scholarly journals Deep-Learning–Based Characterization of Tumor-Infiltrating Lymphocytes in Breast Cancers From Histopathology Images and Multiomics Data

2020 ◽  
pp. 480-490 ◽  
Author(s):  
Zixiao Lu ◽  
Siwen Xu ◽  
Wei Shao ◽  
Yi Wu ◽  
Jie Zhang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Strong Association ◽  
Tumor Infiltrating Lymphocytes ◽  
Genetic Alterations ◽  
Image Features ◽  
Cancer Immunology ◽  
The Cancer Genome Atlas ◽  
Breast Cancer Subtypes ◽  
Cancer Subtypes ◽  
Infiltrating Lymphocytes

PURPOSE Tumor-infiltrating lymphocytes (TILs) and their spatial characterizations on whole-slide images (WSIs) of histopathology sections have become crucial in diagnosis, prognosis, and treatment response prediction for different cancers. However, fully automatic assessment of TILs on WSIs currently remains a great challenge because of the heterogeneity and large size of WSIs. We present an automatic pipeline based on a cascade-training U-net to generate high-resolution TIL maps on WSIs. METHODS We present global cell-level TIL maps and 43 quantitative TIL spatial image features for 1,000 WSIs of The Cancer Genome Atlas patients with breast cancer. For more specific analysis, all the patients were divided into three subtypes, namely, estrogen receptor (ER)–positive, ER-negative, and triple-negative groups. The associations between TIL scores and gene expression and somatic mutation were examined separately in three breast cancer subtypes. Both univariate and multivariate survival analyses were performed on 43 TIL image features to examine the prognostic value of TIL spatial patterns in different breast cancer subtypes. RESULTS The TIL score was in strong association with immune response pathway and genes (eg, programmed death-1 and CLTA4). Different breast cancer subtypes showed TIL score in association with mutations from different genes suggesting that different genetic alterations may lead to similar phenotypes. Spatial TIL features that represent density and distribution of TIL clusters were important indicators of the patient outcomes. CONCLUSION Our pipeline can facilitate computational pathology-based discovery in cancer immunology and research on immunotherapy. Our analysis results are available for the research community to generate new hypotheses and insights on breast cancer immunology and development.

scholarly journals Prognostic and predictive value of tumor-infiltrating lymphocytes in breast cancer (literature review)

2021 ◽  
Vol 4 (1) ◽  
pp. 39-44
Author(s):  
M.O. Bilych
Keyword(s):  
Breast Cancer ◽  
Predictive Factor ◽  
Predictive Value ◽  
Tumor Infiltrating Lymphocytes ◽  
Breast Cancer Subtypes ◽  
Cancer Type ◽  
Primary Tumors ◽  
Positive Correlation ◽  
Cancer Subtypes ◽  
Infiltrating Lymphocytes

Background. Breast cancer is the leading cancer type in women. Improvement in its management requires a continuous investigation of new tools for diagnosis and treatment. Biomarkers for breast cancer remain a field of great interest, despite existing knowledge. Extensive research recognizes the critical role played by tumor-infiltrating lymphocytes (TILs) in terms of prognosis and prediction, but much uncertainty still exists about the application of this biomarker in clinical practice. Thus, the purpose of this paper is to review recent researches about the role of TILs as a prognostic and predictive factor in the clinical management of breast cancer subtypes. Materials and methods. Eligible studies from Medline, Pubmed, Google Scholar (2010–2020) databases were analyzed and retrieved. Results. For primary tumors, a positive correlation was found between TILs and survival prognosis for HER2+ and TNBC subtypes, while for luminal subtypes it was a negative correlation. The predictive value of TILs in the neoadjuvant setting is established for HER2+, TNBC subtypes. In the case of using TILs as a predictive factor for HER2-targeted therapy, it remains a concern due to controversial data. For residual tumor, it is growing body of evidence about the positive correlation of TILs and prognosis for all subtypes, but data are limited. Conclusions. TILs were found to have prognostic and predictive value. However, due to the heterogeneity of breast cancer subtypes, TILs as a biomarker should be interpreted with caution. Further studies need to be carried out to determine the validity of making a clinical decision based on TILs count.

Genetic Alterations and Oncogenic Pathways Associated with Breast Cancer Subtypes

2009 ◽  
Vol 7 (4) ◽  
pp. 511-522 ◽  
Author(s):  
Xiaolan Hu ◽  
Howard M. Stern ◽  
Lin Ge ◽  
Carol O'Brien ◽  
Lauren Haydu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Genetic Alterations ◽  
Breast Cancer Subtypes ◽  
Cancer Subtypes ◽  
Oncogenic Pathways

Tumor-infiltrating lymphocytes to predict survival to anthracycline/taxane-based adjuvant chemotherapy in triple negative breast cancer.

2018 ◽  
Vol 36 (5_suppl) ◽  
pp. 1-1
Author(s):  
Qiyun Ou ◽  
Yunfang Yu ◽  
Xiaoyun Xiao ◽  
Baoming Luo
Keyword(s):  
Breast Cancer ◽  
Adjuvant Chemotherapy ◽  
Triple Negative Breast Cancer ◽  
Triple Negative ◽  
Meta Analysis ◽  
Disease Free Survival ◽  
Breast Cancer Subtypes ◽  
Her2 Positive ◽  
Cancer Subtypes ◽  
Infiltrating Lymphocytes

1 Background: Previous clinical data suggested that the tumour-infiltrating lymphocytes (TILs) were predictive in breast cancer treated with adjuvant chemotherapy; however, clinical relevance has yet to be established. We hypothesized that TILs would be associated with overall survival (OS) and disease-free survival (DFS) after anthracycline/taxane-based adjuvant chemotherapy in breast cancer subtypes. Methods: PubMed and EMBASE were searched until March 2017 for studies that investigated the association of TILs with survival for anthracycline/taxane-based adjuvant chemotherapy in breast cancer. OS and DFS were combined using random-effects meta-analysis and calculated as combined hazard ratio (HR) with 95% credible intervals (CIs). The PROSPERO registry number is CRD42017072133. Results: Twelve studies comprising 9,023 patients were eligible for analysis. Six were prospective adjuvant trials (n = 7686) and six were retrospective studies (n = 1337). Pooled analysis indicated that high TILs have no significant predictive association in overall population (DFS, HR = 0.87, 95% CI, 0.70 – 1.08; OS, HR = 0.98, 95% CI, 0.89 – 1.07), Luminal A/B (DFS, HR = 0.99, 95% CI, 0.94 – 1.04; OS, HR = 1.01, 95% CI, 0.92 – 1.12), and HER2–positive patients (DFS, HR = 0.84, 95% CI, 0.71 – 1.00; OS, HR = 0.89, 95% CI, 0.77 – 1.02), but were related to improved DFS (HR, 0.81; 95% CI, 0.73 – 0.89) and OS (HR, 0.74; 95% CI, 0.66 – 0.84) in triple negative breast cancer (TNBC) patients. Additionally, increasing TILs were not significantly associated with reduced risk of relapse in HER2-positive patient through adjuvant trastuzumab (HR, 0.97; 95% CI, 0.93 – 1.01). Conclusions: This meta-analysis provides an evidence that TILs predicts survival to anthracycline/taxane-based adjuvant chemotherapy in TNBC patients and suggests that predictive benefit seemed to be influenced by breast cancer subtypes as well.

scholarly journals Classifying Breast Cancer Subtypes Using Deep Neural Networks Based on Multi-Omics Data

Genes ◽  
2020 ◽  
Vol 11 (8) ◽  
pp. 888
Author(s):  
Yuqi Lin ◽  
Wen Zhang ◽  
Huanshen Cao ◽  
Gaoyang Li ◽  
Wei Du
Keyword(s):  
Breast Cancer ◽  
Neural Networks ◽  
Feature Selection ◽  
Deep Neural Networks ◽  
Selection Process ◽  
Breast Cancer Subtype ◽  
The Cancer Genome Atlas ◽  
Breast Cancer Subtypes ◽  
Omics Data ◽  
Cancer Subtypes

With the high prevalence of breast cancer, it is urgent to find out the intrinsic difference between various subtypes, so as to infer the underlying mechanisms. Given the available multi-omics data, their proper integration can improve the accuracy of breast cancer subtype recognition. In this study, DeepMO, a model using deep neural networks based on multi-omics data, was employed for classifying breast cancer subtypes. Three types of omics data including mRNA data, DNA methylation data, and copy number variation (CNV) data were collected from The Cancer Genome Atlas (TCGA). After data preprocessing and feature selection, each type of omics data was input into the deep neural network, which consists of an encoding subnetwork and a classification subnetwork. The results of DeepMO based on multi-omics on binary classification are better than other methods in terms of accuracy and area under the curve (AUC). Moreover, compared with other methods using single omics data and multi-omics data, DeepMO also had a higher prediction accuracy on multi-classification. We also validated the effect of feature selection on DeepMO. Finally, we analyzed the enrichment gene ontology (GO) terms and biological pathways of these significant genes, which were discovered during the feature selection process. We believe that the proposed model is useful for multi-omics data analysis.

scholarly journals Identification and validation of expressed HLA-binding breast cancer neoepitopes for potential use in individualized cancer therapy

2021 ◽  
Vol 9 (6) ◽  
pp. e002605
Author(s):  
Hannah Reimann ◽  
Andrew Nguyen ◽  
J Zachary Sanborn ◽  
Charles J Vaske ◽  
Stephen C Benz ◽  
...  
Keyword(s):  
Breast Cancer ◽  
T Cells ◽  
T Cell ◽  
Cell Line ◽  
Tumor Infiltrating Lymphocytes ◽  
The Cancer Genome Atlas ◽  
High Avidity ◽  
Binding Prediction ◽  
Hla Binding ◽  
Infiltrating Lymphocytes

BackgroundTherapeutic regimens designed to augment the immunological response of a patient with breast cancer (BC) to tumor tissue are critically informed by tumor mutational burden and the antigenicity of expressed neoepitopes. Herein we describe a neoepitope and cognate neoepitope-reactive T-cell identification and validation program that supports the development of next-generation immunotherapies.MethodsUsing GPS Cancer, NantOmics research, and The Cancer Genome Atlas databases, we developed a novel bioinformatic-based approach which assesses mutational load, neoepitope expression, human leukocyte antigen (HLA)-binding prediction, and in vitro confirmation of T-cell recognition to preferentially identify targetable neoepitopes. This program was validated by application to a BC cell line and confirmed using tumor biopsies from two patients with BC enrolled in the Tumor-Infiltrating Lymphocytes and Genomics (TILGen) study.ResultsThe antigenicity and HLA-A2 restriction of the BC cell line predicted neoepitopes were determined by reactivity of T cells from HLA-A2-expressing healthy donors. For the TILGen subjects, tumor-infiltrating lymphocytes (TILs) recognized the predicted neoepitopes both as peptides and on retroviral expression in HLA-matched Epstein-Barr virus–lymphoblastoid cell line and BC cell line MCF-7 cells; PCR clonotyping revealed the presence of T cells in the periphery with T-cell receptors for the predicted neoepitopes. These high-avidity immune responses were polyclonal, mutation-specific and restricted to either HLA class I or II. Interestingly, we observed the persistence and expansion of polyclonal T-cell responses following neoadjuvant chemotherapy.ConclusionsWe demonstrate our neoepitope prediction program allows for the successful identification of neoepitopes targeted by TILs in patients with BC, providing a means to identify tumor-specific immunogenic targets for individualized treatment, including vaccines or adoptively transferred cellular therapies.

scholarly journals Computational Disease Subtyping based on Joint Analysis of Clinical and Genomic Data

2018 ◽  
Author(s):  
Diana Diaz ◽  
Aliccia Bollig-Fischer ◽  
Alexander Kotov
Keyword(s):  
Breast Cancer ◽  
Somatic Mutation ◽  
Patient Survival ◽  
Cox Model ◽  
Genomic Data ◽  
Cox Proportional Hazards Model ◽  
The Cancer Genome Atlas ◽  
Breast Cancer Subtypes ◽  
Joint Analysis ◽  
Cancer Subtypes

ABSTRACTObjectiveTo investigate application of non-negative tensor decomposition for disease subtype discovery based on joint analysis of clinical and genomic data.Data and MethodsSomatic mutation profiles including 11,996 genes of 503 breast cancer patients from the Cancer Genome Atlas (TCGA) along with 11 clinical variables and markers of these patients were used to construct a binary third-order tensor. CANDECOMP/PARAFAC method was applied to decompose the constructed tensor into rank-one component tensors. Definitions of breast cancer verotypes were constructed from the patient, gene and clinical vectors corresponding to each component tensor. Patient membership proportions in the identified verotypes were utilized in a Cox proportional hazards model to predict their survival.ResultsQualitative evaluation of the verotypes obtained by tensor factorization indicates that they correspond to clinically meaningful breast cancer subtypes. While some components correspond to the known HER2- or ER-positive breast cancer subtypes, other components correspond to a variant of triple negative subtype and a cohort of patients with high mutation load of tumor suppressor genes. Quantitative evaluation indicates that the Cox model utilizing computationally discovered breast cancer verotypes is more accurate (AUC=0.5796) at predicting patient survival than the Cox models utilizing random patient membership proportions in cancer subtypes (AUC=0.4056) as well as patient membership proportions in genotypes (AUC=0.4731) and phenotypes (AUC=0.5047) obtained by non-negative factorization of the somatic mutation and clinical matrices.ConclusionNon-negative factorization of a binary tensor constructed from clinical and genomic data enables high-throughput discovery of breast cancer verotypes that are effective at predicting patient survival.

scholarly journals The Leptin Axis and Its Association With the Adaptive Immune System in Breast Cancer

2021 ◽  
Vol 12 ◽  
Author(s):  
Laura García-Estevez ◽  
Silvia González-Martínez ◽  
Gema Moreno-Bueno
Keyword(s):  
Breast Cancer ◽  
Adipose Tissue ◽  
Immune System ◽  
Immune Cells ◽  
Leptin Receptor ◽  
Adaptive Immune System ◽  
Tumor Infiltrating Lymphocytes ◽  
Cancer Subtypes ◽  
Adaptive Immune ◽  
Infiltrating Lymphocytes

Adipose tissue secretes various peptides, including leptin. This hormone acts through the leptin receptor (Ob-R), which is expressed ubiquitously on the surface of various cells, including breast cancer cells and immune cells. Increasing evidence points to an interaction between the tumor microenvironment, tumor cells, and the immune system. Leptin plays an important role in breast cancer tumorigenesis and may be implicated in activation of the immune system. While breast cancer cannot be considered an immunogenic cancer, the triple-negative subtype is an exception. Specific immune cells - tumor infiltrating lymphocytes - are involved in the immune response and act as predictive and prognostic factors in certain breast cancer subtypes. The aim of this article is to review the interaction between adipose tissue, through the expression of leptin and its receptor, and the adaptive immune system in breast cancer.

scholarly journals Prediction of Distant Metastatic Recurrence by Tumor-Infiltrating Lymphocytes in Hormone Receptor-Positive Breast Cancer

2020 ◽  
Author(s):  
Koji Takada ◽  
Shinichiro Kashiwagi ◽  
Yuka Asano ◽  
Wataru Goto ◽  
Tamami Morisaki ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Hormone Receptor ◽  
Univariate Analysis ◽  
Tumor Infiltrating Lymphocytes ◽  
Distant Metastases ◽  
University Hospital ◽  
Metastatic Recurrence ◽  
Cancer Subtypes ◽  
Hormone Receptor Positive ◽  
Infiltrating Lymphocytes

Abstract Background: Breast cancer subtypes are known to have different sites of metastatic recurrence. Distant metastases are often seen during the post-operative course in patients with human epidermal growth factor receptor 2 (HER2)-enriched breast cancer (HER2BC) and triple-negative breast cancer (TNBC) while being relatively rare in those with hormone receptor-positive and HER2-negative breast cancer (HR+HER2-BC). Tumor-infiltrating lymphocytes (TILs) can serve as an index to monitor tumor immune microenvironment and possibly predict the prognosis and therapeutic effect in breast cancer. This study aimed to investigate the correlation between TIL density and recurrence site in HR+HER2-BC.Methods: Four-hundred and seventy-one patients with HR+HER2-BC underwent surgery as the first treatment and received adjuvant endocrine therapy except adjuvant chemotherapy at the Osaka City University Hospital from April 2007 to October 2015. To evaluate tumor morphology and examine TILs, needle biopsy specimens were used. Morphological assessment was conducted using conventional hematoxylin and eosin staining.Results: Forty-two patients had a recurrence of breast cancer. In patients with no TIL density, local recurrence was significantly less (p = 0.022), while distant metastases were significantly more (p = 0.015) compared to those in patients with TIL density. Therefore, for the prediction of distant metastases in HR+HER2-BC without chemotherapy, TILs could be used as predictors in univariate analysis (p = 0.015, odds ratio [OR] = 0.127), although not as independent factors (p = 0.285, OR = 0.144).Conclusions: We concluded that TILs may be able to predict distant metastatic recurrence in stages I–II of HR+HER2-BC.

Sign in / Sign up

Export Citation Format

Share Document