AnaXNet: Anatomy Aware Multi-label Finding Classification in Chest X-ray

TL;DR

This paper introduces AnaXNet, a multi-label chest X-ray classification model that leverages anatomical region information and graph convolutional networks to improve accuracy and localization of findings.

Contribution

The novel model integrates anatomical dependency learning with label classification, utilizing graph convolutional networks and an adjacency matrix derived from label correlations.

Findings

Outperforms current state-of-the-art methods in accuracy

Provides precise localization of findings within anatomical regions

Effectively models anatomical relationships using graph convolutional networks

Abstract

Radiologists usually observe anatomical regions of chest X-ray images as well as the overall image before making a decision. However, most existing deep learning models only look at the entire X-ray image for classification, failing to utilize important anatomical information. In this paper, we propose a novel multi-label chest X-ray classification model that accurately classifies the image finding and also localizes the findings to their correct anatomical regions. Specifically, our model consists of two modules, the detection module and the anatomical dependency module. The latter utilizes graph convolutional networks, which enable our model to learn not only the label dependency but also the relationship between the anatomical regions in the chest X-ray. We further utilize a method to efficiently create an adjacency matrix for the anatomical regions using the correlation of the label across the different regions. Detailed experiments and analysis of our results show the effectiveness of our method when compared to the current state-of-the-art multi-label chest X-ray image classification methods while also providing accurate location information.