Interobserver Agreement of PD-L1/SP142 Immunohistochemistry and Tumor-Infiltrating Lymphocytes (TILs) in Distant Metastases of Triple-Negative Breast Cancer: A Proof-of-Concept Study. A Report on Behalf of the International Immuno-Oncology Biomarker Working Group

Global biomarker trends in triple-negative breast cancer research: a bibliometric analysis

BACKGROUND

Triple-negative breast cancer (TNBC) is defined as breast cancer that is negative for estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor-2 (HER-2) in cancer tissue. The lack of specific biomarkers makes the diagnosis and prognosis of TNBC challenging.

METHOD

A comprehensive literature review and bibliometric analysis was performed using CiteSpace, VOSviewer and Scimago Graphica.

RESULTS

TNBC biomarker research has been growing rapidly in recent years, reflecting the enormous academic interest in TNBC biomarker research. A total of 127 journals published relevant studies and 1749 authors were involved in the field, with developed countries such as the United States, France, and the United Kingdom contributing greatly to the field. Collaborative network analysis found that the research in this field has not yet formed good communication and interaction, and the partnership should be strengthened in the future in order to promote the in-depth development of TNBC biomarker research. A comprehensive analysis of keywords and co-cited literature, etc. found that TNBC biomarker research mainly focuses on immune checkpoint markers, microenvironment-related markers, circulating tumor DNA, metabolic markers, genomics markers and so on. These research hotspots will help to better understand the molecular characteristics and biological processes of TNBC, and provide more accurate biomarkers for its diagnosis, treatment and prognosis.

CONCLUSIONS

The bibliometric analysis highlighted global trends and key directions in TNBC biomarker research. Future developments in TNBC biomarker research are likely to be in the direction of multi-omics integration, meticulous study of the microenvironment, targeted therapeutic biomarkers, application of liquid biopsy, application of machine learning and artificial intelligence, and individualized therapeutic strategies. Young scholars should learn and collaborate across disciplines, pay attention to new technologies and methods, improve their data analysis skills, and continue to follow up on the latest research trends in order to meet the challenges and opportunities in the field of TNBC biomarkers.

Reproducibility of c-Met Immunohistochemical Scoring (Clone SP44) for Non-Small Cell Lung Cancer Using Conventional Light Microscopy and Whole Slide Imaging

Emerging therapies for non-small cell lung cancer targeting c-Met overexpression have recently demonstrated promising results. However, the evaluation of c-Met expression can be challenging. We aimed to study the inter and intraobserver reproducibility of c-Met expression evaluation. One hundred ten cases with non-small cell lung cancer (40 biopsies and 70 surgical specimens) were retrospectively selected in a single laboratory (LPCE) and evaluated for c-Met expression. Six pathologists (4 seniors and 2 juniors) evaluated the H-score and made a 3-tier classification of c-Met expression for all cases, using conventional light microscopy (CLM) and whole slide imaging (WSI). The interobserver reproducibility with CLM gave global Cohen Kappa coefficients (ƙ) ranging from 0.581 (95% CI: 0.364-0.771) to 0.763 (95% CI: 0.58-0.92) using the c-Met 3-tier classification and H-score, respectively. ƙ was higher for senior pathologists and biopsy samples. The interobserver reproducibility with WSI gave a global ƙ ranging from 0.543 (95% CI: 0.33-0.724) to 0.905 (95% CI: 0.618-1) using the c-Met H-score and 2-tier classification (≥25% 3+), respectively. ƙ for intraobserver reproducibility between CLM and WSI ranged from 0.713 to 0.898 for the c-Met H-score and from 0.600 to 0.779 for the c-Met 3-tier classification. We demonstrated a moderate to excellent interobserver agreement for c-Met expression with a substantial to excellent intraobserver agreement between CLM and WSI, thereby supporting the development of digital pathology. However, some factors (scoring method, type of tissue samples, and expertise level) affect reproducibility. Our findings highlight the importance of establishing a consensus definition and providing further training, particularly for inexperienced pathologists, for c-Met immunohistochemistry assessment in clinical practice.

Training pathologists to assess stromal tumour-infiltrating lymphocytes in breast cancer synergises efforts in clinical care and scientific research

A growing body of research supports stromal tumour-infiltrating lymphocyte (TIL) density in breast cancer to be a robust prognostic and predicive biomarker. The gold standard for stromal TIL density quantitation in breast cancer is pathologist visual assessment using haematoxylin and eosin-stained slides. Artificial intelligence/machine-learning algorithms are in development to automate the stromal TIL scoring process, and must be validated against a reference standard such as pathologist visual assessment. Visual TIL assessment may suffer from significant interobserver variability. To improve interobserver agreement, regulatory science experts at the US Food and Drug Administration partnered with academic pathologists internationally to create a freely available online continuing medical education (CME) course to train pathologists in assessing breast cancer stromal TILs using an interactive format with expert commentary. Here we describe and provide a user guide to this CME course, whose content was designed to improve pathologist accuracy in scoring breast cancer TILs. We also suggest subsequent steps to translate knowledge into clinical practice with proficiency testing.

Impact of Decalcification, Cold Ischemia, and Deglycosylation on Performance of Programmed Cell Death Ligand-1 Antibodies With Different Binding Epitopes: Comparison of 7 Clones

Programmed cell death ligand-1 (PD-L1) expression levels in patients' tumors have demonstrated clinical utility across many cancer types and are used to determine treatment eligibility. Several independently developed PD-L1 immunohistochemical (IHC) predictive assays are commercially available and have demonstrated different levels of staining between assays, generating interest in understanding the similarities and differences between assays. Previously, we identified epitopes in the internal and external domains of PD-L1, bound by antibodies in routine clinical use (SP263, SP142, 22C3, and 28-8). Variance in performance of assays utilizing these antibodies, observed following exposure to preanalytical factors such as decalcification, cold ischemia, and duration of fixation, encouraged additional investigation of antibody-binding sites, to understand whether binding site structures/conformations contribute to differential PD-L1 IHC assay staining. We proceeded to further investigate the epitopes on PD-L1 bound by these antibodies, alongside the major clones utilized in laboratory-developed tests (E1L3N, QR1, and 73-10). Characterization of QR1 and 73-10 clones demonstrated that both bind the PD-L1 C-terminal internal domain, similar to SP263/SP142. Our results also demonstrate that under suboptimal decalcification or fixation conditions, the performance of internal domain antibodies is less detrimentally affected than that of external domain antibodies 22C3/28-8. Furthermore, we show that the binding sites of external domain antibodies are susceptible to deglycosylation and conformational structural changes, which directly result in IHC staining reduction or loss. The binding sites of internal domain antibodies were unaffected by deglycosylation or conformational structural change. This study demonstrates that the location and conformation of binding sites, recognized by antibodies employed in PD-L1 diagnostic assays, differ significantly and exhibit differing degrees of robustness. These findings should reinforce the need for vigilance when performing clinical testing with different PD-L1 IHC assays, particularly in the control of cold ischemia and the selection of fixation and decalcification conditions.

Reinventing Nuclear Histo-score Utilizing Inherent Morphologic Cutoffs: Blue-brown Color H-score (BBC-HS)

Immunohistochemistry (IHC) is a testing methodology that is widely used for large number of diagnostic, prognostic, and predictive biomarkers. Although IHC is a qualitative methodology, in addition to threshold-based stratification (positive vs. negative), the increasing levels of expression of some of these biomarkers often lead to more intense staining, which published evidence linked to specific diagnosis, prognosis, and responses to therapy. It is essential that the descriptive thresholds between positive and negative staining, as well as between frequently used graded categories of staining intensity (eg, 1+, 2+, 3+) are standardized and reproducible. Histo-score (H-score) is a frequently used scoring system that utilizes these categories. Our study introduces categorization of the cutoff points between positive and negative results and graded categories of staining intensity for nuclear IHC biomarker assays based on color interaction between hematoxylin and diaminobenzidine (DAB); the Blue-brown Color H-score (BBC-HS). Six cases of diffuse large B-cell lymphoma were stained for a nuclear marker MUM1. The staining was assessed by H-score by 12 readers. Short tutorial and illustrated instructions were provided to readers. The novel scoring system in this study uses the interaction between DAB (DAB, brown stain) and hematoxylin (blue counterstain) to set thresholds between "0" (negative nuclei), "1+" (weakly positive nuclei), "2+" (moderately positive nuclei), and "3+" (strongly positive nuclei). The readers recorded scores for 300 cells. Krippendorff alpha (K-alpha) and intraclass correlation coefficient (ICC) were calculated. We have also assessed if reliability improved when counting the first 100 cells, first 200 cells, and for the total 300 cells using K-alpha and ICC. To assess the performance of each individual reader, the mean H-score and percent positive score (PPS) for each case was calculated, and the bias was calculated between each reader's score and the mean. K-alpha was 0.86 for H-score and 0.76 for PPS. ICC was 0.96 for H-score and 0.92 for PPS. The biases for H-score ranged from -58 to 41, whereas for PPS it ranged from -27% to 33%. Overall, most readers showed very low bias. Two readers were consistently underscoring and 2 were consistently overscoring compared with the mean. For nuclear IHC biomarker assays, our newly proposed cutoffs provide highly reliable/reproducible results between readers for positive and negative results and graded categories of staining intensity using existing morphologic parameters. BBC-HS is easy to teach and is applicable to both human eye and image analysis. BBC-HS application should facilitate the development of new reliable/reproducible scoring schemes for IHC biomarkers.

Inter- and Intra-Observer Agreement of PD-L1 SP142 Scoring in Breast Carcinoma-A Large Multi-Institutional International Study

The assessment of PD-L1 expression in TNBC is a prerequisite for selecting patients for immunotherapy. The accurate assessment of PD-L1 is pivotal, but the data suggest poor reproducibility. A total of 100 core biopsies were stained using the VENTANA Roche SP142 assay, scanned and scored by 12 pathologists. Absolute agreement, consensus scoring, Cohen's Kappa and intraclass correlation coefficient (ICC) were assessed. A second scoring round after a washout period to assess intra-observer agreement was carried out. Absolute agreement occurred in 52% and 60% of cases in the first and second round, respectively. Overall agreement was substantial (Kappa 0.654-0.655) and higher for expert pathologists, particularly on scoring TNBC (6.00 vs. 0.568 in the second round). The intra-observer agreement was substantial to almost perfect (Kappa: 0.667-0.956), regardless of PD-L1 scoring experience. The expert scorers were more concordant in evaluating staining percentage compared with the non-experienced scorers (R² = 0.920 vs. 0.890). Discordance predominantly occurred in low-expressing cases around the 1% value. Some technical reasons contributed to the discordance. The study shows reassuringly strong inter- and intra-observer concordance among pathologists in PD-L1 scoring. A proportion of low-expressors remain challenging to assess, and these would benefit from addressing the technical issues, testing a different sample and/or referring for expert opinions.

Concordance of PD-L1 expression in triple-negative breast cancers in Chinese patients: A retrospective and pathologist-based study

OBJECTIVE

To compare the expression of programmed cell death ligand 1 (PD-L1) in different paraffin blocks from the same triple-negative breast cancers (TNBC) specimen and between matched primary tumors and lymph node metastases (LNMets). We also aim to determine the interobserver agreement between pathologists trained on PD-L1 (SP142) assay in assessing TNBC.

METHODS

426 histologically confirmed TNBC cases, in which 85 have LNMets, were included in this study. A PD-L1 (SP142) assay was used to identify PD-L1 expression on tumor infiltrating immune cells (IC) and also on tumor cells (TC) in primary tumors and LNMets of TNBC by two trained pathologists. PD-L1 scoring and assessment were based on criteria in IMpassion 130 trial criteria. Concordance of PD-L1 expression in TNBC were analyzed using Kappa-test and assessed by the Kappa value.

RESULTS

Prevalence of positive PD-L1 expression (PD-L1 +) on tumor-infiltrating immune cells (PD-L1 IC+) (IC≥1%) in LNMets (49.4%) was higher than in the matched primary tumors (38.9%). Concordance of PD-L1 expression on IC between the two paraffin blocks from the same primary tumor specimen was substantial (P < 0.000, Kappa = 0.627) and was identified in 83.1% (108/130) of the selected cases. For TNBC cases with matched primary and LNMets blocks, the concordance of PD-L1IC scoring between the two blocks was moderate (P < 0.000, Kappa = 0.434). Interobserver agreement of PD-L1 assessment was 78.2% (P < 0.000, Kappa = 0.567) in primary tumors and 61.4% (P < 0.000, Kappa = 0.253) in the matched LNets.

CONCLUSION

Substantial intratumor concordance of PD-L1 scoring of the primary tumors in TNBC patients was determined, implying that immunohistochemically detection using one representative block of the primary tumor should be enough to assign the expression status of PD-L1 in clinical practice. The prevalence of PD-L1 + in lymph node metastases (LNMets) was higher than in the matched primary tumors, implying that PD-L1 detection in LNMets may provide additional PD-L1 expression information, especially in TNBC cases with PD-L1- in the matched primary breast tumors. Interobserver agreement of PD-L1 scoring in primary tumors was moderate while only fair in LNMets, implying that the additional training for PD-L1 assessment of TNBC LNMets specimens is recommended to enhance interobserver agreement.

DATA AVAILABILITY

The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.

Predictive Biomarkers of Response to Neoadjuvant Chemotherapy in Breast Cancer: Current and Future Perspectives for Precision Medicine

Pathological complete response (pCR) after neoadjuvant chemotherapy in patients with early breast cancer is correlated with better survival. Meanwhile, an expanding arsenal of post-neoadjuvant treatment strategies have proven beneficial in the absence of pCR, leading to an increased use of neoadjuvant systemic therapy in patients with early breast cancer and the search for predictive biomarkers of response. The better prediction of response to neoadjuvant chemotherapy could enable the escalation or de-escalation of neoadjuvant treatment strategies, with the ultimate goal of improving the clinical management of early breast cancer. Clinico-pathological prognostic factors are currently used to estimate the potential benefit of neoadjuvant systemic treatment but are not accurate enough to allow for personalized response prediction. Other factors have recently been proposed but are not yet implementable in daily clinical practice or remain of limited utility due to the intertumoral heterogeneity of breast cancer. In this review, we describe the current knowledge about predictive factors for response to neoadjuvant chemotherapy in breast cancer patients and highlight the future perspectives that could lead to the better prediction of response, focusing on the current biomarkers used for clinical decision making and the different gene signatures that have recently been proposed for patient stratification and the prediction of response to therapies. We also discuss the intratumoral phenotypic heterogeneity in breast cancers as well as the emerging techniques and relevant pre-clinical models that could integrate this biological factor currently limiting the reliable prediction of response to neoadjuvant systemic therapy.

Development of Training Materials for Pathologists to Provide Machine Learning Validation Data of Tumor-Infiltrating Lymphocytes in Breast Cancer

Simple Summary

The High Throughput Truthing project aims to develop a dataset of stromal tumor-infiltrating lymphocytes (sTILs) density evaluations in hematoxylin and eosin-stained invasive breast cancer specimens fit for a regulatory purpose. After completion of the pilot study, the analysis demonstrated inconsistencies and gaps in the provided training to pathologists. Select regions of interest (ROIs) were reviewed by an expert panel, who provided annotations and commentary on the challenges of the sTILs assessment. We used these annotations to develop a training document and reference standard for new training materials. These materials will train crowd-sourced pathologists to help create an algorithm validation dataset and contribute to sTILs evaluations in clinical practice.

Abstract

The High Throughput Truthing project aims to develop a dataset for validating artificial intelligence and machine learning models (AI/ML) fit for regulatory purposes. The context of this AI/ML validation dataset is the reporting of stromal tumor-infiltrating lymphocytes (sTILs) density evaluations in hematoxylin and eosin-stained invasive breast cancer biopsy specimens. After completing the pilot study, we found notable variability in the sTILs estimates as well as inconsistencies and gaps in the provided training to pathologists. Using the pilot study data and an expert panel, we created custom training materials to improve pathologist annotation quality for the pivotal study. We categorized regions of interest (ROIs) based on their mean sTILs density and selected ROIs with the highest and lowest sTILs variability. In a series of eight one-hour sessions, the expert panel reviewed each ROI and provided verbal density estimates and comments on features that confounded the sTILs evaluation. We aggregated and shaped the comments to identify pitfalls and instructions to improve our training materials. From these selected ROIs, we created a training set and proficiency test set to improve pathologist training with the goal to improve data collection for the pivotal study. We are not exploring AI/ML performance in this paper. Instead, we are creating materials that will train crowd-sourced pathologists to be the reference standard in a pivotal study to create an AI/ML model validation dataset. The issues discussed here are also important for clinicians to understand about the evaluation of sTILs in clinical practice and can provide insight to developers of AI/ML models.