Abstract

The early screening and diagnosis of tuberculosis plays an important role in the control and treatment of tuberculosis infections. In this paper, an integrated computer-aided system based on deep learning is proposed for the detection of multiple categories of tuberculosis lesions in chest radiographs. In this system, the fully convolutional neural network method is used to segment the lung area from the entire chest radiograph for pulmonary tuberculosis detection. Different from the previous analysis of the whole chest radiograph, we focus on the specific tuberculosis lesion areas for the analysis and propose the first multicategory tuberculosis lesion detection method. In it, a learning scalable pyramid structure is introduced into the Faster Region-based Convolutional Network (Faster RCNN), which effectively improves the detection of small-area lesions, mines indistinguishable samples during the training process, and uses reinforcement learning to reduce the detection of false-positive lesions. To compare our method with the current tuberculosis detection system, we propose a classification rule for whole chest X-rays using a multicategory tuberculosis lesion detection model and achieve good performance on two public datasets (Montgomery: AUC = 0.977 and accuracy = 0.926; Shenzhen: AUC = 0.941 and accuracy = 0.902). Our proposed computer-aided system is superior to current systems that can be used to assist radiologists in diagnoses and public health providers in screening for tuberculosis in areas where tuberculosis is endemic.

Highlights

  • Tuberculosis is a communicable disease that is one of the top 10 causes of death worldwide

  • A major limitation of chest radiography is that it requires experienced radiologists, and few experienced radiologists are available in these countries. us, some computer-aided systems have been developed in recent years that use digital techniques to detect the physiological and pathological conditions of various diseases, including breast cancer [6] and Journal of Healthcare Engineering tuberculosis

  • This paper proposes a multicategory tuberculosis lesion detection scheme for the first time, which is different from the methods that classify the whole CXR image and the previous single-category symptom detection methods

Read more

Summary

Introduction

Tuberculosis is a communicable disease that is one of the top 10 causes of death worldwide. Ese methods avoid the problem of manually extracting features by automatically extracting deep high-level hierarchical features for tuberculosis classification directly from the input raw data. These systems use whole chest radiographs as classification targets. In order to avoid the problem of manually extracting image features, a computeraided system based on deep learning is proposed for the detection of multiple categories of tuberculosis lesions in radiographs. This paper proposes a multicategory tuberculosis lesion detection scheme for the first time, which is different from the methods that classify the whole CXR image and the previous single-category symptom detection methods. We have achieved good performance on two public datasets [26], which exceeds the performances of existing methods. e proposed system can effectively improve the diagnostic efficiency of radiologists for tuberculosis and can be used to effectively screen tuberculosis by public health organizations

Materials and Methods
Results and Discussion
Evaluation Metrics and Results
Method
Full Text
Paper version not known

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 call

Disclaimer: 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.