Automated interpretation and analysis of bronchoalveolar lavage fluid. (January 2022)

• Record Type: Journal Article
• Authors: Tao, Yi; Cai, Yu; Fu, Han; Song, Licheng; Xie, Lixin; Wang, Kaifei
• Is Part Of: International journal of medical informatics. Volume 157(2022)
• Publication Date: 2022-01
• Subjects: Deep learning -- Bronchoalveolar lavage fluid -- Artificial intelligence -- Critical care; Medical informatics -- Periodicals; Information science -- Periodicals; Computers -- Periodicals; Medical technology -- Periodicals; Medical Informatics -- Periodicals; Technology, Medical -- Periodicals; Computers; Information science; Medical informatics; Medical technology; Electronic journals; Periodicals; Electronic journals; 610.285
• DOI: 10.1016/j.ijmedinf.2021.104638
• Languages: English
• ISSNs: 1386-5056

Abstract

Highlights: The combination of AI and specimen morphological recognition has a promising future. Bronchoalveolar lavage fluid can reflect the nature of lung diseases. The combination of deep learning and pathologists may outperform operators. Automated analysis of BALF can augment clinical decisions for lung diseases. Abstract: Background: The cytological analysis of bronchoalveolar lavage fluid (BALF) plays an essential role in the differential diagnosis of respiratory diseases. In recent years, deep learning has demonstrated excellent performance in image processing and object recognition. Objectives: We aim to apply deep learning to the automated interpretation and analysis of BALF. Method: Visual images were acquired using an automated biological microscopy platform. We propose a three-step algorithm to automatically interpret BALF cytology based on a convolutional neural network (CNN). The clinical value was evaluated at the patient level. Results: Our model successfully detected most cells in BALF specimens and achieved a sensitivity, precision, and F 1 score of over 0.9 for most cell types. In two tests in the clinical context, the algorithm outperformed experienced practitioners. Conclusion: The program can automatically provide the cytological background of BALF and augment clinical decision-making for clinicians.