Deep Semi Supervised Generative Learning for Automated PD-L1 Tumor Cell Scoring on NSCLC Tissue Needle Biopsies
This addresses the need for objective and consistent biomarker quantification in cancer diagnostics, though it is incremental as it applies existing semi-supervised methods to a specific medical imaging task.
The paper tackles the problem of subjective and variable visual scoring of PD-L1 expression in NSCLC biopsies by proposing a deep learning solution for automated scoring, achieving concordance with pathologist visual scores on unseen slides while ensuring repeatability and objectivity.
The level of PD-L1 expression in immunohistochemistry (IHC) assays is a key biomarker for the identification of Non-Small-Cell-Lung-Cancer (NSCLC) patients that may respond to anti PD-1/PD-L1 treatments. The quantification of PD-L1 expression currently includes the visual estimation of a Tumor Cell (TC) score by a pathologist and consists of evaluating the ratio of PD-L1 positive and PD-L1 negative tumor cells. Known challenges like differences in positivity estimation around clinically relevant cut-offs and sub-optimal quality of samples makes visual scoring tedious and subjective, yielding a scoring variability between pathologists. In this work, we propose a novel deep learning solution that enables the first automated and objective scoring of PD-L1 expression in late stage NSCLC needle biopsies. To account for the low amount of tissue available in biopsy images and to restrict the amount of manual annotations necessary for training, we explore the use of semi-supervised approaches against standard fully supervised methods. We consolidate the manual annotations used for training as well the visual TC scores used for quantitative evaluation with multiple pathologists. Concordance measures computed on a set of slides unseen during training provide evidence that our automatic scoring method matches visual scoring on the considered dataset while ensuring repeatability and objectivity.