Deep learning-based automatic detection of tuberculosis disease in chest X-ray images

Abstract

Purpose:To train a convolutional neural network (CNN) model from scratch to automatically detect tuberculosis (TB) from chest X-ray (CXR) images and compare its performance with transfer learning based technique of different pre-trained CNNs. Material and methods:We used two publicly available datasets of postero-anterior chest radiographs, which are from Montgomery County, Maryland, and Shenzhen, China. A CNN (ConvNet) from scratch was trained to automatically detect TB on chest radiographs. Also, a CNN-based transfer learning approach using five different pre-trained models, including Inception_v3, Xception, ResNet50, VGG19, and VGG16 was utilized for classifying TB and normal cases from CXR images. The performance of models for testing datasets was evaluated using five performances metrics, including accuracy, sensitivity/recall, precision, area under curve (AUC), and F1-score. Results:All proposed models provided an acceptable accuracy for two-class classification. Our proposed CNN architecture (i.e., ConvNet) achieved 88.0% precision, 87.0% sensitivity, 87.0% F1-score, 87.0% accuracy, and AUC of 87.0%, which was slightly less than the pre-trained models. Among all models, Exception, ResNet50, and VGG16 provided the highest classification performance of automated TB classification with precision, sensitivity, F1-score, and AUC of 91.0%, and 90.0% accuracy. Conclusions:Our study presents a transfer learning approach with deep CNNs to automatically classify TB and normal cases from the chest radiographs. The classification accuracy, precision, sensitivity, and F1-score for the detection of TB were found to be more than 87.0% for all models used in the study. Exception, ResNet50, and VGG16 models outperformed other deep CNN models for the datasets with image augmentation methods.

A Review of Recent Advances in Deep Learning Models for Chest Disease Detection Using Radiography

“…Results show the effectiveness of the attention mechanism with an ACC of 92.73%, a PRE of 92.73%, an F1-score of 92.82% and an AUC of 97.71%. Eman et al [118] introduced a DCNN model (ConvNet) trained from scratch to automatically detect TB on CXR images. Furthermore, a transfer learning techniques with five different pre-trained models (VGG-16, VGG-19, Inception-V3, ResNet-50 and, Xception) was used to evaluate the performance of each model with the proposed technique.…”

Fully automated clinical target volume segmentation for glioblastoma radiotherapy using a deep convolutional neural network

“…Deep convolutional neural networks (CNNs), as a deep learning method, outperform alternative methods, i.e. classic machine learning methods, in a wide range of applications [17][18][19][20], including medical image segmentation [21,22]. Therefore, deep CNNs can be considered as the state-of-the art computer-assisted method for segmentation.…”

Convolution Neural Network With Coordinate Attention for the Automatic Detection of Pulmonary Tuberculosis Images on Chest X-Rays

“…In previous studies, deep learning, such as convolutional neural networks have achieved relatively good results in the classification and recognition of tuberculosis medical images. Eman Showkatian et al [8] proposed a CNN architecture (ConvNet), which achieved 88.0% accuracy, 87.0% sensitivity, 87.0% F1 score, 87.0% Precision and 87.0% AUC on the tuberculosis classification data sets in Shenzhen and Montgomery, China. Qingchen, Zhang et al [9]achieved an accuracy of 87.71% on the Montgomery tuberculosis classification dataset by changing the global average pooling of the network model to an adaptive dropout layer based on the residual network ResNet50.…”