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

Abstract

Tuberculosis is a chronic respiratory infectious disease that seriously endangers human health. Diagnosis of pulmonary tuberculosis usually depend on the analysis of chest X-rays by radiologists. However, there is a certain misdiagnosis rate with time consuming. Therefore, the purpose of this study is to propose a low-cost and automatic detection method of pulmonary tuberculosis images on chest X-rays to help primary radiologists. A pulmonary tuberculosis classification algorithm based on convolution neural network is proposed, which uses deep learning to classify chest X-ray images. Our method introduces coordinate attention mechanism into convolutional neural network (VGG16), so that the algorithm can capture not only cross-channel information, but also direction sensing and position sensing information, in order to better identify and classify pulmonary tuberculosis images. During the training process, we use the method of transfer learning and freeze network to make the model fit faster. The performance of our method is evaluated on the public dataset of tuberculosis classification of Shenzhen Third Hospital, China. We take the average data through 5-fold cross validation: accuracy= 92.73%, AUC= 97.71%, precision= 92.73%, recall= 92.83%, F1 score = 92.82%. Compared with the existing end-to-end method based on convolutional neural network (CNN), our method is superior to ConvNet, FPN + Faster RCNN and other methods. The comparison results with other methods show that our method has better accuracy, which can help radiologists make auxiliary diagnosis.

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

“…All experiments are performed using image data acquired from different sources (Montgomery, a labeled dataset created by different institutes under the ministry of health of the Republic of Belarus and a labeled dataset, that was acquired by the kaggle public available repository). Tianhao and Zhenming [117] proposed an automated TB detection model called VGG16-CoordAttention. The proposed approach involves implementing a coordinated attention mechanism to the architecture of VGG-16.…”

A Novel Digitized Microscopic Images of ZN-Stained Sputum Smear and Its Classification Based on IUATLD Grades

“…Sputum smear microscopy, chest X-rays [3], [4], [5], [6], [7], [8], [9], [10], [11], [12] rapid molecular tests, MRI [13], and culture methods are diagnostic laboratory tests for TB. Sputum smear microscopy is the most common and essential method used in Indonesia because it is the most reliable and cost-effective approach recommended by the WHO for first-line laboratory diagnosis of TB [14].…”

Uncertainty-Aware Convolutional Neural Network for Identifying Bilateral Opacities on Chest X-rays: A Tool to Aid Diagnosis of Acute Respiratory Distress Syndrome

“…A review of the recent literature on computer-aided chest X-ray (CXR) classification was performed for the benefit of this study. Numerous studies have adopted convolutional neural networks (CNNs) to identify abnormalities on CXR images, such as pneumonia [ 27 , 28 , 29 , 30 ], tuberculosis [ 31 , 32 , 33 ], and COVID-19 [ 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 ]. The release of datasets like CheXpert [ 20 ] and MIMIC-CXR [ 21 ] has also enabled the training of deep learning models on large amounts of data to identify multiple CXR findings like atelectasis, edema, consolidation, cardiomegaly, and pleural effusion.…”

“…Many works incorporate attention mechanisms into CNNs to focus on regions of interest and improve diagnostic accuracy [ 32 , 47 , 49 , 53 ]. Many studies use ensembles of machine learning classifiers to improve disease classification using CXR images [ 29 , 40 , 43 ].…”