# Gigapixel Histopathological Image Analysis using Attention-based Neural Networks

arXiv: https://arxiv.org/abs/2101.09992 · HTML: https://mlsanity.com/paper/2101.09992/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 25 Jan 2021.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification](https://mlsanity.com/paper/1504.07947/) (2015)
- [BACH: Grand Challenge on Breast Cancer Histology Images](https://mlsanity.com/paper/1808.04277/) (2018)
- [Neural Image Compression for Gigapixel Histopathology Image Analysis](https://mlsanity.com/paper/1811.02840/) (2018)
- [Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge](https://mlsanity.com/paper/1807.08284/) (2018)
- [Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach](https://mlsanity.com/paper/1802.02212/) (2018)
- [Attention-Based Deep Neural Networks for Detection of Cancerous and Precancerous Esophagus Tissue on Histopathological Slides](https://mlsanity.com/paper/1811.08513/) (2018)
- [Histopathological Image Classification using Discriminative Feature-oriented Dictionary Learning](https://mlsanity.com/paper/1506.05032/) (2015)
- [Deep Learning Framework for Multi-class Breast Cancer Histology Image Classification](https://mlsanity.com/paper/1802.00931/) (2018)
- [Improving High Resolution Histology Image Classification with Deep Spatial Fusion Network](https://mlsanity.com/paper/1807.10552/) (2018)

## Built on by (most cited first, 6 of 6)

- [BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images](https://mlsanity.com/paper/2111.04740/) (2021)
- [Efficient Quality Control of Whole Slide Pathology Images with Human-in-the-loop Training](https://mlsanity.com/paper/2409.19587/) (2024)
- [Attention De-sparsification Matters: Inducing Diversity in Digital Pathology Representation Learning](https://mlsanity.com/paper/2309.06439/) (2023)
- [Patch Gradient Descent: Training Neural Networks on Very Large Images](https://mlsanity.com/paper/2301.13817/) (2023)
- [Semantic Segmentation Based Quality Control of Histopathology Whole Slide Images](https://mlsanity.com/paper/2410.03289/) (2024)
- [Augmentation-Based Deep Learning for Identification of Circulating Tumor Cells](https://mlsanity.com/paper/2503.03410/) (2025)

## Abstract (arXiv)

Although CNNs are widely considered as the state-of-the-art models in various applications of image analysis, one of the main challenges still open is the training of a CNN on high resolution images. Different strategies have been proposed involving either a rescaling of the image or an individual processing of parts of the image. Such strategies cannot be applied to images, such as gigapixel histopathological images, for which a high reduction in resolution inherently effects a loss of discriminative information, and in respect of which the analysis of single parts of the image suffers from a lack of global information or implies a high workload in terms of annotating the training images in such a way as to select significant parts. We propose a method for the analysis of gigapixel histopathological images solely by using weak image-level labels. In particular, two analysis tasks are taken into account: a binary classification and a prediction of the tumor proliferation score. Our method is based on a CNN structure consisting of a compressing path and a learning path. In the compressing path, the gigapixel image is packed into a grid-based feature map by using a residual network devoted to the feature extraction of each patch into which the image has been divided. In the learning path, attention modules are applied to the grid-based feature map, taking into account spatial correlations of neighboring patch features to find regions of interest, which are then used for the final whole slide analysis. Our method integrates both global and local information, is flexible with regard to the size of the input images and only requires weak image-level labels. Comparisons with different methods of the state-of-the-art on two well known datasets, Camelyon16 and TUPAC16, have been made to confirm the validity of the proposed model.