Related Experiment Video
Updated: Jan 12, 2026
Bronchoalveolar Lavage of Murine Lungs to Analyze Inflammatory Cell Infiltration
Published on: May 4, 2017
Bronchoalveolar Lavage as a Candidate for Artificial Intelligence Integration: Insights into Differential Cell Count
Josua Schaefer1, Fabienne Hagmann1, Stefan Reinhard1
1Institute of Tissue Medicine and Pathology, University of Bern, Bern, Switzerland.
Insights
AI algorithms show promise in analyzing bronchoalveolar lavage (BAL) samples, improving cell count accuracy and Golde score assessment for pulmonary disease diagnosis. This digital cytology approach reduces variability compared to manual methods.
Area of Science:
- Digital cytology
- Artificial intelligence in diagnostics
- Pulmonary medicine
Background:
- Bronchoalveolar lavage (BAL) is crucial for diagnosing lung diseases.
- Manual cell counting in BAL is prone to errors and variability.
- Assessing iron-laden macrophages (Golde score) is a key diagnostic metric.
Purpose of the Study:
- To develop and validate AI algorithms for automated cell counting in BAL.
- To assess the AI's accuracy in calculating the Golde score.
- To improve diagnostic accuracy and reduce interobserver variability in BAL analysis.
Main Methods:
- Training AI algorithms on internal datasets of Hemacolor, Papanicolaou, and iron-stained BAL smears.
- Validating AI performance on independent sets of stained slides.
- Comparing AI-derived cell counts and Golde scores against manual cytological assessments.
Main Results:
- AI algorithms demonstrated fair to excellent correlation with manual counts for most cell types across staining methods.
- High accuracy was observed for macrophages and neutrophils.
- The automated Golde score calculation showed a mean deviation of 19 points from manual evaluation.
Conclusions:
- AI-supported methods offer potential for accurate BAL analysis in diagnostic cytology.
- The study highlights the benefits of AI for cell recognition and Golde score calculation.
- Further research is recommended to integrate digital cytology into clinical practice for conventional smears.
Introduction:
Bronchoalveolar lavage (BAL) brings an important contribution in diagnosing pulmonary diseases. The analysis of standard cell distribution and the assessment of iron-laden macrophages (the Golde score) are integral to standard medical reports. However, the traditional cytological method of manual cell counting is subject to interobserver variability and staining quality issues.
Methods:
To address these issues, we trained AI-based algorithms to enhance the accuracy of differentiated cell counts of macrophages, lymphocytes, neutrophils, eosinophils, ciliated cells, and squamous cells as well as the Golde score, which assesses the hemosiderin content in macrophages. For this purpose, we assembled an internal sample cohort with 16 Hemacolor, 16 Papanicolaou, and 5 iron-stained smears. For validation, we used 10 slides each of Papanicolaou and Hemacolor staining and 5 with iron staining.
Results:
The algorithm achieved fair to excellent correlation compared to two cytologists: For Papanicolaou staining, the correlations were macrophages 0.96, lymphocytes 0.98, neutrophil granulocytes 0.99, eosinophils 0.58, ciliated cells 0.61, squamous cells 0.31. In Hemacolor staining the correlations were macrophages 0.97, lymphocytes 0.92, neutrophils 0.99, eosinophils 0.99, ciliated cells 0.58, squamous cells -0.145. The automated Golde score calculation deviated on average by 19 points from the manual evaluation.
Conclusion:
The study demonstrates the potential of AI-supported methods for BAL analysis in diagnostic cytology. The high accuracy in recognizing cell types and calculating the Golde score underlines the benefits of expanding the training data for broader clinical applications. Further research is encouraged to support the use of digital cytology on conventional smears in clinical practice.
