Longitudinal assessment of tumor-infiltrating lymphocytes in primary breast cancer following neoadjuvant radiotherapy

BACKGROUND

Tumor-infiltrating lymphocytes (TILs) have prognostic significance in several cancers, including breast. Despite interest in combining radiotherapy with immunotherapy, little is known about the effect of radiotherapy itself on the tumor-immune microenvironment, including TILs. Here, we interrogated longitudinal dynamics of tumor-infiltrating and systemic lymphocytes in patient samples taken before, during, and after neoadjuvant radiotherapy (NART), from XXX and XXX breast clinical trials.

METHODS

We manually scored stromal TILs (sTILs) from longitudinal tumor samples using standardized guidelines, as well as deep learning-based scores at cell-level (cTIL) and cell- and tissue-level combination analysis (SuperTIL). In parallel, we interrogated absolute lymphocyte counts from routine blood tests at corresponding timepoints during treatment. Exploratory analyses studied the relationship between TILs and pathological complete response (pCR) and long-term outcomes.

RESULTS

Patients receiving NART experienced a significant and uniform decrease in sTILs that did not recover at the time of surgery (P < 0.0001). This lymphodepletive effect was also mirrored in peripheral blood. Our "SuperTIL" deep learning score showed good concordance with manual sTILs, and importantly performed comparably to manual scores in predicting pCR from diagnostic biopsies. Analysis suggested an association between baseline sTILs and pCR, as well as sTILs at surgery and relapse, in patients receiving NART.

CONCLUSIONS

This study provides novel insights into TIL dynamics in the context of NART in breast cancer, and demonstrates the potential for artificial intelligence to assist routine pathology. We have identified trends which warrant further interrogation and have a bearing on future radio-immunotherapy trials.

Self-supervised deep learning for highly efficient spatial immunophenotyping

BACKGROUND

Efficient biomarker discovery and clinical translation depend on the fast and accurate analytical output from crucial technologies such as multiplex imaging. However, reliable cell classification often requires extensive annotations. Label-efficient strategies are urgently needed to reveal diverse cell distribution and spatial interactions in large-scale multiplex datasets.

METHODS

This study proposed Self-supervised Learning for Antigen Detection (SANDI) for accurate cell phenotyping while mitigating the annotation burden. The model first learns intrinsic pairwise similarities in unlabelled cell images, followed by a classification step to map learnt features to cell labels using a small set of annotated references. We acquired four multiplex immunohistochemistry datasets and one imaging mass cytometry dataset, comprising 2825 to 15,258 single-cell images to train and test the model.

FINDINGS

With 1% annotations (18-114 cells), SANDI achieved weighted F1-scores ranging from 0.82 to 0.98 across the five datasets, which was comparable to the fully supervised classifier trained on 1828-11,459 annotated cells (-0.002 to -0.053 of averaged weighted F1-score, Wilcoxon rank-sum test, P = 0.31). Leveraging the immune checkpoint markers stained in ovarian cancer slides, SANDI-based cell identification reveals spatial expulsion between PD1-expressing T helper cells and T regulatory cells, suggesting an interplay between PD1 expression and T regulatory cell-mediated immunosuppression.

INTERPRETATION

By striking a fine balance between minimal expert guidance and the power of deep learning to learn similarity within abundant data, SANDI presents new opportunities for efficient, large-scale learning for histology multiplex imaging data.

FUNDING

This study was funded by the Royal Marsden/ICR National Institute of Health Research Biomedical Research Centre.

Spatial interplay of tissue hypoxia and T-cell regulation in ductal carcinoma in situ

Hypoxia promotes aggressive tumor phenotypes and mediates the recruitment of suppressive T cells in invasive breast carcinomas. We investigated the role of hypoxia in relation to T-cell regulation in ductal carcinoma in situ (DCIS). We designed a deep learning system tailored for the tissue architecture complexity of DCIS, and compared pure DCIS cases with the synchronous DCIS and invasive components within invasive ductal carcinoma cases. Single-cell classification was applied in tandem with a new method for DCIS ductal segmentation in dual-stained CA9 and FOXP3, whole-tumor section digital pathology images. Pure DCIS typically has an intermediate level of colocalization of FOXP3+ and CA9+ cells, but in invasive carcinoma cases, the FOXP3+ (T-regulatory) cells may have relocated from the DCIS and into the invasive parts of the tumor, leading to high levels of colocalization in the invasive parts but low levels in the synchronous DCIS component. This may be due to invasive, hypoxic tumors evolving to recruit T-regulatory cells in order to evade immune predation. Our data support the notion that hypoxia promotes immune tolerance through recruitment of T-regulatory cells, and furthermore indicate a spatial pattern of relocalization of T-regulatory cells from DCIS to hypoxic tumor cells. Spatial colocalization of hypoxic and T-regulatory cells may be a key event and useful marker of DCIS progression.

Artificial intelligence and digital pathology: Opportunities and implications for immuno-oncology

The field of immuno-oncology has expanded rapidly over the past decade, but key questions remain. How does tumour-immune interaction regulate disease progression? How can we prospectively identify patients who will benefit from immunotherapy? Identifying measurable features of the tumour immune-microenvironment which have prognostic or predictive value will be key to making meaningful gains in these areas. Recent developments in deep learning enable big-data analysis of pathological samples. Digital approaches allow data to be acquired, integrated and analysed far beyond what is possible with conventional techniques, and to do so efficiently and at scale. This has the potential to reshape what can be achieved in terms of volume, precision and reliability of output, enabling data for large cohorts to be summarised and compared. This review examines applications of artificial intelligence (AI) to important questions in immuno-oncology (IO). We discuss general considerations that need to be taken into account before AI can be applied in any clinical setting. We describe AI methods that have been applied to the field of IO to date and present several examples of their use.

Impact of early postoperative platelet count on volumetric liver gain and perioperative outcomes after major liver resection

Background

Although perioperative platelet count has been associated with postoperative morbidity and mortality, its impact on liver regeneration has not been examined directly. This study sought to determine the impact of platelet count on liver regeneration after major liver resection using cross-sectional imaging volumetric assessment.

Methods

Patients who underwent major liver resection between 2004 and 2015 and had available data on immediate postoperative platelet count, as well as preoperative and postoperative CT images, were identified retrospectively. Resected liver volume was subtracted from total liver volume (TLV) to define postoperative remnant liver volume (RLVp). The liver regeneration index was defined as the relative increase in liver volume within 2 months ((RLV2m – RLVp)/RLVp, where RLV2m is the remnant liver volume around 2 months after surgery). The association between platelet count, liver regeneration and outcomes was assessed.

Results

A total of 99 patients met the inclusion criteria. Overall, 25 patients (25 per cent) had a low platelet count (less than 150 × 109/l), whereas 74 had a normal–high platelet count (at least 150 × 109/l). Despite having comparable clinicopathological characteristics and RLVp/TLV at surgery (P = 0·903), the relative increase in liver volume within 2 months was considerably lower in the low-platelet group (3·9 versus 16·5 per cent; P = 0·043). Patients with a low platelet count had an increased risk of postoperative complications (72 versus 38 per cent; P = 0·003), longer hospital stay (8 versus 6 days; P = 0·004) and worse median overall survival (24·5 versus 67·3 months; P = 0·005) than those with a normal or high platelet count.

Conclusion

After major liver resection, a low postoperative platelet count was associated with inhibited liver regeneration, as well as worse short- and long-term outcomes. Immediate postoperative platelet count may be an early indicator to identify patients at increased risk of worse outcomes.