HER2 quantitative continuous scoring for accurate patient selection in HER2 negative trastuzumab deruxtecan treated breast cancer.

Many targeted cancer therapies rely on biomarkers assessed by scoring of immunohistochemically (IHC)-stained tissue, which is subjective, semiquantitative, and does not account for expression heterogeneity. We describe an image analysis-based method for quantitative continuous scoring (QCS) of digital whole-slide images acquired from baseline human epidermal growth factor receptor 2 (HER2) IHC-stained breast cancer tissue. Candidate signatures for patient stratification using QCS of HER2 expression on subcellular compartments were identified, addressing the spatial distribution of tumor cells and tumor-infiltrating lymphocytes. Using data from trastuzumab deruxtecan-treated patients with HER2-positive and HER2-negative breast cancer from a phase 1 study (NCT02564900; DS8201-A-J101; N = 151), QCS-based patient stratification showed longer progression-free survival (14.8 vs 8.6 months) with higher prevalence of patient selection (76.4 vs 56.9%) and a better cross-validated log-rank p value (0.026 vs 0.26) than manual scoring based on the American Society of Clinical Oncology / College of American Pathologists guidelines. QCS-based features enriched the HER2-negative subgroup by correctly predicting 20 of 26 responders.

Spatial heterogeneity of cancer associated protein expression in immunohistochemically stained images as an improved prognostic biomarker.

The identification of new tumor biomarkers for patient stratification before therapy, for monitoring of disease progression, and for characterization of tumor biology plays a crucial role in cancer research. The status of these biomarkers is mostly scored manually by a pathologist and such scores typically, do not consider the spatial heterogeneity of the protein's expression in the tissue. Using advanced image analysis methods, marker expression can be determined quantitatively with high accuracy and reproducibility on a per-cell level. To aggregate such per-cell marker expressions on a patient level, the expression values for single cells are usually averaged for the whole tissue. However, averaging neglects the spatial heterogeneity of the marker expression in the tissue. We present two novel approaches for quantitative scoring of spatial marker expression heterogeneity. The first approach is based on a co-occurrence analysis of the marker expression in neighboring cells. The second approach accounts for the local variability of the protein's expression by tiling the tissue with a regular grid and assigning local spatial heterogeneity phenotypes per tile. We apply our novel scores to quantify the spatial expression of four different membrane markers, i.e., HER2, CMET, CD44, and EGFR in immunohistochemically (IHC) stained tissue sections of colorectal cancer patients. We evaluate the prognostic relevance of our spatial scores in this cohort and show that the spatial heterogeneity scores clearly outperform the marker expression average as a prognostic factor (CMET: p-value=0.01 vs. p-value=0.3).

Domain Adaptation-Based Deep Learning for Automated Tumor Cell (TC) Scoring and Survival Analysis on PD-L1 Stained Tissue Images.

We report the ability of two deep learning-based decision systems to stratify non-small cell lung cancer (NSCLC) patients treated with checkpoint inhibitor therapy into two distinct survival groups. Both systems analyze functional and morphological properties of epithelial regions in digital histopathology whole slide images stained with the SP263 PD-L1 antibody. The first system learns to replicate the pathologist assessment of the Tumor Cell (TC) score with a cut-point for positivity at 25% for patient stratification. The second system is free from assumptions related to TC scoring and directly learns patient stratification from the overall survival time and event information. Both systems are built on a novel unpaired domain adaptation deep learning solution for epithelial region segmentation. This approach significantly reduces the need for large pixel-precise manually annotated datasets while superseding serial sectioning or re-staining of slides to obtain ground truth by cytokeratin staining. The capacity of the first system to replicate the TC scoring by pathologists is evaluated on 703 unseen cases, with an addition of 97 cases from an independent cohort. Our results show Lin's concordance values of 0.93 and 0.96 against pathologist scoring, respectively. The ability of the first and second system to stratify anti-PD-L1 treated patients is evaluated on 151 clinical samples. Both systems show similar stratification powers (first system: HR = 0.539, p = 0.004 and second system: HR = 0.525, p = 0.003) compared to TC scoring by pathologists (HR = 0.574, p = 0.01).

Deep Semi Supervised Generative Learning for Automated Tumor Proportion Scoring on NSCLC Tissue Needle Biopsies.

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 by a pathologist of the percentage (tumor proportional scoring or TPS) of tumor cells showing PD-L1 staining. 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 TPS 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.