Automated Tumour Recognition and Digital Pathology Scoring Unravels New Role for PD-L1 in Predicting Good Outcome in ER-/HER2+ Breast Cancer

Abstract

The role of PD-L1 as a prognostic and predictive biomarker is an area of great interest. However, there is a lack of consensus on how to deliver PD-L1 as a clinical biomarker. At the heart of this conundrum is the subjective scoring of PD-L1 IHC in most studies to date. Current standard scoring systems involve separation of epithelial and inflammatory cells and find clinical significance in different percentages of expression, e.g., above or below 1%. Clearly, an objective, reproducible and accurate approach to PD-L1 scoring would bring a degree of necessary consistency to this landscape. Using a systematic comparison of technologies and the application of QuPath, a digital pathology platform, we show that high PD-L1 expression is associated with improved clinical outcome in Triple Negative breast cancer in the context of standard of care (SoC) chemotherapy, consistent with previous findings. In addition, we demonstrate for the first time that high PD-L1 expression is also associated with better outcome in ER- disease as a whole including HER2+ breast cancer. We demonstrate the influence of antibody choice on quantification and clinical impact with the Ventana antibody (SP142) providing the most robust assay in our hands. Through sampling different regions of the tumour, we show that tumour rich regions display the greatest range of PD-L1 expression and this has the most clinical significance compared to stroma and lymphoid rich areas. Furthermore, we observe that both inflammatory and epithelial PD-L1 expression are associated with improved survival in the context of chemotherapy. Moreover, as seen with PD-L1 inhibitor studies, a low threshold of PD-L1 expression stratifies patient outcome. This emphasises the importance of using digital pathology and precise biomarker quantitation to achieve accurate and reproducible scores that can discriminate low PD-L1 expression.

Figure 1

(a) Map of the Horizon Discovery PDL1 Reference Standard panel demonstrating negative, low, medium, and strong protein expression (Data provided by Horizon Discovery). (b) Histogram of IHC-determined protein and RNAScope-determined mRNA expression of PDL1 in the Horizon Discovery custom cell line panel. IHC was performed with 3 different antibodies (Abcam (28-8), Spring Bioscience (SP142), and Cell Signalling (405.9A11)) and on the Bondmax and Benchmark automated platforms. IHC was quantified using the QuPath software. RNAScope was quantified using SpotStudio (ACD).

Figure 2

(a) Areas of tumour cores targeted for use in subsequent tissue microarrays. Where sufficient material was available, three cores of tissue were taken from three areas, (1) enriched with tumour epithelium (green), (2) enriched with tumour stroma, (<50% tumour epithelium) (black), and (3) enriched for lymphoid infiltrates within the tumour (red). (b) (i) Representative cores ranging from absent to high PD-L1 protein expression assessed by IHC using SP142, as indicated. Both raw immunohistochemistry images and QuPath cell detection masks are shown. A magnified region is shown in an exploded view. The key displays the QuPath cell classifier on the mask images. (ii) Displays PD-L1 expression identified by RNAscope. Cores ranging from absent to high PD-L1 RNAScope expression, as indicated. A magnified region is shown in an exploded view.

Figure 3

Kaplan Meier Plots of relapse free survival stratified based on PD-L1 expression above or below 1% as determined by the (i) SP142 or (ii) by RNAScope.

Figure 4

(a) Box and whisker plot showing the range min. to max. of PD-L1 expression (determined by SP142) in the three different tumour core types: stroma rich (TS), tumour rich (T), and lymphoid rich (TL). (b) Kaplan Meier Plots of relapse free survival stratified based on PD-L1 expression above or below 1% in the three different core types (i)TS, (ii)T, and (iii) TL. (c) (i) Box and whisker plot showing the range of min. to max. and (ii) the correlation between tumour and stroma derived PD-L1 expression within the tumour rich (T) cores. (d) Kaplan Meier Plots of relapse free survival stratified based on (i) tumour or (ii) stroma derived PD-L1 expression above or below 1%.

Figure 5

(a) Scatter plot of percentage stoma TILs (median and interquartile range indicated) in cases determined to be low (<1%) or high (>1%) for PD-L1 expression (whole core assessment) in the tumour rich cores. (b) Intratumoural (i) CD4 and (ii) CD8 expression in PD-L1 low (<1%) and high (>1%) samples. (c) Box and whisker plots of gene expression derived (i) M1/M2 signature scores and (ii) CD68/CD8 ratio in PD-L1 low (<1%) and high (>1%) samples.

Figure 6

(a) Kaplan Meier Plots of relapse free survival stratified based on PD-L1 expression above or below 1% in breast cancer as a whole. (b) Box and whisker plot showing the range (min. to max.) of PD-L1 expression in the different subtypes of breast cancer. Kaplan Meier Plots of relapse free survival stratified based on PD-L1 expression above or below 1% in (c) TNBC, (d) Luminal A, (e) Luminal B/HER2 negative, (f) Luminal B/HER2 positive, (g) HER2 positive, and (h) ER negative breast cancer.