Dynamic Residual Encoding with Slide-Level Contrastive Learning for End-to-End Whole Slide Image Representation

• URL: http://arxiv.org/abs/2511.05034v1
• Date: Fri, 07 Nov 2025 07:17:17 GMT
• Title: Dynamic Residual Encoding with Slide-Level Contrastive Learning for End-to-End Whole Slide Image Representation
• Abstract summary: Whole Slide Image (WSI) representation is critical for cancer subtyping, cancer recognition and mutation prediction.<n>We propose a method of dynamic residual encoding with slide-level contrastive learning (DRE-SLCL) for end-to-end WSI representation.
• Score: 20.60316821474408
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Whole Slide Image (WSI) representation is critical for cancer subtyping, cancer recognition and mutation prediction.Training an end-to-end WSI representation model poses significant challenges, as a standard gigapixel slide can contain tens of thousands of image tiles, making it difficult to compute gradients of all tiles in a single mini-batch due to current GPU limitations. To address this challenge, we propose a method of dynamic residual encoding with slide-level contrastive learning (DRE-SLCL) for end-to-end WSI representation. Our approach utilizes a memory bank to store the features of tiles across all WSIs in the dataset. During training, a mini-batch usually contains multiple WSIs. For each WSI in the batch, a subset of tiles is randomly sampled and their features are computed using a tile encoder. Then, additional tile features from the same WSI are selected from the memory bank. The representation of each individual WSI is generated using a residual encoding technique that incorporates both the sampled features and those retrieved from the memory bank. Finally, the slide-level contrastive loss is computed based on the representations and histopathology reports ofthe WSIs within the mini-batch. Experiments conducted over cancer subtyping, cancer recognition, and mutation prediction tasks proved the effectiveness of the proposed DRE-SLCL method.

Related papers

• Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning [52.41928980786654]
  We propose PathCTM to enable token-efficient scale-space continuous reasoning for gigapixel whole slide images.<n>PathCTM formulates diagnostic inference as a dynamic sequential information pursuit.<n>It reduces the number of required image patches by 95.95% and shortens inference time by approximately 95.62%, while maintaining AUC without degradation.
  arXiv  Detail & Related papers  (2026-05-19T07:46:44Z)
• Parameter-efficient Prompt Tuning and Hierarchical Textual Guidance for Few-shot Whole Slide Image Classification [2.2346611200823934]
  Whole Slide Images (WSIs) are giga-pixel in scale and are typically partitioned into small instances in WSI classification pipelines.<n>We introduce a new parameter efficient prompt tuning method by scaling and shifting features in text encoder.<n>We also introduce a WSI representation learning approach with a soft hierarchical textual guidance strategy without utilizing hard instance filtering.
  arXiv  Detail & Related papers  (2026-03-23T02:50:52Z)
• Aggregation Schemes for Single-Vector WSI Representation Learning in Digital Pathology [2.0088541799100392]
  A crucial step to efficiently integrate Whole Slide Images (WSIs) in computational pathology is assigning a single high-quality feature vector, i.e., one embedding, to each WSI.<n>In this paper, we evaluate the WSI search performance of multiple recently developed aggregation techniques.
  arXiv  Detail & Related papers  (2025-01-29T18:14:51Z)
• MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuning [47.66327196203432]
  Multiple instance learning has become a standard paradigm for the weakly supervised classification of whole slide images.<n>The lack of training data and the presence of rare diseases pose significant challenges for these methods.<n>We propose a Multi-Scale and Context-focused Prompt Tuning (MSCPT) method for the Few-shot Weakly Supervised WSI Classification task.
  arXiv  Detail & Related papers  (2024-08-21T10:25:51Z)
• RetMIL: Retentive Multiple Instance Learning for Histopathological Whole Slide Image Classification [10.365234803533982]
  We propose a retentive MIL method called RetMIL, which processes WSI sequences through hierarchical feature propagation structure. At the local level, the WSI sequence is divided into multiple subsequences. Tokens of each subsequence are updated through a parallel linear retention mechanism. At the global level, subsequences are fused into a global sequence, then updated through a serial retention mechanism, and finally the slide-level representation is obtained through a global attention pooling.
  arXiv  Detail & Related papers  (2024-03-16T08:50:47Z)
• Subobject-level Image Tokenization [60.80949852899857]
  Patch-based image tokenization ignores the morphology of the visual world.<n>Inspired by subword tokenization, we introduce subobject-level adaptive token segmentation.<n>We show that subobject tokenization enables faster convergence and better generalization while using fewer visual tokens.
  arXiv  Detail & Related papers  (2024-02-22T06:47:44Z)
• A self-supervised framework for learning whole slide representations [52.774822784847565]
  We present Slide Pre-trained Transformers (SPT) for gigapixel-scale self-supervision of whole slide images. We benchmark SPT visual representations on five diagnostic tasks across three biomedical microscopy datasets.
  arXiv  Detail & Related papers  (2024-02-09T05:05:28Z)
• Artifact-Robust Graph-Based Learning in Digital Pathology [2.9998889086656586]
  Whole slide images(WSIs) are digitized images of tissues placed in glass slides using advanced scanners. In this work, a novel robust learning approach to account for these artifacts is presented. The accuracy and scores of the proposed model with prostate cancer dataset compared with non-robust algorithms show significant improvement in cancer diagnosis.
  arXiv  Detail & Related papers  (2023-10-27T15:06:01Z)
• Hierarchical Transformer for Survival Prediction Using Multimodality Whole Slide Images and Genomics [63.76637479503006]
  Learning good representation of giga-pixel level whole slide pathology images (WSI) for downstream tasks is critical. This paper proposes a hierarchical-based multimodal transformer framework that learns a hierarchical mapping between pathology images and corresponding genes. Our architecture requires fewer GPU resources compared with benchmark methods while maintaining better WSI representation ability.
  arXiv  Detail & Related papers  (2022-11-29T23:47:56Z)
• Learning Binary and Sparse Permutation-Invariant Representations for Fast and Memory Efficient Whole Slide Image Search [3.2580463372881234]
  We propose a novel framework for learning binary and sparse WSI representations utilizing a deep generative modelling and the Fisher Vector. We introduce new loss functions for learning sparse and binary permutation-invariant WSI representations that employ instance-based training. The proposed method outperforms Yottixel (a recent search engine for histopathology images) both in terms of retrieval accuracy and speed.
  arXiv  Detail & Related papers  (2022-08-29T14:56:36Z)
• Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation [119.009033745244]
  This paper presents a Self-supervised Low-Rank Network ( SLRNet) for single-stage weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS) SLRNet uses cross-view self-supervision, that is, it simultaneously predicts several attentive LR representations from different views of an image to learn precise pseudo-labels. Experiments on the Pascal VOC 2012, COCO, and L2ID datasets demonstrate that our SLRNet outperforms both state-of-the-art WSSS and SSSS methods with a variety of different settings.
  arXiv  Detail & Related papers  (2022-03-19T09:19:55Z)
• Scalable Visual Transformers with Hierarchical Pooling [61.05787583247392]
  We propose a Hierarchical Visual Transformer (HVT) which progressively pools visual tokens to shrink the sequence length. It brings a great benefit by scaling dimensions of depth/width/resolution/patch size without introducing extra computational complexity. Our HVT outperforms the competitive baselines on ImageNet and CIFAR-100 datasets.
  arXiv  Detail & Related papers  (2021-03-19T03:55:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.