2023 World Conference on Lung Cancer (Posters)-EP06.01. Evaluation of Unstained Cytology Slides for Artificial Intelligence Rapid On-Site Evaluation

EP06.01. Evaluation of Unstained Cytology Slides for Artificial Intelligence Rapid On-Site Evaluation - PDF(Slides)

Pdf Summary

The study evaluated the use of unstained cytology slides for artificial intelligence (AI) rapid on-site evaluation (ROSE) in pulmonary cytopathology. ROSE is a technique that increases diagnostic yield and reduces the need for repeat procedures. However, its diagnostic accuracy for pulmonary lesions is only about 75.3%. On the other hand, AI has shown promise in tissue subtyping and quantification in non-pulmonary tissue. The study aimed to determine the clinical value of using AI with unstained cytology specimens.<br /><br />A label-free microscopy system called Pathware was used to digitize unstained cytology specimens collected during pulmonary procedures. The specimens included fine-needle aspirate, touch prep, and bronchial brush specimens. The results showed that the novel microscope was able to highlight nucleated cells by providing endogenous contrast between cellular nucleus and cytoplasm on unstained slides. This allowed for the identification and differentiation of tissue and cell types, even without staining.<br /><br />The use of unstained specimens has several advantages. It allows for the preservation of tissue for additional testing, such as biomarker analysis and special staining for specimens with low cellularity. Additionally, it eliminates the need for uniform processing and staining, which can result in tissue loss. The standardization of slide preparation enables the universal application of AI ROSE.<br /><br />Overall, the study demonstrates the potential of using unstained cytology slides and AI for rapid on-site evaluation in pulmonary cytopathology. This technique allows for quick digitalization of pulmonary specimens in real-time, providing images that aid in the identification and differentiation of tissue and cell types. This advancement could lead to improved diagnostic accuracy and reduced need for repeat procedures, ultimately benefiting patients.

Asset Subtitle

Eric Flenaugh

Meta Tag

Speaker Eric Flenaugh

Topic Pathology & Biomarkers: Artificial Intelligence in Pathology

Keywords

unstained cytology slides

artificial intelligence

rapid on-site evaluation

pulmonary cytopathology

diagnostic accuracy

label-free microscopy system

digitize

tissue and cell types

biomarker analysis

improved diagnostic accuracy