Transfer Learning with Deep Convolutional Neural Network (CNN) for Pneumonia Detection Using Chest X-ray

Abstract

Pneumonia is a life-threatening disease, which occurs in the lungs caused by either bacterial or viral infection. It can be life-endangering if not acted upon at the right time and thus the early diagnosis of pneumonia is vital. The paper aims to automatically detect bacterial and viral pneumonia using digital x-ray images. It provides a detailed report on advances in accurate detection of pneumonia and then presents the methodology adopted by the authors. Four different pre-trained deep Convolutional Neural Network (CNN): AlexNet, ResNet18, DenseNet201, and SqueezeNet were used for transfer learning. A total of 5247 chest X-ray images consisting of bacterial, viral, and normal chest x-rays images were preprocessed and trained for the transfer learning-based classification task. In this study, the authors have reported three schemes of classifications: normal vs. pneumonia, bacterial vs. viral pneumonia, and normal, bacterial, and viral pneumonia. The classification accuracy of normal and pneumonia images, bacterial and viral pneumonia images, and normal, bacterial, and viral pneumonia were 98%, 95%, and 93.3%, respectively. This is the highest accuracy, in any scheme, of the accuracies reported in the literature. Therefore, the proposed study can be useful in more quickly diagnosing pneumonia by the radiologist and can help in the fast airport screening of pneumonia patients.

Deep-Pneumonia Framework Using Deep Learning Models Based on Chest X-Ray Images

“…For classifying normal and pneumonia patients using chest X-ray images, four common, CNN-based, deep learning techniques were trained and tested in [1]. These algorithms were DenseNet201, ResNet18, SqueezeNet, and AlexNet.…”

“…Moreover, in [15][16][17][18], accuracy and other metrics were used. However, the author in [1] is the only one that has used all performance metrics, as in our model. Additionally, our models exceed the others in accuracy and all other performance metrics.…”

“…The optimizer and fit functions were used to train and validate these models, where each model ran around 500 epochs and each epoch has 8 steps with a batch size of 32. The results were obtained by applying the equations for each performance metric [1] to the resulting validation data outputs and the recorded results represented the maximum obtained validation values. The complete code for our deep learning framework models was uploaded to the GitHub website in [38].…”

“…Additionally, about two billion people worldwide suffer from pneumonia every year, and death can occur if action is not taken. Early diagnosis of pneumonia is a vital matter [1,2]. Therefore, rapid diagnosis by an expert radiologist using chest X-rays is required to avoid misdiagnosis.…”

Artificial Intelligence Framework for Efficient Detection and Classification of Pneumonia Using Chest Radiography Images

“…[17] is consisting of three main folders: the training, testing, and validation folders; and inside each folder there are two subfolders one of them contains pneumonia chest x-ray images while the other contains normal chest x-ray images. A total of 5,852 Chest x-ray images of anterior-posterior cross-section were carefully chosen from retrospective pediatric patients between 1 and 5 years old [15]. The entire pneumonia chest x-ray images were named with bacteria or virus and these labels were used to split the pneumonia folder into two subfolders: viral pneumonia and bacterial pneumonia.…”