Evaluation of Virtual Stain Multiplexed CD68 for Macrophage Detection in NSCLC PD-L1 Slides

Elad Arbel, Oded Ben-David, Itay Remer, Amir Ben-Dor, Daniela Rabkin, Sarit Aviel-Ronen, Frederik Aidt, Tine Hagedorn-Olsen, Lars Jacobsen, Kristopher Kersch, Jim Christian, Quyen Nguyen, Anya Tsalenko
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:30-58, 2026.

Abstract

Manual reading of tissue slides by pathologists serves both as a foundation for clinical decision-making and as a source of ground truth for training artificial intelligence (AI) models. However, challenges such as inter-observer variability, limited tissue availability, and complex annotation tasks often compromise reliability and scalability. This study exemplifies a broader trend in pathology: leveraging virtual staining and other AI-based methodologies to address these challenges. We applied virtual stain multiplexing to a challenging annotation task - macrophage identification in non-small cell lung cancer tissue PD-L1 IHC stains, demonstrating its ability to improve pathologist performance and inter-observer agreement. In six challenging regions selected from 49 curated whole slide images, virtual staining significantly increased macrophage detection consistency, with Fleiss\’{kappa} improving from -0.1 to 0.62, and enhanced overall accuracy, with the F1 score increasing from 0.13 to 0.65.These results highlight the potential use of AI-based virtual staining to assist pathologists reading slides, thereby improving consistency, enhancing accuracy, and alleviating the dependence on additional costly staining. Virtual stain multiplexing demonstrates a generalizable approach to improving pathologist performance through measurement-based AI tools, addressing broader needs for reproducibility and efficiency in diagnostic pathology.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-arbel26a, title = {Evaluation of Virtual Stain Multiplexed CD68 for Macrophage Detection in NSCLC PD-L1 Slides}, author = {Arbel, Elad and Ben-David, Oded and Remer, Itay and Ben-Dor, Amir and Rabkin, Daniela and Aviel-Ronen, Sarit and Aidt, Frederik and Hagedorn-Olsen, Tine and Jacobsen, Lars and Kersch, Kristopher and Christian, Jim and Nguyen, Quyen and Tsalenko, Anya}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {30--58}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/arbel26a/arbel26a.pdf}, url = {https://proceedings.mlr.press/v301/arbel26a.html}, abstract = {Manual reading of tissue slides by pathologists serves both as a foundation for clinical decision-making and as a source of ground truth for training artificial intelligence (AI) models. However, challenges such as inter-observer variability, limited tissue availability, and complex annotation tasks often compromise reliability and scalability. This study exemplifies a broader trend in pathology: leveraging virtual staining and other AI-based methodologies to address these challenges. We applied virtual stain multiplexing to a challenging annotation task - macrophage identification in non-small cell lung cancer tissue PD-L1 IHC stains, demonstrating its ability to improve pathologist performance and inter-observer agreement. In six challenging regions selected from 49 curated whole slide images, virtual staining significantly increased macrophage detection consistency, with Fleiss\’{kappa} improving from -0.1 to 0.62, and enhanced overall accuracy, with the F1 score increasing from 0.13 to 0.65.These results highlight the potential use of AI-based virtual staining to assist pathologists reading slides, thereby improving consistency, enhancing accuracy, and alleviating the dependence on additional costly staining. Virtual stain multiplexing demonstrates a generalizable approach to improving pathologist performance through measurement-based AI tools, addressing broader needs for reproducibility and efficiency in diagnostic pathology.} }
Endnote
%0 Conference Paper %T Evaluation of Virtual Stain Multiplexed CD68 for Macrophage Detection in NSCLC PD-L1 Slides %A Elad Arbel %A Oded Ben-David %A Itay Remer %A Amir Ben-Dor %A Daniela Rabkin %A Sarit Aviel-Ronen %A Frederik Aidt %A Tine Hagedorn-Olsen %A Lars Jacobsen %A Kristopher Kersch %A Jim Christian %A Quyen Nguyen %A Anya Tsalenko %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-arbel26a %I PMLR %P 30--58 %U https://proceedings.mlr.press/v301/arbel26a.html %V 301 %X Manual reading of tissue slides by pathologists serves both as a foundation for clinical decision-making and as a source of ground truth for training artificial intelligence (AI) models. However, challenges such as inter-observer variability, limited tissue availability, and complex annotation tasks often compromise reliability and scalability. This study exemplifies a broader trend in pathology: leveraging virtual staining and other AI-based methodologies to address these challenges. We applied virtual stain multiplexing to a challenging annotation task - macrophage identification in non-small cell lung cancer tissue PD-L1 IHC stains, demonstrating its ability to improve pathologist performance and inter-observer agreement. In six challenging regions selected from 49 curated whole slide images, virtual staining significantly increased macrophage detection consistency, with Fleiss\’{kappa} improving from -0.1 to 0.62, and enhanced overall accuracy, with the F1 score increasing from 0.13 to 0.65.These results highlight the potential use of AI-based virtual staining to assist pathologists reading slides, thereby improving consistency, enhancing accuracy, and alleviating the dependence on additional costly staining. Virtual stain multiplexing demonstrates a generalizable approach to improving pathologist performance through measurement-based AI tools, addressing broader needs for reproducibility and efficiency in diagnostic pathology.
APA
Arbel, E., Ben-David, O., Remer, I., Ben-Dor, A., Rabkin, D., Aviel-Ronen, S., Aidt, F., Hagedorn-Olsen, T., Jacobsen, L., Kersch, K., Christian, J., Nguyen, Q. & Tsalenko, A.. (2026). Evaluation of Virtual Stain Multiplexed CD68 for Macrophage Detection in NSCLC PD-L1 Slides. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:30-58 Available from https://proceedings.mlr.press/v301/arbel26a.html.

Related Material