Gigapixel Histopathological Image Analysis using Attention-based Neural Networks

TL;DR

This paper introduces an attention-based CNN approach for analyzing gigapixel histopathological images using only weak labels, effectively capturing global and local features for tasks like binary classification and tumor proliferation scoring.

Contribution

The proposed method uniquely combines a residual network with attention modules to analyze high-resolution images without detailed annotations, addressing key challenges in gigapixel image analysis.

Findings

Outperforms state-of-the-art methods on Camelyon16 and TUPAC16 datasets.

Effectively captures spatial correlations for improved localization.

Requires only weak image-level labels, reducing annotation effort.

Abstract

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.