High inter-follicular spatial co-localization of CD8+FOXP3+ with CD4+CD8+ cells predicts favorable outcome in follicular lymphoma.

The spatial architecture of the lymphoid tissue in follicular lymphoma (FL) presents unique challenges to studying its immune microenvironment. We investigated the spatial interplay of T cells, macrophages, myeloid cells and natural killer T cells using multispectral immunofluorescence images of diagnostic biopsies of 32 patients. A deep learning-based image analysis pipeline was tailored to the needs of follicular lymphoma spatial histology research, enabling the identification of different immune cells within and outside neoplastic follicles. We analyzed the density and spatial co-localization of immune cells in the inter-follicular and intra-follicular regions of follicular lymphoma. Low inter-follicular density of CD8+FOXP3+ cells and co-localization of CD8+FOXP3+ with CD4+CD8+ cells were significantly associated with relapse (p = 0.0057 and p = 0.0019, respectively) and shorter time to progression after first-line treatment (Logrank p = 0.0097 and log-rank p = 0.0093, respectively). A low inter-follicular density of CD8+FOXP3+ cells is associated with increased risk of relapse independent of follicular lymphoma international prognostic index (FLIPI) (p = 0.038, Hazard ratio (HR) = 0.42 [0.19, 0.95], but not independent of co-localization of CD8+FOXP3+ with CD4+CD8+ cells (p = 0.43). Co-localization of CD8+FOXP3+ with CD4+CD8+ cells is predictors of time to relapse independent of the FLIPI score and density of CD8+FOXP3+ cells (p = 0.027, HR = 0.0019 [7.19 × 10-6 , 0.49], This suggests a potential role of inter-follicular CD8+FOXP3+ and CD4+CD8+ cells in the disease progression of FL, warranting further validation on larger patient cohorts.

Deep Learning Enables Spatial Mapping of the Mosaic Microenvironment of Myeloma Bone Marrow Trephine Biopsies.

Bone marrow trephine biopsy is crucial for the diagnosis of multiple myeloma. However, the complexity of bone marrow cellular, morphologic, and spatial architecture preserved in trephine samples hinders comprehensive evaluation. To dissect the diverse cellular communities and mosaic tissue habitats, we developed a superpixel-inspired deep learning method (MoSaicNet) that adapts to complex tissue architectures and a cell imbalance aware deep learning pipeline (AwareNet) to enable accurate detection and classification of rare cell types in multiplex immunohistochemistry images. MoSaicNet and AwareNet achieved an AUC of >0.98 for tissue and cellular classification on separate test datasets. Application of MoSaicNet and AwareNet enabled investigation of bone heterogeneity and thickness as well as spatial histology analysis of bone marrow trephine samples from monoclonal gammopathies of undetermined significance (MGUS) and from paired newly diagnosed and posttreatment multiple myeloma. The most significant difference between MGUS and newly diagnosed multiple myeloma (NDMM) samples was not related to cell density but to spatial heterogeneity, with reduced spatial proximity of BLIMP1+ tumor cells to CD8+ cells in MGUS compared with NDMM samples. Following treatment of patients with multiple myeloma, there was a reduction in the density of BLIMP1+ tumor cells, effector CD8+ T cells, and regulatory T cells, indicative of an altered immune microenvironment. Finally, bone heterogeneity decreased following treatment of patients with multiple myeloma. In summary, deep learning-based spatial mapping of bone marrow trephine biopsies can provide insights into the cellular topography of the myeloma marrow microenvironment and complement aspirate-based techniques. SIGNIFICANCE: Spatial analysis of bone marrow trephine biopsies using histology, deep learning, and tailored algorithms reveals the bone marrow architectural heterogeneity and evolution during myeloma progression and treatment.

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.

Artificial intelligence-based morphometric signature to identify ductal carcinoma in situ with low risk of progression to invasive breast cancer.

Ductal carcinoma in situ (DCIS) may progress to ipsilateral invasive breast cancer (iIBC), but often never will. Because DCIS is treated as early breast cancer, many women with harmless DCIS face overtreatment. To identify these women that may forego treatment, we hypothesized that DCIS morphometric features relate to the risk of subsequent iIBC. We developed an artificial intelligence-based DCIS morphometric analysis pipeline (AIDmap) to detect DCIS as a pathologist and measure morphological structures in hematoxylin-eosin-stained (H&E) tissue sections. These were from a case-control study of patients diagnosed with primary DCIS, treated by breast-conserving surgery without radiotherapy. We analyzed 689 WSIs of DCIS of which 226 were diagnosed with subsequent iIBC (cases) and 463 were not (controls). The distribution of 15 duct morphological measurements in each H&E was summarized in 55 morphometric variables. A ridge regression classifier with cross validation predicted 5-years-free of iIBC with an area-under the curve of 0.65 (95% CI 0.55-0.76). A morphometric signature based on the 30 variables most associated with outcome, identified lesions containing small-sized ducts, low number of cells and low DCIS/stroma area ratio. This signature was associated with lower iIBC risk in a multivariate regression model including grade, ER, HER2 and COX-2 expression (HR = 0.56; 95% CI 0.28-0.78). AIDmap has potential to identify harmless DCIS that may not need treatment.

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.