The artificial intelligence-based model ANORAK improves histopathological grading of lung adenocarcinoma

The introduction of the International Association for the Study of Lung Cancer grading system has furthered interest in histopathological grading for risk stratification in lung adenocarcinoma. Complex morphology and high intratumoral heterogeneity present challenges to pathologists, prompting the development of artificial intelligence (AI) methods. Here we developed ANORAK (pyrAmid pooliNg crOss stReam Attention networK), encoding multiresolution inputs with an attention mechanism, to delineate growth patterns from hematoxylin and eosin-stained slides. In 1,372 lung adenocarcinomas across four independent cohorts, AI-based grading was prognostic of disease-free survival, and further assisted pathologists by consistently improving prognostication in stage I tumors. Tumors with discrepant patterns between AI and pathologists had notably higher intratumoral heterogeneity. Furthermore, ANORAK facilitates the morphological and spatial assessment of the acinar pattern, capturing acinus variations with pattern transition. Collectively, our AI method enabled the precision quantification and morphology investigation of growth patterns, reflecting intratumoral histological transitions in lung adenocarcinoma.

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 Positioning of Immune Hotspots Reflects the Interplay between B and T Cells in Lung Squamous Cell Carcinoma

Beyond tertiary lymphoid structures, a significant number of immune-rich areas without germinal center-like structures are observed in non-small cell lung cancer. Here, we integrated transcriptomic data and digital pathology images to study the prognostic implications, spatial locations, and constitution of immune rich areas (immune hotspots) in a cohort of 935 patients with lung cancer from The Cancer Genome Atlas. A high intratumoral immune hotspot score, which measures the proportion of immune hotspots interfacing with tumor islands, was correlated with poor overall survival in lung squamous cell carcinoma but not in lung adenocarcinoma. Lung squamous cell carcinomas with high intratumoral immune hotspot scores were characterized by consistent upregulation of B-cell signatures. Spatial statistical analyses conducted on serial multiplex IHC slides further revealed that only 4.87% of peritumoral immune hotspots and 0.26% of intratumoral immune hotspots were tertiary lymphoid structures. Significantly lower densities of CD20+CXCR5+ and CD79b+ B cells and less diverse immune cell interactions were found in intratumoral immune hotspots compared with peritumoral immune hotspots. Furthermore, there was a negative correlation between the percentages of CD8+ T cells and T regulatory cells in intratumoral but not in peritumoral immune hotspots, with tertiary lymphoid structures excluded. These findings suggest that the intratumoral immune hotspots reflect an immunosuppressive niche compared with peritumoral immune hotspots, independent of the distribution of tertiary lymphoid structures. A balance toward increased intratumoral immune hotspots is indicative of a compromised antitumor immune response and poor outcome in lung squamous cell carcinoma.

SIGNIFICANCE

Intratumoral immune hotspots beyond tertiary lymphoid structures reflect an immunosuppressive microenvironment, different from peritumoral immune hotspots, warranting further study in the context of immunotherapies.

Bridging clinic and wildlife care with AI-powered pan-species computational pathology

Cancers occur across species. Understanding what is consistent and varies across species can provide new insights into cancer initiation and evolution, with significant implications for animal welfare and wildlife conservation. We build a pan-species cancer digital pathology atlas (panspecies.ai) and conduct a pan-species study of computational comparative pathology using a supervised convolutional neural network algorithm trained on human samples. The artificial intelligence algorithm achieves high accuracy in measuring immune response through single-cell classification for two transmissible cancers (canine transmissible venereal tumour, 0.94; Tasmanian devil facial tumour disease, 0.88). In 18 other vertebrate species (mammalia = 11, reptilia = 4, aves = 2, and amphibia = 1), accuracy (range 0.57-0.94) is influenced by cell morphological similarity preserved across different taxonomic groups, tumour sites, and variations in the immune compartment. Furthermore, a spatial immune score based on artificial intelligence and spatial statistics is associated with prognosis in canine melanoma and prostate tumours. A metric, named morphospace overlap, is developed to guide veterinary pathologists towards rational deployment of this technology on new samples. This study provides the foundation and guidelines for transferring artificial intelligence technologies to veterinary pathology based on understanding of morphological conservation, which could vastly accelerate developments in veterinary medicine and comparative oncology.

Immune selection determines tumor antigenicity and influences response to checkpoint inhibitors

In cancer, evolutionary forces select for clones that evade the immune system. Here we analyzed >10,000 primary tumors and 356 immune-checkpoint-treated metastases using immune dN/dS, the ratio of nonsynonymous to synonymous mutations in the immunopeptidome, to measure immune selection in cohorts and individuals. We classified tumors as immune edited when antigenic mutations were removed by negative selection and immune escaped when antigenicity was covered up by aberrant immune modulation. Only in immune-edited tumors was immune predation linked to CD8 T cell infiltration. Immune-escaped metastases experienced the best response to immunotherapy, whereas immune-edited patients did not benefit, suggesting a preexisting resistance mechanism. Similarly, in a longitudinal cohort, nivolumab treatment removes neoantigens exclusively in the immunopeptidome of nonimmune-edited patients, the group with the best overall survival response. Our work uses dN/dS to differentiate between immune-edited and immune-escaped tumors, measuring potential antigenicity and ultimately helping predict response to treatment.

Abstract 5055: Precise segmentation of growth patterns in TRACERx lung adenocarcinoma

Histologic growth patterns are associated with patient prognosis, thus recognized as an important part of the WHO classification in lung adenocarcinoma (Travis et al. 2015, Moreira et al., 2020). The wide spectrum of growth patterns proves challenging for reproducible and quantitative scoring. Currently, scoring is based on manual identification of the predominant pattern and percentages of patterns in routine diagnostic slides. The lack of an automated method also limits our ability to investigate the immune microenvironment of growth patterns.

To overcome the above challenges, we present a deep learning method, Pyramid Stream Networks, to precisely segment growth patterns at pixel level. Unlike existing methods, the proposed method captures different spatial scales of the histology information by novel attention strategies at different learning stages. This problem-oriented design yields precise boundaries for each pattern, enabling the investigation of growth pattern heterogeneity, and the relationship with tumor microenvironment components.

Experiments were conducted on 49 haematoxylin and eosin whole slide images (WSIs) from TRACERx 100 cohort (AbdulJabbar et al., 2020). Each WSI was sparsely annotated by 3 senior pathologists. A total of 2968 annotated patches were split into 5 folds for cross validation. We compared our method with two state-of-the-art methods applied in semantic segmentation, attention U-net (Oktay et al. 2018) and DeepLabV3+ (Chen et al. 2018). When evaluated at patch level, our method outperformed the better comparison method, DeepLabV3+, by 3.43% and 2.99% in pixel-wise Dice and overall precision (OP) (Dice: 60.34% vs. 56,91%, OP: 65.43% vs. 62.44%). When applied to WSIs, the model correctly predicted the predominant pattern for 38 out of 49 samples, achieving an accuracy of 77.55%. Interestingly, in the 11 discordant cases, 10 showed high intra-tumor heterogeneity of growth patterns, measured by Shannon diversity, highlighting the impact of intra-tumor heterogeneity on growth pattern assessment. Additionally, we combined the identified growth patterns with lymphocytic distribution measured in (AbdulJabbar et al., 2020) and revealed a significantly increased immune infiltration in proximity to the solid pattern as compared to others, which is in line with previous findings (Tavernari et al., 2021).

In summary, by leveraging image-analysis and artificial intelligence techniques, we propose a new method for precise growth pattern segmentation from routine histology samples of lung adenocarcinoma. It provides quantitative and reproducible scores of growth patterns, which can be developed into a decision support system for pathologists and clinicians. Furthermore, through pattern-specific spatial mapping, it enables future studies of intra-tumor heterogeneity, such as the preferential infiltration of lymphocyte subsets adjacent to diverse growth patterns.

Citation Format: Xiaoxi Pan, Hanyun Zhang, Anca-Ioana Grapa, Khalid AbdulJabbar, Shan E. Ahmed Raza, HO KWAN ALVIN CHEUNG, Takahiro Karasaki, John Le Quesne, David A. Moore, Charles Swanton, Yinyin Yuan. Precise segmentation of growth patterns in TRACERx lung adenocarcinoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 5055.

Abstract LB153: Clinical relevance of spatial intermixing of growth patterns and immune infiltration in lung adenocarcinoma-from TRACERx to LATTICe-A

Adenocarcinoma, the most common histologic variant of lung cancer, is morphologically diverse. The International Association for the Study of Lung Cancer (IASLC) grading system, based on the percentages of growth patterns within the tumour, is highly prognostic (Moreira et al. 2020). However, the clinicopathological significance of transitions between growth patterns, and the combinatorial effects of growth pattern and inflammatory cell infiltration are not yet known. We used a deep learning model to delineate six growth patterns (lepidic, acinar, papillary, micropapillary, solid, and cribriform) at pixel level on hematoxylin and eosin diagnostic whole slide images. The model was trained on 49 slides from the TRACERx cohort (AbdulJabbar et al. 2020), and subsequently applied to 4324 slides from 970 adenocarcinoma cases from the Leicester Archival Thoracic Tumor Investigatory Cohort (Moore et al. 2019). To examine how tumor growth patterns are spatially intermixed, we created a graph network of growth patterns. A linking criterion based on effective cell-cell communication distance was established, whereby adjacent compact tumor islands were linked together. Frequencies of 15 types of pairwise links were further evaluated. A higher intermixing score, measured as the Shannon diversity of link percentages, was associated with adverse relapse free survival (RFS) (p<0.001, Hazard Ratio (HR)=1.5, 95% Confidence Interval (CI)=1.3-1.8, n=966), independently of automated IASLC grading (p=0.001, HR=1.4, 95% CI=1.1-1.7). The clinical relevance of intermixing profiles was investigated by clustering patients into 3 groups, based on the similarity between link percentages. The group dominated by links involving high grade patterns (solid, micropapillary, cribriform), showed the highest risk of relapse (p<0.001, HR=1.7, 95% CI=1.4-2.2), followed by the group enriched with papillary-acinar links (p=0.006, HR=1.4, 95% CI=1.1-1.7). Although micropapillary subtype per se confers an unfavorable prognosis (Cao et al. 2016), its association with papillary morphology increased the risk of relapse (p=0.002, HR=4.2, 95% CI=1.6-11.0), independently of micropapillary burden. To investigate the immune microenvironment surrounding growth patterns, we quantified immune cells at the interface between growth patterns. We observed significantly reduced immune infiltration between micropapillary and papillary than between micropapillary and acinar, solid, and cribriform patterns (p<0.001). In conclusion, we showed that tumor growth pattern spatial intermixing is associated with adverse prognosis and immune infiltration. These findings offer novel insights into the spatial interplay of histological phenotypes and its clinical relevance, which may have an impact on immune escape.

Citation Format: Anca-Ioana Grapa, Hanyun Zhang, Xiaoxi Pan, Khalid AbdulJabbar, Jose Coelho-Lima, Ho Kwan Alvin Cheung, Sarah J. Aitken, David A. Moore, Charles Swanton, John Le Quesne, Yinyin Yuan. Clinical relevance of spatial intermixing of growth patterns and immune infiltration in lung adenocarcinoma-from TRACERx to LATTICe-A [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr LB153.

Abstract LB064: B cells synergize with T cell regulation at immune hotspots in lung squamous cell carcinoma

The interplay of immune cell subpopulations underpinning heterogeneous immune infiltration is poorly understood, hindering the establishment of robust prognostic markers and therapeutic targets.

To study the prognostic implications and constitution of immune cell aggregates in lung squamous cell carcinoma, we integrated transcriptomic data and deep-learning-based spatial analysis. With the automatically identified tumor and immune cells on hematoxylin and eosin (H&E) diagnostic whole slide images, we were able to map regions with lymphoid aggregates (immune hotspots - IHs) and tumor aggregates (cancer hotspots) using the Getis-Ord hotspot analysis (Getis and Ord, 1992; Nawaz et al., 2015), in 462 TCGA samples. IHs were further categorized into intratumoral (intra-IH) and peritumoral (peri-IH) based on whether they overlapped with cancer hotspots. The intra-IH score, quantifying the fraction of IHs at the cancer interface, was associated with poor overall survival independently of age, stage, and packs per year (p < 0.01, Hazard Ratio (HR) = 2.1 [1.3-3.2]). The increased score was coupled with upregulated transcriptional signals of B cells and T regulatory cells, and expression of B cell-related genes CXCR5, MS4A1 (CD20), CD79b.

To investigate cellular compositions of IHs, we selected 10 TRACERX patients with high intra-IH score based on H&E and performed immunohistochemistry on two serial sections followed by a deep learning model to locate subpopulations of T cells (CD4+FOXP3-, CD4+FOXP3+, CD8+) and B cells (CD20+CXCR5-, CD20+CXCR5+, and CD79b+). By spatially aligning these IHC images with H&E, we observed higher abundances of CD20+CXCR5+ and CD79b+ B cells at peri-IHs than intra-IHs (p<0.01; p<0.05), whereas none of the T cell subtypes showed a difference in localization. Tertiary lymphoid structures (TLSs) accounted for a minor proportion of peri-IHs (5.04 +- 4.38%) and intra-IHs (0.43 +- 0.61%). Furthermore, percentages of CD20+CXCR5+ B cells were significantly higher at peri-IHs than intra-IHs when TLSs were excluded (p=0.007), suggesting that the enrichment of CD20+CXCR5+ B cells at peri-IHs was not fully explained by the presence of TLSs.

To test if IHs have a role in the regulation of anti-tumor activity of T cytotoxic cells, we further measured the ratio of CD8+ to CD4+FOXP3+ T cells infiltrating into the tumor nest. The ratio at tumor regions adjacent to intra-IH was lower than the rest of the tumor nest (p<0.001), suggesting a suppressive effect of intra-IH on tumor-infiltrating CD8+ T cells.

Taken together, our results signified a protumor role of intratumoral lymphoid aggregates beyond TLSs, which may be attributed to the spatial interplay between CD8+ T cells, Tregs and B cells. Immune hotspots can serve as a prognostic indicator and potential therapeutic target in lung squamous cell carcinoma.

Citation Format: Hanyun Zhang, Khalid AbdulJabbar, David A. Moore, Ayse Akarca, Katey Enfield, Mariam Jamal-Hanjani, Shan E Ahmed Raza, Selvaraju Veeriah, Dhruva Biswas, Roberto Salgado, Nicholas McGranahan, TRACERx Consortium, John Le Quesne, Charles Swanton, Teresa Marafioti, Yinyin Yuan. B cells synergize with T cell regulation at immune hotspots in lung squamous cell carcinoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr LB064.

Abstract LB504: Automated grading of growth patterns in lung adenocarcinoma-from TRACERx to LATTICe-A

Lung adenocarcinoma exhibits distinct growth patterns (WHO, 2021) and the International Association for the Study of Lung Cancer (IASLC) grading system, based on the nature and proportion of histologic subtypes, is highly prognostic (Moreira et al. 2020). However, both recognition and quantification of growth patterns suffer from high interobserver variability among pathologists. Here, we present a large-scale application to automate the segmentation of histologic patterns and reproduce the IASLC grading system to stratify patients and predict prognosis.

A deep learning model was trained to recognize and segment 6 histologic patterns (lepidic, acinar, papillary, micropapillary, solid, and cribriform) on 49 whole-slide images from TRACERx (AbdulJabbar et al. 2020). This model was directly applied to an independent cohort, consisting of 4324 hematoxylin and eosin-stained sections from 970 patients (the Leicester Archival Thoracic Tumor Investigatory Cohort, Moore et al. 2019).

Growth pattern segmentation performance was first evaluated against 2433 hand annotations covering 6 patterns from 9 images at a pixel level using Dice coefficient. The average Dice was 0.502. Predicted predominant pattern per tumor was then compared to a subspecialty pathologist, achieving an overall agreement (51%), comparable to the interobserver rate among pathologists (52%, Boland et al. 2017). Discordant cases were more heterogeneous (p=4.5e-10, Shannon diversity based on pathological scores), underscoring the challenges posed by intratumor heterogeneity.

Patients with a high proportion of micropapillary in the tumor, identified by deep learning, had significantly worse relapse-free survival (RFS) in multivariate analyses including clinical parameters (p=0.00127, Hazard Ratio (HR)=6.4, 95% confidence interval (CI)=2.07-19.8, n=827), consistent with previous publication (Cha et al. 2014). The Kaplan-Meier curve for RFS was significantly differentiated with both automated and pathological IASLC grading (p<0.0001). Moreover, patients with predominantly high-grade patterns (solid, micropapillary, cribriform) identified by deep learning had significantly reduced RFS (p=6.22e-4, HR=1.5, 95% CI=1.18-1.8, n=970). The prognostic effect was stronger using IASLC grading (cutoff: 20%, p=5.56e-6, HR=1.7, 95% CI=1.36-2.2), comparable to the pathological score at IASLC grade 3 (cutoff: 20%, p=2.41e-5, HR=1.8, 95% CI=1.35-2.3). A similar performance was observed for overall survival regarding above analyses.

To the best of our knowledge, this study represents the largest application of deep learning to recognize tumor growth patterns in lung adenocarcinoma. Histologically heterogeneous growth patterns can be automatically identified using a method trained on an independent cohort. Automated tumor grading is significantly associated with patient outcomes, supporting its potential clinical utility.

Citation Format: Xiaoxi Pan, Khalid AbdulJabbar, Jose Coelho-Lima, Anca-Ioana Grapa, Hanyun Zhang, Ho Kwan Alvin Cheung, Sarah J. Aitken, David A. Moore, Charles Swanton, John Le Quesne, Yinyin Yuan. Automated grading of growth patterns in lung adenocarcinoma-from TRACERx to LATTICe-A [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr LB504.

Biomarkers for site-specific response to neoadjuvant chemotherapy in epithelial ovarian cancer: relating MRI changes to tumour cell load and necrosis

BACKGROUND

Diffusion-weighted magnetic resonance imaging (DW-MRI) potentially interrogates site-specific response to neoadjuvant chemotherapy (NAC) in epithelial ovarian cancer (EOC).

METHODS

Participants with newly diagnosed EOC due for platinum-based chemotherapy and interval debulking surgery were recruited prospectively in a multicentre study (n = 47 participants). Apparent diffusion coefficient (ADC) and solid tumour volume (up to 10 lesions per participant) were obtained from DW-MRI before and after NAC (including double-baseline for repeatability assessment in n = 19). Anatomically matched lesions were analysed after surgical excision (65 lesions obtained from 25 participants). A trained algorithm determined tumour cell fraction, percentage tumour and percentage necrosis on histology. Whole-lesion post-NAC ADC and pre/post-NAC ADC changes were compared with histological metrics (residual tumour/necrosis) for each tumour site (ovarian, omental, peritoneal, lymph node).

RESULTS

Tumour volume reduced at all sites after NAC. ADC increased between pre- and post-NAC measurements. Post-NAC ADC correlated negatively with tumour cell fraction. Pre/post-NAC changes in ADC correlated positively with percentage necrosis. Significant correlations were driven by peritoneal lesions.

CONCLUSIONS

Following NAC in EOC, the ADC (measured using DW-MRI) increases differentially at disease sites despite similar tumour shrinkage, making its utility site-specific. After NAC, ADC correlates negatively with tumour cell fraction; change in ADC correlates positively with percentage necrosis.

CLINICAL TRIAL REGISTRATION

ClinicalTrials.gov NCT01505829.

Immune Surveillance in Clinical Regression of Preinvasive Squamous Cell Lung Cancer

Before squamous cell lung cancer develops, precancerous lesions can be found in the airways. From longitudinal monitoring, we know that only half of such lesions become cancer, whereas a third spontaneously regress. Although recent studies have described the presence of an active immune response in high-grade lesions, the mechanisms underpinning clinical regression of precancerous lesions remain unknown. Here, we show that host immune surveillance is strongly implicated in lesion regression. Using bronchoscopic biopsies from human subjects, we find that regressive carcinoma in situ lesions harbor more infiltrating immune cells than those that progress to cancer. Moreover, molecular profiling of these lesions identifies potential immune escape mechanisms specifically in those that progress to cancer: antigen presentation is impaired by genomic and epigenetic changes, CCL27-CCR10 signaling is upregulated, and the immunomodulator TNFSF9 is downregulated. Changes appear intrinsic to the carcinoma in situ lesions, as the adjacent stroma of progressive and regressive lesions are transcriptomically similar. SIGNIFICANCE: Immune evasion is a hallmark of cancer. For the first time, this study identifies mechanisms by which precancerous lesions evade immune detection during the earliest stages of carcinogenesis and forms a basis for new therapeutic strategies that treat or prevent early-stage lung cancer.See related commentary by Krysan et al., p. 1442.This article is highlighted in the In This Issue feature, p. 1426.

Geospatial immune variability illuminates differential evolution of lung adenocarcinoma

Remarkable progress in molecular analyses has improved our understanding of the evolution of cancer cells toward immune escape1-5. However, the spatial configurations of immune and stromal cells, which may shed light on the evolution of immune escape across tumor geographical locations, remain unaddressed. We integrated multiregion exome and RNA-sequencing (RNA-seq) data with spatial histology mapped by deep learning in 100 patients with non-small cell lung cancer from the TRACERx cohort6. Cancer subclones derived from immune cold regions were more closely related in mutation space, diversifying more recently than subclones from immune hot regions. In TRACERx and in an independent multisample cohort of 970 patients with lung adenocarcinoma, tumors with more than one immune cold region had a higher risk of relapse, independently of tumor size, stage and number of samples per patient. In lung adenocarcinoma, but not lung squamous cell carcinoma, geometrical irregularity and complexity of the cancer-stromal cell interface significantly increased in tumor regions without disruption of antigen presentation. Decreased lymphocyte accumulation in adjacent stroma was observed in tumors with low clonal neoantigen burden. Collectively, immune geospatial variability elucidates tumor ecological constraints that may shape the emergence of immune-evading subclones and aggressive clinical phenotypes.

Pitfalls in assessing stromal tumor infiltrating lymphocytes (sTILs) in breast cancer

Stromal tumor-infiltrating lymphocytes (sTILs) are important prognostic and predictive biomarkers in triple-negative (TNBC) and HER2-positive breast cancer. Incorporating sTILs into clinical practice necessitates reproducible assessment. Previously developed standardized scoring guidelines have been widely embraced by the clinical and research communities. We evaluated sources of variability in sTIL assessment by pathologists in three previous sTIL ring studies. We identify common challenges and evaluate impact of discrepancies on outcome estimates in early TNBC using a newly-developed prognostic tool. Discordant sTIL assessment is driven by heterogeneity in lymphocyte distribution. Additional factors include: technical slide-related issues; scoring outside the tumor boundary; tumors with minimal assessable stroma; including lymphocytes associated with other structures; and including other inflammatory cells. Small variations in sTIL assessment modestly alter risk estimation in early TNBC but have the potential to affect treatment selection if cutpoints are employed. Scoring and averaging multiple areas, as well as use of reference images, improve consistency of sTIL evaluation. Moreover, to assist in avoiding the pitfalls identified in this analysis, we developed an educational resource available at www.tilsinbreastcancer.org/pitfalls.

Report on computational assessment of Tumor Infiltrating Lymphocytes from the International Immuno-Oncology Biomarker Working Group

Assessment of tumor-infiltrating lymphocytes (TILs) is increasingly recognized as an integral part of the prognostic workflow in triple-negative (TNBC) and HER2-positive breast cancer, as well as many other solid tumors. This recognition has come about thanks to standardized visual reporting guidelines, which helped to reduce inter-reader variability. Now, there are ripe opportunities to employ computational methods that extract spatio-morphologic predictive features, enabling computer-aided diagnostics. We detail the benefits of computational TILs assessment, the readiness of TILs scoring for computational assessment, and outline considerations for overcoming key barriers to clinical translation in this arena. Specifically, we discuss: 1. ensuring computational workflows closely capture visual guidelines and standards; 2. challenges and thoughts standards for assessment of algorithms including training, preanalytical, analytical, and clinical validation; 3. perspectives on how to realize the potential of machine learning models and to overcome the perceptual and practical limits of visual scoring.

The T cell differentiation landscape is shaped by tumour mutations in lung cancer

Tumour mutational burden (TMB) predicts immunotherapy outcome in non-small cell lung cancer (NSCLC), consistent with immune recognition of tumour neoantigens. However, persistent antigen exposure is detrimental for T cell function. How TMB affects CD4 and CD8 T cell differentiation in untreated tumours, and whether this affects patient outcomes is unknown. Here we paired high-dimensional flow cytometry, exome, single-cell and bulk RNA sequencing from patients with resected, untreated NSCLC to examine these relationships. TMB was associated with compartment-wide T cell differentiation skewing, characterized by loss of TCF7-expressing progenitor-like CD4 T cells, and an increased abundance of dysfunctional CD8 and CD4 T cell subsets, with significant phenotypic and transcriptional similarity to neoantigen-reactive CD8 T cells. A gene signature of redistribution from progenitor-like to dysfunctional states associated with poor survival in lung and other cancer cohorts. Single-cell characterization of these populations informs potential strategies for therapeutic manipulation in NSCLC.