# Cross-scale Attention Guided Multi-instance Learning for Crohn's Disease Diagnosis with Pathological Images

arXiv: https://arxiv.org/abs/2208.07322 · HTML: https://mlsanity.com/paper/2208.07322/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 34 references that are in the map.
- First posted on arXiv 15 Aug 2022.

## Builds on (most cited first, 15 of 15)

- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks](https://mlsanity.com/paper/2009.11169/) (2020)
- [Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification](https://mlsanity.com/paper/1504.07947/) (2015)
- [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)
- [Deep Learning for Whole Slide Image Analysis: An Overview](https://mlsanity.com/paper/1910.11097/) (2019)
- [Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology](https://mlsanity.com/paper/2012.03583/) (2020)
- [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)
- [Multi-Class Cell Detection Using Spatial Context Representation](https://mlsanity.com/paper/2110.04886/) (2021)
- [Negative Log Likelihood Ratio Loss for Deep Neural Network Classification](https://mlsanity.com/paper/1804.10690/) (2018)
- [SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification](https://mlsanity.com/paper/2003.05080/) (2020)
- [AMINN: Autoencoder-based Multiple Instance Neural Network Improves Outcome Prediction of Multifocal Liver Metastases](https://mlsanity.com/paper/2012.06875/) (2020)

## Built on by (most cited first, 4 of 4)

- [Cross-scale Multi-instance Learning for Pathological Image Diagnosis](https://mlsanity.com/paper/2304.00216/) (2023)
- [A Cytology Dataset for Early Detection of Oral Squamous Cell Carcinoma](https://mlsanity.com/paper/2506.09661/) (2025)
- [Cross-modality Attention-based Multimodal Fusion for Non-small Cell Lung Cancer (NSCLC) Patient Survival Prediction](https://mlsanity.com/paper/2308.09831/) (2023)
- [MsaMIL-Net: An End-to-End Multi-Scale Aware Multiple Instance Learning Network for Efficient Whole Slide Image Classification](https://mlsanity.com/paper/2503.08581/) (2025)

## Abstract (arXiv)

Multi-instance learning (MIL) is widely used in the computer-aided interpretation of pathological Whole Slide Images (WSIs) to solve the lack of pixel-wise or patch-wise annotations. Often, this approach directly applies "natural image driven" MIL algorithms which overlook the multi-scale (i.e. pyramidal) nature of WSIs. Off-the-shelf MIL algorithms are typically deployed on a single-scale of WSIs (e.g., 20x magnification), while human pathologists usually aggregate the global and local patterns in a multi-scale manner (e.g., by zooming in and out between different magnifications). In this study, we propose a novel cross-scale attention mechanism to explicitly aggregate inter-scale interactions into a single MIL network for Crohn's Disease (CD), which is a form of inflammatory bowel disease. The contribution of this paper is two-fold: (1) a cross-scale attention mechanism is proposed to aggregate features from different resolutions with multi-scale interaction; and (2) differential multi-scale attention visualizations are generated to localize explainable lesion patterns. By training ~250,000 H&E-stained Ascending Colon (AC) patches from 20 CD patient and 30 healthy control samples at different scales, our approach achieved a superior Area under the Curve (AUC) score of 0.8924 compared with baseline models. The official implementation is publicly available at https://github.com/hrlblab/CS-MIL.