EP06.01-04 Deep Learning Based Quality Assessment of DAPI Stained Nuclei Images Obtained from Routine FISH Test for Lung Cancer

Fluorescent in situ hybridization (FISH) is a useful tool for identifying genetic abnormalities in lung cancer patients, which can inform treatment decisions and improve outcomes. DAPI staining is frequently used as a counterstain in FISH experiments to visualize cell nuclei. Because of the variability of tumor cell quality and the admixture of non-tumor cells, the role of DAPI in assisting the identification of the tumor cells being analyzed is critical. Here, we develop a deep learning algorithm that can accurately detect images have high quality lung cancer DAPI images for helping pathologist interpretation of FISH.