GREN: Graph-Regularized Embedding Network for Weakly-Supervised Disease Localization in X-ray Images

TL;DR

GREN introduces a graph-regularized embedding network that models intra- and inter-image relationships to improve weakly-supervised disease localization in chest X-ray images, achieving state-of-the-art results.

Contribution

The paper proposes GREN, a novel method that incorporates cross-region and cross-image relationships using graph regularization for better disease localization.

Findings

Achieves state-of-the-art performance on NIH chest X-ray dataset.

Effectively models intra-image lung lobe relationships.

Utilizes graph regularization to enhance embedding structural information.

Abstract

Locating diseases in chest X-ray images with few careful annotations saves large human effort. Recent works approached this task with innovative weakly-supervised algorithms such as multi-instance learning (MIL) and class activation maps (CAM), however, these methods often yield inaccurate or incomplete regions. One of the reasons is the neglection of the pathological implications hidden in the relationship across anatomical regions within each image and the relationship across images. In this paper, we argue that the cross-region and cross-image relationship, as contextual and compensating information, is vital to obtain more consistent and integral regions. To model the relationship, we propose the Graph Regularized Embedding Network (GREN), which leverages the intra-image and inter-image information to locate diseases on chest X-ray images. GREN uses a pre-trained U-Net to segment the lung lobes, and then models the intra-image relationship between the lung lobes using an intra-image graph to compare different regions. Meanwhile, the relationship between in-batch images is modeled by an inter-image graph to compare multiple images. This process mimics the training and decision-making process of a radiologist: comparing multiple regions and images for diagnosis. In order for the deep embedding layers of the neural network to retain structural information (important in the localization task), we use the Hash coding and Hamming distance to compute the graphs, which are used as regularizers to facilitate training. By means of this, our approach achieves the state-of-the-art result on NIH chest X-ray dataset for weakly-supervised disease localization. Our codes are accessible online (https://github.com/qibaolian/GREN).