# Multi-scale Efficient Graph-Transformer for Whole Slide Image Classification

arXiv: https://arxiv.org/abs/2305.15773 · HTML: https://mlsanity.com/paper/2305.15773/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 59 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Nystr"omformer: A Nystr"om-Based Algorithm for Approximating Self-Attention](https://mlsanity.com/paper/2102.03902/) (2021)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [Learning Deep Transformer Models for Machine Translation](https://mlsanity.com/paper/1906.01787/) (2019)
- [DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2203.12081/) (2022)
- [Gated Multimodal Units for Information Fusion](https://mlsanity.com/paper/1702.01992/) (2017)
- [Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding](https://mlsanity.com/paper/2103.15358/) (2021)
- [Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks](https://mlsanity.com/paper/2009.11169/) (2020)
- [How Much Position Information Do Convolutional Neural Networks Encode?](https://mlsanity.com/paper/2001.08248/) (2020)
- [Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks](https://mlsanity.com/paper/2107.13048/) (2021)
- [Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding](https://mlsanity.com/paper/2105.12723/) (2021)
- [Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotations](https://mlsanity.com/paper/2008.05571/) (2020)
- [A graph-transformer for whole slide image classification](https://mlsanity.com/paper/2205.09671/) (2022)
- [Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images](https://mlsanity.com/paper/2001.01599/) (2020)
- [Neural Image Compression for Gigapixel Histopathology Image Analysis](https://mlsanity.com/paper/1811.02840/) (2018)
- [Hierarchical Graph Representations in Digital Pathology](https://mlsanity.com/paper/2102.11057/) (2021)
- [CGC-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Images](https://mlsanity.com/paper/1909.01068/) (2019)
- [Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers](https://mlsanity.com/paper/2211.11315/) (2022)
- [ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classification](https://mlsanity.com/paper/2207.01805/) (2022)

## Built on by (most cited first, 5 of 5)

- [Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspective](https://mlsanity.com/paper/2407.07841/) (2024)
- [Integrative Graph-Transformer Framework for Histopathology Whole Slide Image Representation and Classification](https://mlsanity.com/paper/2403.18134/) (2024)
- [Gene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Images](https://mlsanity.com/paper/2507.14670/) (2025)
- [Prototype-driven fusion of pathology and spatial transcriptomics for interpretable survival prediction](https://mlsanity.com/paper/2602.12441/) (2026)
- [Enhancing Thyroid Cytology Diagnosis with RAG-Optimized LLMs and Pa-thology Foundation Models](https://mlsanity.com/paper/2505.08590/) (2025)

## Abstract (arXiv)

The multi-scale information among the whole slide images (WSIs) is essential for cancer diagnosis. Although the existing multi-scale vision Transformer has shown its effectiveness for learning multi-scale image representation, it still cannot work well on the gigapixel WSIs due to their extremely large image sizes. To this end, we propose a novel Multi-scale Efficient Graph-Transformer (MEGT) framework for WSI classification. The key idea of MEGT is to adopt two independent Efficient Graph-based Transformer (EGT) branches to process the low-resolution and high-resolution patch embeddings (i.e., tokens in a Transformer) of WSIs, respectively, and then fuse these tokens via a multi-scale feature fusion module (MFFM). Specifically, we design an EGT to efficiently learn the local-global information of patch tokens, which integrates the graph representation into Transformer to capture spatial-related information of WSIs. Meanwhile, we propose a novel MFFM to alleviate the semantic gap among different resolution patches during feature fusion, which creates a non-patch token for each branch as an agent to exchange information with another branch by cross-attention. In addition, to expedite network training, a novel token pruning module is developed in EGT to reduce the redundant tokens. Extensive experiments on TCGA-RCC and CAMELYON16 datasets demonstrate the effectiveness of the proposed MEGT.