Abstract
Currently, the tuberculosis (TB) detection model based on chest X-ray images has the problem of excessive reliance on hardware computing resources, high equipment performance requirements, and being harder to deploy in low-cost personal computer and embedded devices. An efficient tuberculosis detection model is proposed to achieve accurate, efficient, and stable tuberculosis screening on devices with lower hardware levels. Due to the particularity of the chest X-ray images of TB patients, there are fewer labeled data, and the deep neural network model is difficult to fully train. We first analyzed the data distribution characteristics of two public TB datasets, and found that the two-stage tuberculosis identification (first divide, then classify) is insufficient. Secondly, according to the particularity of the detection image(s), the basic residual module was optimized and improved, and this is regarded as a crucial component of this article’s network. Finally, an efficient attention mechanism was introduced, which was used to fuse the channel features. The network architecture was optimally designed and adjusted according to the correct and sufficient experimental content. In order to evaluate the performance of the network, it was compared with other lightweight networks under personal computer and Jetson Xavier embedded devices. The experimental results show that the recall rate and accuracy of the E-TBNet proposed in this paper are better than those of classic lightweight networks such as SqueezeNet and ShuffleNet, and it also has a shorter reasoning time. E-TBNet will be more advantageous to deploy on equipment with low levels of hardware.
Highlights
According to the “Global Tuberculosis Report 2020” issued by the World HealthOrganization (WHO), the number of new tuberculosis patients in China in 2019 was approximately 833,000, ranking third in the world [1]
Digital radiography (DR) technology is widely used in tuberculosis screening, and chest radiographs are examined by experienced physicians for the diagnosis of TB
We propose an efficient tuberculosis identification network that does not require large-scale data and has a faster reasoning process, and has some limitations; for example, (1) its input must be 512 × 512 × 3 PNG images, and it cannot adapt to the image size; (2) the images collected by different digital radiography (DR) devices have differences in brightness, grayscale, etc., which will make the network unstable; and (3) The Digital Imaging and Communications in Medicine (DICOM) data generated by the DR equipment must be converted into PNG images before they can be used for model classification
Summary
According to the “Global Tuberculosis Report 2020” issued by the World HealthOrganization (WHO), the number of new tuberculosis patients in China in 2019 was approximately 833,000, ranking third in the world [1]. Due to the lack of experienced physicians or related diagnostic equipment in China’s economically underdeveloped remote areas, the prevention and treatment of tuberculosis in primary hospitals is difficult. The use of “Internet +” technology can improve the level of screening of tuberculosis patients in primary hospitals, which is an important part of effective prevention and treatment of tuberculosis. Digital radiography (DR) technology is widely used in tuberculosis screening, and chest radiographs are examined by experienced physicians for the diagnosis of TB. Physicians in primary hospitals have less experience in reading such radiographs, and the imaging quality of the DR equipment is not good. With the widespread application of deep learning technology in the field of medical image processing, the accuracy of convolutional neural networks (CNNs) in the detection of tuberculosis has been continuously improved
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
