Diagnosis of Tuberculosis Using Medical Images by Convolutional Neural Networks
Background: One of the best ways to reduce the spread of tuberculosis (TB) is to diagnose the disease using chest X-ray (CXR) images as a low-cost and affordable method. However, there are two problems: the lack of adequate radiologists and the possibility of misdiagnosis. This is why it is necessar...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Kerman University of Medical Sciences
2024-08-01
|
| Series: | Journal of Kerman University of Medical Sciences |
| Subjects: | |
| Online Access: | https://jkmu.kmu.ac.ir/article_92487_46e5785723fed7ba803e27d2079c2684.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850034593493680128 |
|---|---|
| author | Abolfazl Pordeli Shahreki Fatemeh Sadat Hosseini-Baharanchi Masoud Roudbari |
| author_facet | Abolfazl Pordeli Shahreki Fatemeh Sadat Hosseini-Baharanchi Masoud Roudbari |
| author_sort | Abolfazl Pordeli Shahreki |
| collection | DOAJ |
| description | Background: One of the best ways to reduce the spread of tuberculosis (TB) is to diagnose the disease using chest X-ray (CXR) images as a low-cost and affordable method. However, there are two problems: the lack of adequate radiologists and the possibility of misdiagnosis. This is why it is necessary to use an accessible and accurate diagnostic system. This research aimed to design an accurate and accessible automatic diagnosis system that can solve diagnosis problems using deep learning.Methods: Six convolutional neural networks (CNNs), InceptionV3, ResNet50, DenseNet201, MnasNet, MobileNetV3, and EfficientNet-B4, were trained by transfer learning, the Adam optimizer, and 20 training epochs using the new, large, and accurate TBX11K dataset. The network was designed to categorize images into three groups: patients diagnosed with TB, patients exhibiting lung abnormalities unrelated to TB, and healthy individuals with no evidence of TB or other pulmonary anomalies within the lung imagery.Results: In the testing step, the networks achieved very high performance. The EfficientNet-B4 network outperformed the other networks with a sensitivity of 97.1%, specificity of 99.9%, and accuracy of 99.5%. It also performed better than previous studies in TB diagnosis using CXR images by CNNs.Conclusion: This research showed that with access to large high-quality datasets and standard training, it is possible to entrust the diagnosis of TB using medical images to computers and artificial neural networks with high confidence as they achieved accuracies higher than 99%. |
| format | Article |
| id | doaj-art-04a2ce7dbd044c4f8ac403449c3ca05c |
| institution | DOAJ |
| issn | 1023-9510 2008-2843 |
| language | English |
| publishDate | 2024-08-01 |
| publisher | Kerman University of Medical Sciences |
| record_format | Article |
| series | Journal of Kerman University of Medical Sciences |
| spelling | doaj-art-04a2ce7dbd044c4f8ac403449c3ca05c2025-08-20T02:57:45ZengKerman University of Medical SciencesJournal of Kerman University of Medical Sciences1023-95102008-28432024-08-0131418018610.34172/jkmu.2024.2992487Diagnosis of Tuberculosis Using Medical Images by Convolutional Neural NetworksAbolfazl Pordeli Shahreki0Fatemeh Sadat Hosseini-Baharanchi1Masoud Roudbari2Department of Biostatistics, School of Public Health, Iran University of Medical Sciences, Tehran, IranMinimally Invasive Surgery Research Center, & Department of Biostatistics, School of Public Health, Iran University of Medical Sciences, Tehran, IranDepartment of Biostatistics, School of Public Health, Iran University of Medical Sciences, Tehran, IranBackground: One of the best ways to reduce the spread of tuberculosis (TB) is to diagnose the disease using chest X-ray (CXR) images as a low-cost and affordable method. However, there are two problems: the lack of adequate radiologists and the possibility of misdiagnosis. This is why it is necessary to use an accessible and accurate diagnostic system. This research aimed to design an accurate and accessible automatic diagnosis system that can solve diagnosis problems using deep learning.Methods: Six convolutional neural networks (CNNs), InceptionV3, ResNet50, DenseNet201, MnasNet, MobileNetV3, and EfficientNet-B4, were trained by transfer learning, the Adam optimizer, and 20 training epochs using the new, large, and accurate TBX11K dataset. The network was designed to categorize images into three groups: patients diagnosed with TB, patients exhibiting lung abnormalities unrelated to TB, and healthy individuals with no evidence of TB or other pulmonary anomalies within the lung imagery.Results: In the testing step, the networks achieved very high performance. The EfficientNet-B4 network outperformed the other networks with a sensitivity of 97.1%, specificity of 99.9%, and accuracy of 99.5%. It also performed better than previous studies in TB diagnosis using CXR images by CNNs.Conclusion: This research showed that with access to large high-quality datasets and standard training, it is possible to entrust the diagnosis of TB using medical images to computers and artificial neural networks with high confidence as they achieved accuracies higher than 99%.https://jkmu.kmu.ac.ir/article_92487_46e5785723fed7ba803e27d2079c2684.pdfconvolutional neural networkmedical imagesdeep learningchest x-raytuberculosis |
| spellingShingle | Abolfazl Pordeli Shahreki Fatemeh Sadat Hosseini-Baharanchi Masoud Roudbari Diagnosis of Tuberculosis Using Medical Images by Convolutional Neural Networks Journal of Kerman University of Medical Sciences convolutional neural network medical images deep learning chest x-ray tuberculosis |
| title | Diagnosis of Tuberculosis Using Medical Images by Convolutional Neural Networks |
| title_full | Diagnosis of Tuberculosis Using Medical Images by Convolutional Neural Networks |
| title_fullStr | Diagnosis of Tuberculosis Using Medical Images by Convolutional Neural Networks |
| title_full_unstemmed | Diagnosis of Tuberculosis Using Medical Images by Convolutional Neural Networks |
| title_short | Diagnosis of Tuberculosis Using Medical Images by Convolutional Neural Networks |
| title_sort | diagnosis of tuberculosis using medical images by convolutional neural networks |
| topic | convolutional neural network medical images deep learning chest x-ray tuberculosis |
| url | https://jkmu.kmu.ac.ir/article_92487_46e5785723fed7ba803e27d2079c2684.pdf |
| work_keys_str_mv | AT abolfazlpordelishahreki diagnosisoftuberculosisusingmedicalimagesbyconvolutionalneuralnetworks AT fatemehsadathosseinibaharanchi diagnosisoftuberculosisusingmedicalimagesbyconvolutionalneuralnetworks AT masoudroudbari diagnosisoftuberculosisusingmedicalimagesbyconvolutionalneuralnetworks |