Deep-Learning-Aided Detection of Mycobacteria in Pathology Specimens Increases the Sensitivity in Early Diagnosis of Pulmonary Tuberculosis Compared with Bacteriology Tests
The histopathological diagnosis of mycobacterial infection may be improved by a comprehensive analysis using artificial intelligence. Two autopsy cases of pulmonary tuberculosis, and forty biopsy cases of undetected acid-fast bacilli (AFB) were used to train AI (convolutional neural network), and co...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/3/709 |
| _version_ | 1827649324058673152 |
|---|---|
| author | Yoshiaki Zaizen Yuki Kanahori Sousuke Ishijima Yuka Kitamura Han-Seung Yoon Mutsumi Ozasa Hiroshi Mukae Andrey Bychkov Tomoaki Hoshino Junya Fukuoka |
| author_facet | Yoshiaki Zaizen Yuki Kanahori Sousuke Ishijima Yuka Kitamura Han-Seung Yoon Mutsumi Ozasa Hiroshi Mukae Andrey Bychkov Tomoaki Hoshino Junya Fukuoka |
| author_sort | Yoshiaki Zaizen |
| collection | DOAJ |
| description | The histopathological diagnosis of mycobacterial infection may be improved by a comprehensive analysis using artificial intelligence. Two autopsy cases of pulmonary tuberculosis, and forty biopsy cases of undetected acid-fast bacilli (AFB) were used to train AI (convolutional neural network), and construct an AI to support AFB detection. Forty-two patients underwent bronchoscopy, and were evaluated using AI-supported pathology to detect AFB. The AI-supported pathology diagnosis was compared with bacteriology diagnosis from bronchial lavage fluid and the final definitive diagnosis of mycobacteriosis. Among the 16 patients with mycobacteriosis, bacteriology was positive in 9 patients (56%). Two patients (13%) were positive for AFB without AI assistance, whereas AI-supported pathology identified eleven positive patients (69%). When limited to tuberculosis, AI-supported pathology had significantly higher sensitivity compared with bacteriology (86% vs. 29%, <i>p</i> = 0.046). Seven patients diagnosed with mycobacteriosis had no consolidation or cavitary shadows in computed tomography; the sensitivity of bacteriology and AI-supported pathology was 29% and 86%, respectively (<i>p</i> = 0.046). The specificity of AI-supported pathology was 100% in this study. AI-supported pathology may be more sensitive than bacteriological tests for detecting AFB in samples collected via bronchoscopy. |
| first_indexed | 2024-03-09T19:56:29Z |
| format | Article |
| id | doaj.art-85b17e98b490411e88f89a13744c26c0 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T19:56:29Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-85b17e98b490411e88f89a13744c26c02023-11-24T00:56:02ZengMDPI AGDiagnostics2075-44182022-03-0112370910.3390/diagnostics12030709Deep-Learning-Aided Detection of Mycobacteria in Pathology Specimens Increases the Sensitivity in Early Diagnosis of Pulmonary Tuberculosis Compared with Bacteriology TestsYoshiaki Zaizen0Yuki Kanahori1Sousuke Ishijima2Yuka Kitamura3Han-Seung Yoon4Mutsumi Ozasa5Hiroshi Mukae6Andrey Bychkov7Tomoaki Hoshino8Junya Fukuoka9Department of Pathology, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8501, JapanDepartment of Pathology, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8501, JapanDepartment of Pathology, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8501, JapanDepartment of Pathology, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8501, JapanDepartment of Pathology, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8501, JapanDepartment of Pathology, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8501, JapanDepartment of Respiratory Medicine, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8501, JapanDepartment of Pathology, Kameda Medical Center, 929 Higashi-cho, Kamogawa, Chiba 296-8602, JapanDivision of Respirology, Neurology and Rheumatology, Department of Medicine, Kurume University School of Medicine, 67 Asahi-machi, Kurume, Fukuoka 830-0011, JapanDepartment of Pathology, Nagasaki University Graduate School of Biomedical Sciences, 1-7-1 Sakamoto, Nagasaki 852-8501, JapanThe histopathological diagnosis of mycobacterial infection may be improved by a comprehensive analysis using artificial intelligence. Two autopsy cases of pulmonary tuberculosis, and forty biopsy cases of undetected acid-fast bacilli (AFB) were used to train AI (convolutional neural network), and construct an AI to support AFB detection. Forty-two patients underwent bronchoscopy, and were evaluated using AI-supported pathology to detect AFB. The AI-supported pathology diagnosis was compared with bacteriology diagnosis from bronchial lavage fluid and the final definitive diagnosis of mycobacteriosis. Among the 16 patients with mycobacteriosis, bacteriology was positive in 9 patients (56%). Two patients (13%) were positive for AFB without AI assistance, whereas AI-supported pathology identified eleven positive patients (69%). When limited to tuberculosis, AI-supported pathology had significantly higher sensitivity compared with bacteriology (86% vs. 29%, <i>p</i> = 0.046). Seven patients diagnosed with mycobacteriosis had no consolidation or cavitary shadows in computed tomography; the sensitivity of bacteriology and AI-supported pathology was 29% and 86%, respectively (<i>p</i> = 0.046). The specificity of AI-supported pathology was 100% in this study. AI-supported pathology may be more sensitive than bacteriological tests for detecting AFB in samples collected via bronchoscopy.https://www.mdpi.com/2075-4418/12/3/709tuberculosisartificial intelligencebronchoscopybronchial lavagemycobacteria |
| spellingShingle | Yoshiaki Zaizen Yuki Kanahori Sousuke Ishijima Yuka Kitamura Han-Seung Yoon Mutsumi Ozasa Hiroshi Mukae Andrey Bychkov Tomoaki Hoshino Junya Fukuoka Deep-Learning-Aided Detection of Mycobacteria in Pathology Specimens Increases the Sensitivity in Early Diagnosis of Pulmonary Tuberculosis Compared with Bacteriology Tests Diagnostics tuberculosis artificial intelligence bronchoscopy bronchial lavage mycobacteria |
| title | Deep-Learning-Aided Detection of Mycobacteria in Pathology Specimens Increases the Sensitivity in Early Diagnosis of Pulmonary Tuberculosis Compared with Bacteriology Tests |
| title_full | Deep-Learning-Aided Detection of Mycobacteria in Pathology Specimens Increases the Sensitivity in Early Diagnosis of Pulmonary Tuberculosis Compared with Bacteriology Tests |
| title_fullStr | Deep-Learning-Aided Detection of Mycobacteria in Pathology Specimens Increases the Sensitivity in Early Diagnosis of Pulmonary Tuberculosis Compared with Bacteriology Tests |
| title_full_unstemmed | Deep-Learning-Aided Detection of Mycobacteria in Pathology Specimens Increases the Sensitivity in Early Diagnosis of Pulmonary Tuberculosis Compared with Bacteriology Tests |
| title_short | Deep-Learning-Aided Detection of Mycobacteria in Pathology Specimens Increases the Sensitivity in Early Diagnosis of Pulmonary Tuberculosis Compared with Bacteriology Tests |
| title_sort | deep learning aided detection of mycobacteria in pathology specimens increases the sensitivity in early diagnosis of pulmonary tuberculosis compared with bacteriology tests |
| topic | tuberculosis artificial intelligence bronchoscopy bronchial lavage mycobacteria |
| url | https://www.mdpi.com/2075-4418/12/3/709 |
| work_keys_str_mv | AT yoshiakizaizen deeplearningaideddetectionofmycobacteriainpathologyspecimensincreasesthesensitivityinearlydiagnosisofpulmonarytuberculosiscomparedwithbacteriologytests AT yukikanahori deeplearningaideddetectionofmycobacteriainpathologyspecimensincreasesthesensitivityinearlydiagnosisofpulmonarytuberculosiscomparedwithbacteriologytests AT sousukeishijima deeplearningaideddetectionofmycobacteriainpathologyspecimensincreasesthesensitivityinearlydiagnosisofpulmonarytuberculosiscomparedwithbacteriologytests AT yukakitamura deeplearningaideddetectionofmycobacteriainpathologyspecimensincreasesthesensitivityinearlydiagnosisofpulmonarytuberculosiscomparedwithbacteriologytests AT hanseungyoon deeplearningaideddetectionofmycobacteriainpathologyspecimensincreasesthesensitivityinearlydiagnosisofpulmonarytuberculosiscomparedwithbacteriologytests AT mutsumiozasa deeplearningaideddetectionofmycobacteriainpathologyspecimensincreasesthesensitivityinearlydiagnosisofpulmonarytuberculosiscomparedwithbacteriologytests AT hiroshimukae deeplearningaideddetectionofmycobacteriainpathologyspecimensincreasesthesensitivityinearlydiagnosisofpulmonarytuberculosiscomparedwithbacteriologytests AT andreybychkov deeplearningaideddetectionofmycobacteriainpathologyspecimensincreasesthesensitivityinearlydiagnosisofpulmonarytuberculosiscomparedwithbacteriologytests AT tomoakihoshino deeplearningaideddetectionofmycobacteriainpathologyspecimensincreasesthesensitivityinearlydiagnosisofpulmonarytuberculosiscomparedwithbacteriologytests AT junyafukuoka deeplearningaideddetectionofmycobacteriainpathologyspecimensincreasesthesensitivityinearlydiagnosisofpulmonarytuberculosiscomparedwithbacteriologytests |