Concordance analysis of AI-powered CD8 quantification and automated CD8 topology with manual histopathological assessment across seven solid tumor types
The degree of CD8+ lymphocyte infiltration into the tumor microenvironment, as well as the distribution of lymphocytes within the tumor and surrounding stroma (inflamed, excluded, or desert immunophenotypes), are key determinants for the potential efficacy of immunotherapy1-3. Thus, accurate characterization of the tumor immune microenvironment is essential. However, manual histopathological assessment of CD8 topology is subject to many challenges, including subjectivity and reproducibility4,5.
We previously developed ML-based models for the identification and quantification of CD8+ lymphocytes6 and topology7 in melanoma. Here, we developed ML-based models for the identification and quantification of CD8+ lymphocytes and CD8 topology classifiers across seven cancer types: urothelial carcinoma (UC), head and neck squamous cell carcinoma (HNSCC), non-small cell lung cancer (NSCLC), gastric cancer (GC), colorectal cancer (CRC), pancreatic cancer (PC), and hepatocellular carcinoma (HCC).
1. Waldman AD, et al. Nat Rev Immunol. 2020; 20:651-668.
2. Peske JD, et al. Adv Cancer Res. 2015; 128:263-307.
3. Ji RR, et al. Cancer Immunol Immunother. 2012;61:1019-1031.
4. Van Bockstal MR, et al. Mod Pathol. 2021; 34:2130-2140.
5. Trimm T, et al. Acta Oncol. 2018; 57:90-94.
6. Glass, B, et al. J Immunother Cancer. 2021; 9(Suppl 2):A859.
7. Lee, G, et al. J Immunother Cancer. 2021; 9(Suppl 2):A420