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

by   Baolian Qi, et al.

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.


page 1

page 4

page 8

page 9


Cross Chest Graph for Disease Diagnosis with Structural Relational Reasoning

Locating lesions is important in the computer-aided diagnosis of X-ray i...

Contralaterally Enhanced Networks for Thoracic Disease Detection

Identifying and locating diseases in chest X-rays are very challenging, ...

Deep multiscale convolutional feature learning for weakly supervised localization of chest pathologies in X-ray images

Localization of chest pathologies in chest X-ray images is a challenging...

Iterative Attention Mining for Weakly Supervised Thoracic Disease Pattern Localization in Chest X-Rays

Given image labels as the only supervisory signal, we focus on harvestin...

Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs

The lack of fine-grained annotations hinders the deployment of automated...

Weakly Supervised Object Localization with Inter-Intra Regulated CAMs

Weakly supervised object localization (WSOL) aims to locate objects in i...

Weighing Features of Lung and Heart Regions for Thoracic Disease Classification

Chest X-rays are the most commonly available and affordable radiological...

Please sign up or login with your details

Forgot password? Click here to reset