# DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis

arXiv: https://arxiv.org/abs/2109.05788 · HTML: https://mlsanity.com/paper/2109.05788/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 67 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification](https://mlsanity.com/paper/1504.07947/) (2015)
- [Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks](https://mlsanity.com/paper/1803.02579/) (2018)
- [Deep Learning for Identifying Metastatic Breast Cancer](https://mlsanity.com/paper/1606.05718/) (2016)
- [SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization](https://mlsanity.com/paper/2009.00726/) (2020)
- [Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primary](https://mlsanity.com/paper/2006.13932/) (2020)
- [Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images](https://mlsanity.com/paper/2001.01599/) (2020)
- [Attention Based Glaucoma Detection: A Large-scale Database and CNN Model](https://mlsanity.com/paper/1903.10831/) (2019)
- [Global Second-order Pooling Convolutional Networks](https://mlsanity.com/paper/1811.12006/) (2018)
- [Neural Image Compression for Gigapixel Histopathology Image Analysis](https://mlsanity.com/paper/1811.02840/) (2018)
- [Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images](https://mlsanity.com/paper/1905.06368/) (2019)
- [Adaptive Weighting Multi-Field-of-View CNN for Semantic Segmentation in Pathology](https://mlsanity.com/paper/1904.06040/) (2019)
- [RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification](https://mlsanity.com/paper/2010.06440/) (2020)
- [Towards Robust Image Classification Using Sequential Attention Models](https://mlsanity.com/paper/1912.02184/) (2019)
- [BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation](https://mlsanity.com/paper/2106.14033/) (2021)
- [SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification](https://mlsanity.com/paper/2003.05080/) (2020)

## Built on by (most cited first, 7 of 7)

- [FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification](https://mlsanity.com/paper/2411.14743/) (2024)
- [MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention](https://mlsanity.com/paper/2503.00374/) (2025)
- [Gene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Images](https://mlsanity.com/paper/2507.14670/) (2025)
- [SEW: Self-calibration Enhanced Whole Slide Pathology Image Analysis](https://mlsanity.com/paper/2412.10853/) (2024)
- [Any-to-Any Learning in Computational Pathology via Triplet Multimodal Pretraining](https://mlsanity.com/paper/2505.12711/) (2025)
- [Efficient Pyramidal Analysis of Gigapixel Images on a Decentralized Modest Computer Cluster](https://mlsanity.com/paper/2509.02440/) (2025)
- [Interpretable Multimodal Cancer Prototyping with Whole Slide Images and Incompletely Paired Genomics](https://mlsanity.com/paper/2511.21937/) (2025)

## Abstract (arXiv)

We present a novel weakly-supervised framework for classifying whole slide images (WSIs). WSIs, due to their gigapixel resolution, are commonly processed by patch-wise classification with patch-level labels. However, patch-level labels require precise annotations, which is expensive and usually unavailable on clinical data. With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label. To address this issue, we posit that WSI analysis can be effectively conducted by integrating information at both high magnification (local) and low magnification (regional) levels. We auto-encode the visual signals in each patch into a latent embedding vector representing local information, and down-sample the raw WSI to hardware-acceptable thumbnails representing regional information. The WSI label is then predicted with a Dual-Stream Network (DSNet), which takes the transformed local patch embeddings and multi-scale thumbnail images as inputs and can be trained by the image-level label only. Experiments conducted on two large-scale public datasets demonstrate that our method outperforms all recent state-of-the-art weakly-supervised WSI classification methods.