CD8+ T cell infiltration in breast and colon cancer: A histologic and statistical analysis

Abstract

The prevalence of cytotoxic tumor infiltrating lymphocytes (TILs) has demonstrated prognostic value in multiple tumor types. In particular, CD8 counts (in combination with CD3 and CD45RO) have been shown to be superior to traditional UICC staging in colon cancer patients and higher total CD8 counts have been associated with better survival in breast cancer patients. However, immune infiltrate heterogeneity can lead to potentially significant misrepresentations of marker prevalence in routine histologic sections. We examined step sections of breast and colorectal cancer samples for CD8+ T cell prevalence by standard chromogenic immunohistochemistry to determine marker variability and inform practice of T cell biomarker assessment in formalin-fixed, paraffin-embedded (FFPE) tissue samples. Stained sections were digitally imaged and CD8+ lymphocytes within defined regions of interest (ROI) including the tumor and surrounding stroma were enumerated. Statistical analyses of CD8+ cell count variability using a linear model/ANOVA framework between patients as well as between levels within a patient sample were performed. Our results show that CD8+ T-cell distribution is highly homogeneous within a standard tissue sample in both colorectal and breast carcinomas. As such, cytotoxic T cell prevalence by immunohistochemistry on a single level or even from a subsample of biopsy fragments taken from that level can be considered representative of cytotoxic T cell infiltration for the entire tumor section within the block. These findings support the technical validity of biomarker strategies relying on CD8 immunohistochemistry.

Fig 1. Sample workflow for immunohistochemistry and image analysis.

Tumor blocks were sectioned and levels for CD8 immunohistochemistry taken at 25 μm intervals. Stained slides were scanned and the tumor area and immediately adjacent stroma was manually designated by a pathologist on all slides. All nucleated cells as well as CD8+ cells within the defined area were identified and counted by image analysis. Simulated core biopsies were identified by creating a grid of rectangular regions over the entire image, each approx. 2mm². in size. Rectangular regions that overlapped with at least 0.7 mm² of manually identified region were analyzed. Scale bar illustrated in “Level 1” panel equals 500 μm.

Fig 2. CD8 IHC repeated measures staining results for 25 breast (red) and colorectal (blue) carcinoma samples.

Each tumor block was sectioned 8 times or until the sample was exhausted.

Fig 3. Slide-level biopsy simulation results.

(A) Percent of times over 1000 rounds of simulations that the values obtained from sampling increased numbers of biopsy fragments produced a result within 1SD of the mean CD8 staining for a given slide. Calculating the mean over increased numbers of biopsies led to better estimates of the mean, while calculating maxima over the sample biopsies led to overestimates of a slide’s CD8 levels. Samples are sorted by increasing performance in terms of being able to produce an estimate within 1SD of total CD8 staining for that slide. (B) Estimates of the standard deviation of the difference between the mean or maximum of selected core biopsies and the mean or maximum of the out-of-bag or unselected cores on a given slide. Increased sampling leads to improvements in variability for when using means but not when using order statistics. (C) Estimates of the standard deviation of the difference between the mean or maximum of selected core biopsies and the mean or maximum of the out-of-bag or unselected cores on a given slide as a function of the mean CD8 percent positive staining for a slide. Loess fits are used to highlight mean performance over the observed dynamic range on both the log₂ and observed percent staining scales. Increased sampling leads to improvements in variability when using means but not when using order statistics.

Fig 4. Block-level biopsy simulation results.

(A) Percent of times over 1000 rounds of simulations that the values obtained from sampling increased numbers of biopsy fragments produced a result within 1SD of the mean CD8 staining for an entire tumor block. Calculating the mean over increased numbers of fragments led to better estimates of the mean, while calculating maxima over the sample biopsies led to overestimates of a sample’s CD8 levels. Samples are sorted by increasing performance in terms of being able to produce an estimate within 1SD of total CD8 staining for that tumor block. (B) Estimates of the standard deviation of the difference between the mean or maximum of selected core biopsies and the mean or maximum of the out-of-bag or unselected cores for a given tumor sample. Increased sampling leads to improvements in variability for when using means but not when using order statistics. (C) Estimates of the standard deviation of the difference between the mean or maximum of selected core biopsies and the mean or maximum of the out-of-bag or unselected cores for a given tumor sample as a function of the mean CD8 percent positive staining for that block. Loess fits are used to highlight mean performance over the observed dynamic range on both the log₂ and observed percent staining scales. Increased sampling leads to improvements in variability when using means but not when using order statistics.

Fig 5. Simulation receiver-operator characteristic (ROC) curves.

With increased sampling, there is increased performance of the CD8 IHC assay to classify as positive or negative for a given cut-off (different colors) when using the means of different numbers of sampled biopsies (left) and decreased performance when using maxima (right). Over the set of cut-offs (1%, 2%, 5%, 10%), the analysis treated the mean CD8 staining as the true intensity against which the results of the subsamples of biopsy fragments were evaluated. Similar results were obtained when benchmarking the staining result from core biopsies against the mean staining of the entire block (data not shown).