Deep Learning Methods for Chest Disease Detection Using Radiography Images

Abstract

X-ray images are the most widely used medical imaging modality. They are affordable, non-dangerous, accessible, and can be used to identify different diseases. Multiple computer-aided detection (CAD) systems using deep learning (DL) algorithms were recently proposed to support radiologists in identifying different diseases on medical images. In this paper, we propose a novel two-step approach for chest disease classification. The first is a multi-class classification step based on classifying X-ray images by infected organs into three classes (normal, lung disease, and heart disease). The second step of our approach is a binary classification of seven specific lungs and heart diseases. We use a consolidated dataset of 26,316 chest X-ray (CXR) images. Two deep learning methods are proposed in this paper. The first is called DC-ChestNet. It is based on ensembling deep convolutional neural network (DCNN) models. The second is named VT-ChestNet. It is based on a modified transformer model. VT-ChestNet achieved the best performance overcoming DC-ChestNet and state-of-the-art models (DenseNet121, DenseNet201, EfficientNetB5, and Xception). VT-ChestNet obtained an area under curve (AUC) of 95.13% for the first step. For the second step, it obtained an average AUC of 99.26% for heart diseases and an average AUC of 99.57% for lung diseases.

Multimodality Risk Assessment of Patients with Ischemic Heart Disease Using Deep Learning Models Applied to Electrocardiograms and Chest X-rays

“…Therefore, the results should be interpreted with caution and are not necessarily generalizable. As for the CXR analysis model, it was difficult to use previously-reported models directly, 10,19) therefore, we created a model to detect the cardiomegaly using the open-access VinDr-CXR dataset. Although previous studies using VirDr-CXR dataset used various methods, there have been no reports using the exact same approach as ours.…”

“…6) Additionally, CXR models that can detect common morphological abnormalities of the heart from CXR images have been reported. 10) One such abnormality is cardiomegaly, which is known to be a prognostic indicator of heart failure. 11) These models have the potential to automatically detect well-known prognostic indicators from image data, thereby offering efficient and reliable diagnostic support through single-modality analysis.…”