Understanding response to immunotherapy requires accurate and complete characterization of tumor-associated immune cells in order to fully contextualize the immuno-oncology biomarker expression. Current standard practices surrounding enumeration of biomarker-positive immune cells using image analysis necessitate a duallabeling approach combining the biomarker of interest and immune cell identification assays.
Machine Learning (ML) may be used to distinguish different tissue types in a biopsy (e.g. tumor vs. non-tumor), or to identify different cell types (e.g. macrophages vs other cells). A ML algorithm obtains statistics for a specific tissue class or cell type based on a training set, given by “ground truth” examples. The algorithm then generalizes
from the given examples to “learn” the ability to find the tissue or cell type on the rest of the digital scan of the tissue slide, or other scans.
Here we specifically describe ML methods for macrophage identification in digital scans of non-small cell lung carcinoma (NSCLC) tissue slides. In Method 1, the ML algorithm was trained by pathologist assistance. In Method 2, the ML algorithm was trained by immunofluorescence assistance. While both methods enable quantification of macrophages without the routine use of immunohistochemistry (IHC) to label themacrophages, the two methods are distinct and will be described separately.