image Colorizationcited by 1,113
  12. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
21 more
  1. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
  2. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  3. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
  4. 2020Hopfield Networks is All You Needcited by 461
  5. 2018HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Imagescited by 387
  6. 2017Multi-task Self-Supervised Visual Learningcited by 200
  7. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  8. 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
  9. 2018Self-Supervised Video Representation Learning with Space-Time Cubic Puzzlescited by 149
  10. 2020Self supervised contrastive learning for digital histopathologycited by 146
  11. 2020On Robustness and Transferability of Convolutional Neural Networkscited by 98
  12. 2021Training Vision Transformers for Image Retrievalcited by 90
  13. 2020Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotationscited by 89
  14. 2020Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Imagescited by 81
  15. 2021Deep Learning for Instance Retrieval: A Surveycited by 70
  16. 2020Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Imagescited by 33
  17. 2021Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imagingcited by 31
  18. 2020Divide-and-Rule: Self-Supervised Learning for Survival Analysis in Colorectal Cancercited by 17
  19. 2021Semantic annotation for computational pathology: Multidisciplinary experience and best practice recommendationscited by 13
  20. 2020Deep Learning Methods for Lung Cancer Segmentation in Whole-slide Histopathology Images -- the ACDC@LungHP Challenge 2019cited by 11
  21. 2021Pay Attention with Focus: A Novel Learning Scheme for Classification of Whole Slide Imagescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 7; 2024: 7; 2025: 10; 2026: 6.

32 papers.

Sort:

By area:

  1. 2023Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Imagescited by 132
  2. 2024Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathologycited by 70
  3. 2024Multimodal Prototyping for cancer survival predictioncited by 47
  4. 2023A General-Purpose Self-Supervised Model for Computational Pathologycited by 42
  5. 2023CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Countingcited by 33
  6. 2023Domain Generalization in Computational Pathology: Survey and Guidelinescited by 29
  7. 2024Multistain Pretraining for Slide Representation Learning in Pathologycited by 27
  8. 2024CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignmentcited by 20
  9. 2023Masked Pre-Training of Transformers for Histology Image Analysiscited by 12
  10. 2024StainFuser: Controlling Diffusion for Faster Neural Style Transfer in Multi-Gigapixel Histology Imagescited by 6
  11. 2025Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representationcited by 6
  12. 2025DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Predictioncited by 6
20 more
  1. 2023Unsupervised Mutual Transformer Learning for Multi-Gigapixel Whole Slide Image Classificationcited by 3
  2. 2024Pan-cancer Histopathology WSI Pre-training with Position-aware Masked Autoencodercited by 3
  3. 2025PS3: A Multimodal Transformer Integrating Pathology Reports with Histology Images and Biological Pathways for Cancer Survival Predictioncited by 3
  4. 2026Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learningcited by 3
  5. 2022CD-Net: Histopathology Representation Learning using Pyramidal Context-Detail Networkcited by 2
  6. 2022HistoPerm: A Permutation-Based View Generation Approach for Improving Histopathologic Feature Representation Learningcited by 2
  7. 2024Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learningcited by 2
  8. 2025PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantizationcited by 2
  9. 2025PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysiscited by 2
  10. 2026Bridging the Modality Bottleneck in Pathology MIL through Virtual Molecular Stainingcited by 2
  11. 2026Prototype-driven fusion of pathology and spatial transcriptomics for interpretable survival predictioncited by 1
  12. 2023Classifying Whole Slide Images: What Matters?cited by 0
  13. 2025Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Imagescited by 0
  14. 2025Histomorphology-Guided Prototypical Multi-Instance Learning for Breast Cancer WSI Classificationcited by 0
  15. 2025Cross-Modal Prototype Allocation: Unsupervised Slide Representation Learning via Patch-Text Contrast in Computational Pathologycited by 0
  16. 2025The Next Layer: Augmenting Foundation Models with Structure-Preserving and Attention-Guided Learning for Local Patches to Global Context Awareness in Computational Pathologycited by 0
  17. 2025Structural Prognostic Event Modeling for Multimodal Cancer Survival Analysiscited by 0
  18. 2026Tissue Classification and Whole-Slide Images Analysis via Modeling of the Tumor Microenvironment and Biological Pathwayscited by 0
  19. 2026PA-MIL: Phenotype-Aware Multiple Instance Learning Guided by Language Prompting and Genotype-to-Phenotype Relationshipscited by 0
  20. 2026Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensationcited by 0