Deep-Learning-Aided Detection of Mycobacteria in Pathology Specimens Increases the Sensitivity in Early Diagnosis of Pulmonary Tuberculosis Compared with Bacteriology Tests

• Published in: Diagnostics (Basel) Vol. 12; no. 3; p. 709
• Main Authors: Zaizen, Yoshiaki, Kanahori, Yuki, Ishijima, Sousuke, Kitamura, Yuka, Yoon, Han-Seung, Ozasa, Mutsumi, Mukae, Hiroshi, Bychkov, Andrey, Hoshino, Tomoaki, Fukuoka, Junya
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 14.03.2022; MDPI
• Subjects: Annotations; Artificial intelligence; Autopsies; Bacteriology; Biopsy; Bone marrow; bronchial lavage; Bronchoscopy; Infections; Lymphatic system; Medical records; Microscopy; mycobacteria; Pathology; Patients; Semantics; Software; Tuberculosis; United States > US; Japan; bronchial lavage; mycobacteria; artificial intelligence; tuberculosis; bronchoscopy
• ISSN: 2075-4418; 2075-4418
• DOI: 10.3390/diagnostics12030709

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%, = 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 ( = 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.