mlsanityData to 14 Oct 2026

DSCA: A Dual-Stream Network with Cross-Attention on Whole-Slide Image Pyramids for Cancer Prognosis

arXiv 2206.05782 ↗First posted 12 Jun 2022eess.IV cs.CV cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

The cancer prognosis on gigapixel Whole-Slide Images (WSIs) has always been a challenging task. To further enhance WSI visual representations, existing methods have explored image pyramids, instead of single-resolution images, in WSIs. In spite of this, they still face two major problems: high computational cost and the unnoticed semantical gap in multi-resolution feature fusion. To tackle these problems, this paper proposes to efficiently exploit WSI pyramids from a new perspective, the dual-stream network with cross-attention (DSCA). Our key idea is to utilize two sub-streams to process the WSI patches with two resolutions, where a square pooling is devised in a high-resolution stream to significantly reduce computational costs, and a cross-attention-based method is proposed to properly handle the fusion of dual-stream features. We validate our DSCA on three publicly-available datasets with a total number of 3,101 WSIs from 1,911 patients. Our experiments and ablation studies verify that (i) the proposed DSCA could outperform existing state-of-the-art methods in cancer prognosis, by an average C-Index improvement of around 4.6%; (ii) our DSCA network is more efficient in computation -- it has more learnable parameters (6.31M vs. 860.18K) but less computational costs (2.51G vs. 4.94G), compared to a typical existing multi-resolution network. (iii) the key components of DSCA, dual-stream and cross-attention, indeed contribute to our model's performance, gaining an average C-Index rise of around 2.0% while maintaining a relatively-small computational load. Our DSCA could serve as an alternative and effective tool for WSI-based cancer prognosis.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 24 of its 54 references that are in the map. First posted on arXiv 12 Jun 2022.

Builds on

24 of 54 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2016Layer Normalizationcited by 5,669
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  9. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  10. 2017Deep Setscited by 1,421
  11. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  12. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
12 more
  1. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
  2. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
  3. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
  4. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 359
  5. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  6. 2020Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networkscited by 178
  7. 2016Multiple Instance Learning: A Survey of Problem Characteristics and Applicationscited by 164
  8. 2021Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networkscited by 124
  9. 2016Revisiting Multiple Instance Neural Networkscited by 119
  10. 2020Feature Pyramid Transformercited by 96
  11. 2021Hierarchical Graph Representations in Digital Pathologycited by 59
  12. 2020HACT-Net: A Hierarchical Cell-to-Tissue Graph Neural Network for Histopathological Image Classificationcited by 33

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 5; 2025: 0; 2026: 1.

10 papers.

  1. 2022AdvMIL: Adversarial Multiple Instance Learning for the Survival Analysis on Whole-Slide Imagescited by 24
  2. 2024Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathologycited by 14
  3. 2023Dual Attention Model with Reinforcement Learning for Classification of Histology Whole-Slide Imagescited by 5
  4. 2023ProtoDiv: Prototype-guided Division of Consistent Pseudo-bags for Whole-slide Image Classificationcited by 5
  5. 2023Multi-scale Efficient Graph-Transformer for Whole Slide Image Classificationcited by 5
  6. 2024cDP-MIL: Robust Multiple Instance Learning via Cascaded Dirichlet Processcited by 5
  7. 2024Self-Contrastive Weakly Supervised Learning Framework for Prognostic Prediction Using Whole Slide Imagescited by 0
  8. 2024M2EF-NNs: Multimodal Multi-instance Evidence Fusion Neural Networks for Cancer Survival Predictioncited by 0
  9. 2024Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning for Imbalanced Multiclassification of Whole Slide Imagecited by 0
  10. 2026Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoringcited by 0