Computational immunohistochemical mapping adds immune context to histological phenotypes in mouse models of colitis.

Inflammatory bowel disease (IBD) is characterized by chronic, dysregulated inflammation in the gastrointestinal tract. The heterogeneity of IBD is reflected through two major subtypes, Crohn's Disease (CD) and Ulcerative Colitis (UC). CD and UC differ across symptomatic presentation, histology, immune responses, and treatment. While colitis mouse models have been influential in deciphering IBD pathogenesis, no single model captures the full heterogeneity of clinical disease. The translational capacity of mouse models may be augmented by shifting to multi-mouse model studies that aggregate analysis across various well-controlled phenotypes. Here, we evaluate the value of histology in multi-mouse model characterizations by building upon a previous pipeline that detects histological disease classes in hematoxylin and eosin (H&E)-stained murine colons. Specifically, we map immune marker positivity across serially-sectioned slides to H&E histological classes across the dextran sodium sulfate (DSS) chemical induction model and the intestinal epithelium-specific, inducible Villin-CreERT2;Klf5fl/fl (Klf5ΔIND) genetic model. In this study, we construct the beginning frameworks to define H&E-patch-based immunophenotypes based on IHC-H&E mappings.

Deep learning-based approach to the characterization and quantification of histopathology in mouse models of colitis.

Inflammatory bowel disease (IBD) is a chronic immune-mediated disease of the gastrointestinal tract. While therapies exist, response can be limited within the patient population. Researchers have thus studied mouse models of colitis to further understand pathogenesis and identify new treatment targets. Flow cytometry and RNA-sequencing can phenotype immune populations with single-cell resolution but provide no spatial context. Spatial context may be particularly important in colitis mouse models, due to the simultaneous presence of colonic regions that are involved or uninvolved with disease. These regions can be identified on hematoxylin and eosin (H&E)-stained colonic tissue slides based on the presence of abnormal or normal histology. However, detection of such regions requires expert interpretation by pathologists. This can be a tedious process that may be difficult to perform consistently across experiments. To this end, we trained a deep learning model to detect 'Involved' and 'Uninvolved' regions from H&E-stained colonic tissue slides. Our model was trained on specimens from controls and three mouse models of colitis-the dextran sodium sulfate (DSS) chemical induction model, the recently established intestinal epithelium-specific, inducible Klf5ΔIND (Villin-CreERT2;Klf5fl/fl) genetic model, and one that combines both induction methods. Image patches predicted to be 'Involved' and 'Uninvolved' were extracted across mice to cluster and identify histological classes. We quantified the proportion of 'Uninvolved' patches and 'Involved' patch classes in murine swiss-rolled colons. Furthermore, we trained linear determinant analysis classifiers on these patch proportions to predict mouse model and clinical score bins in a prospectively treated cohort of mice. Such a pipeline has the potential to reveal histological links and improve synergy between various colitis mouse model studies to identify new therapeutic targets and pathophysiological mechanisms.

Spatial Characterization of Tumor-Infiltrating Lymphocytes and Breast Cancer Progression.

Tumor-infiltrating lymphocytes (TILs) have been established as a robust prognostic biomarker in breast cancer, with emerging utility in predicting treatment response in the adjuvant and neoadjuvant settings. In this study, the role of TILs in predicting overall survival and progression-free interval was evaluated in two independent cohorts of breast cancer from the Cancer Genome Atlas (TCGA BRCA) and the Carolina Breast Cancer Study (UNC CBCS). We utilized machine learning and computer vision algorithms to characterize TIL infiltrates in digital whole-slide images (WSIs) of breast cancer stained with hematoxylin and eosin (H&E). Multiple parameters were used to characterize the global abundance and spatial features of TIL infiltrates. Univariate and multivariate analyses show that large aggregates of peritumoral and intratumoral TILs (forests) were associated with longer survival, whereas the absence of intratumoral TILs (deserts) is associated with increased risk of recurrence. Patients with two or more high-risk spatial features were associated with significantly shorter progression-free interval (PFI). This study demonstrates the practical utility of Pathomics in evaluating the clinical significance of the abundance and spatial patterns of distribution of TIL infiltrates as important biomarkers in breast cancer.

KLF5 protects the intestinal epithelium against Th17 immune response in a murine colitis model.

Inflammatory bowel disease (IBD) is a chronic illness characterized by dysregulated immune cascades in the intestines, in which the Th17 immune response plays an important role. We demonstrated that mice with intestinal epithelium-specific deletion of Krüppel-like factor 5 (Klf5) developed Th17-dependent colonic inflammation. In the absence of KLF5, there was aberrant cellular localization of phosphorylated STAT3, an essential mediator of the Th17-associated cytokine, IL-22, which is required for epithelial tissue regeneration. In contrast, mitigation of IL-17A with anti-IL-17A neutralizing antibody attenuated colitis in Klf5-deficient mice. There was also a considerable shift in the colonic microbiota of Klf5-deficient mice that phenocopied human IBD. Notably, the inflammatory response due to Klf5 deletion was alleviated by antibiotic treatment, implicating the role of microbiota in pathogenesis. Finally, human colitic tissues had reduced KLF5 levels when compared with healthy tissues. Together, these findings demonstrated the importance of KLF5 in protecting the intestinal epithelium against Th17-mediated immune and inflammatory responses. The mice described herein may serve as a potential model for human IBD.

State of machine and deep learning in histopathological applications in digestive diseases.

Machine learning (ML)- and deep learning (DL)-based imaging modalities have exhibited the capacity to handle extremely high dimensional data for a number of computer vision tasks. While these approaches have been applied to numerous data types, this capacity can be especially leveraged by application on histopathological images, which capture cellular and structural features with their high-resolution, microscopic perspectives. Already, these methodologies have demonstrated promising performance in a variety of applications like disease classification, cancer grading, structure and cellular localizations, and prognostic predictions. A wide range of pathologies requiring histopathological evaluation exist in gastroenterology and hepatology, indicating these as disciplines highly targetable for integration of these technologies. Gastroenterologists have also already been primed to consider the impact of these algorithms, as development of real-time endoscopic video analysis software has been an active and popular field of research. This heightened clinical awareness will likely be important for future integration of these methods and to drive interdisciplinary collaborations on emerging studies. To provide an overview on the application of these methodologies for gastrointestinal and hepatological histopathological slides, this review will discuss general ML and DL concepts, introduce recent and emerging literature using these methods, and cover challenges moving forward to further advance the field.

RXRs control serous macrophage neonatal expansion and identity and contribute to ovarian cancer progression.

Tissue-resident macrophages (TRMs) populate all tissues and play key roles in homeostasis, immunity and repair. TRMs express a molecular program that is mostly shaped by tissue cues. However, TRM identity and the mechanisms that maintain TRMs in tissues remain poorly understood. We recently found that serous-cavity TRMs (LPMs) are highly enriched in RXR transcripts and RXR-response elements. Here, we show that RXRs control mouse serous-macrophage identity by regulating chromatin accessibility and the transcriptional regulation of canonical macrophage genes. RXR deficiency impairs neonatal expansion of the LPM pool and reduces the survival of adult LPMs through excess lipid accumulation. We also find that peritoneal LPMs infiltrate early ovarian tumours and that RXR deletion diminishes LPM accumulation in tumours and strongly reduces ovarian tumour progression in mice. Our study reveals that RXR signalling controls the maintenance of the serous macrophage pool and that targeting peritoneal LPMs may improve ovarian cancer outcomes.

High-dimensional single cell mapping of cerium distribution in the lung immune microenvironment of an active smoker.

BACKGROUND: Mass cytometry leverages inductively coupled mass spectrometry to perform high dimensional single cell analyses using antibodies tagged with rare earth isotopes that are considered to be largely absent in biological samples. We have recently noted an unusual exception to this rule while analyzing tissue samples from patients undergoing surgical resection for early stage lung cancer, and here we present a detailed cytometric characterization of cerium in a clinical patient sample. METHODS: We performed a CyTOF analysis on cell suspensions derived from matched blood, tumor lesion, and non-involved lung tissue from an active smoker undergoing surgical resection for early stage lung adenocarcinoma. The samples were stained with a 31-parameter antibody panel to allow a detailed characterization of the cellular heterogeneity of the samples. The data were visualized using viSNE, major immune subsets were identified based on canonical marker expression patterns, and single cell cerium levels were evaluated across each of these defined subsets. RESULTS: High dimensional immune cell mapping revealed that high levels of cerium were specifically associated with a phenotypically distinct subset of lung macrophages that were most prevalent in noninvolved lung tissue, whereas tumor associated macrophages showed relatively lower levels of cerium. We hypothesize that these findings reflect alveolar macrophage phagocytosis of inhaled cerium derived from cigarette flint lighters. CONCLUSIONS: These results demonstrate the first high-dimensional single cell characterization of environmental metal exposure associated with smoking, and offer a demonstration of the unique potential for applying mass cytometry to the field of environmental toxicology. © 2017 International Clinical Cytometry Society.

Innate Immune Landscape in Early Lung Adenocarcinoma by Paired Single-Cell Analyses.

To guide the design of immunotherapy strategies for patients with early stage lung tumors, we developed a multiscale immune profiling strategy to map the immune landscape of early lung adenocarcinoma lesions to search for tumor-driven immune changes. Utilizing a barcoding method that allows a simultaneous single-cell analysis of the tumor, non-involved lung, and blood cells, we provide a detailed immune cell atlas of early lung tumors. We show that stage I lung adenocarcinoma lesions already harbor significantly altered T cell and NK cell compartments. Moreover, we identified changes in tumor-infiltrating myeloid cell (TIM) subsets that likely compromise anti-tumor T cell immunity. Paired single-cell analyses thus offer valuable knowledge of tumor-driven immune changes, providing a powerful tool for the rational design of immune therapies. VIDEO ABSTRACT.