Deep learning on tertiary lymphoid structures in hematoxylin-eosin predicts cancer prognosis and immunotherapy response
Ontology highlight
ABSTRACT:
SUBMITTER: Chen Z
PROVIDER: S-EPMC10959936 | biostudies-literature | 2024 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Ovarian cancer (OC) has the lowest survival rate among gynecologic malignancies. Ectopic lymphocyte aggregates, namely tertiary lymphoid structures (TLSs), have been reported as positive biomarkers for tumor prognosis. However, the related gene signature of tertiary lymphoid structure in ovarian cancer was less understood. Therefore, this study first exhibited the organizational patterns of tertiary lymphoid structure by H&E staining and immunohistochemistry (IHC), and confirmed the improved survival values of tertiary lymphoid structure and quantified tumor-infiltrating lymphocytes (CD20+ B cells and CD8+ T cells) in ovarian cancer patients. Secondly, we collected the genes involved in tertiary lymphoid structure from databases. By the univariate regression analysis, the tertiary lymphoid structure gene signature (CETP, CCR7, SELL, LAMP3, CCL19, CXCL9, CXCL10, CXCL11, and CXCL13) with prognostic value, characteristically of ovarian cancer, was constructed in the TCGA dataset and validated in the GSE140082 dataset. Thirdly, by performing CIBERSORT and Tumor Immune Dysfunction and Exclusion (TIDE) analysis, we found that the high expression of this gene signature was positively correlated with developed immune infiltration and reduced immune escape. The improved IPS score and application in the IMvigor210 dataset received PD-L1 proved the predictive value of immunotherapy for this gene signature. Furthermore, this signature showed a better correlation between tumor mutation burden and classical checkpoint genes. In conclusion, Tertiary lymphoid structure plays important role in tumor immunity and the gene signature can be evaluated as a biomarker for predicting prognosis and guiding immunotherapy in ovarian cancer.
| S-EPMC9871364 | biostudies-literature
Project description:IntroductionCholangiocarcinoma (CCA) is a malignant tumor of the biliary epithelium with a poor prognosis. The lack of biomarkers to predict therapeutic response and prognosis is one of the major challenges for CCA treatment. Tertiary lymphoid structures (TLS) provide a local and pivotal microenvironment for tumor immune responses. The prognostic value and clinical relevance of TLS in CCA remain unclear. We aimed to explore the characteristics and clinical significance of TLS in CCA.MethodsWe investigated the prognostic value and clinical relevance of TLS in CCA using a surgery cohort containing 471 CCA patients (cohort 1) and an immunotherapy cohort containing 100 CCA patients (cohort 2). Hematoxylin and eosin (H&E) and immunohistochemical (IHC) staining were used to evaluate the maturity of TLS. Multiplex IHC (mIHC) was employed to characterize the composition of TLS.ResultsDifferent maturity of TLS were observed in CCA tissue sections. Strong staining of the four-gene signature including PAX5, TCL1A, TNFRSF13C, and CD79A were found in TLS regions. A high density of intra-tumoral TLS (T-score high) were significantly correlated with longer overall survival (OS) both in CCA cohort 1 (p = 0.002) and cohort 2 (p = 0.01), whereas a high density of peri-tumoral TLS (P-score high) were associated with shorter OS in these two cohorts (p = 0.003 and p = 0.03, respectively).ConclusionThe established four-gene signature efficiently identified the TLS in CCA tissues. The abundance and spatial distribution of TLS were significantly correlated with the prognosis and immune checkpoint inhibitors (ICIs) immunotherapy response of CCA patients. The presence of intra-tumoral TLS are positive prognostic factors for CCA, which provide a theoretical basis for the future diagnosis and treatment of CCA.
| S-EPMC10206168 | biostudies-literature
Project description:Tertiary lymphoid structures (TLSs) are part of immune response against cancer. Their high density and high diameter have been shown to be associated with prognosis in different cancer types. The aim of this study was to examine the prognostic significance of TLS density and diameter in gastric cancer and reproducibility of their assessments. TLS densities and maximal TLS diameter were assessed from hematoxylin-eosin (HE) stained slides of 721 surgically treated gastric cancer patients from two hospitals in Finland. Mortality hazard ratios (HRs) for TLS densities and maximal TLS diameter were analyzed. TLS densities and maximal TLS diameter were assessed with moderate interobserver agreement (Cohen's kappa 0.50-0.62). Maximal TLS density was not associated with survival (adjusted HR 0.85, 95% CI 0.70-1.02) and neither was hotspot TLS density (adjusted HR 0.85, 95% CI 0.70-1.02). High maximal TLS diameter was associated with longer survival in overall study population (adjusted HR 0.74, 95% CI 0.61-0.89) and in diffuse type subgroup (adjusted HR 0.65, 95% CI 0.50-0.85). In conclusion, high maximal TLS diameter is associated with improved survival in gastric cancer and can be assessed from HE-stained slides. Its prognostic value might be limited to diffuse histological type.
| S-EPMC10092160 | biostudies-literature
Project description:Substantial progress has been made in using deep learning for cancer detection and diagnosis in medical images. Yet, there is limited success on prediction of treatment response and outcomes, which has important implications for personalized treatment strategies. A significant hurdle for clinical translation of current data-driven deep learning models is lack of interpretability, often attributable to a disconnect from the underlying pathobiology. Here, we present a biology-guided deep learning approach that enables simultaneous prediction of the tumor immune and stromal microenvironment status as well as treatment outcomes from medical images. We validate the model for predicting prognosis of gastric cancer and the benefit from adjuvant chemotherapy in a multi-center international study. Further, the model predicts response to immune checkpoint inhibitors and complements clinically approved biomarkers. Importantly, our model identifies a subset of mismatch repair-deficient tumors that are non-responsive to immunotherapy and may inform the selection of patients for combination treatments.
| S-EPMC10447467 | biostudies-literature
Project description:Treatment with immune checkpoint blockade (ICB) has revolutionized cancer therapy. Until now, predictive biomarkers1-10 and strategies to augment clinical response have largely focused on the T cell compartment. However, other immune subsets may also contribute to anti-tumour immunity11-15, although these have been less well-studied in ICB treatment16. A previously conducted neoadjuvant ICB trial in patients with melanoma showed via targeted expression profiling17 that B cell signatures were enriched in the tumours of patients who respond to treatment versus non-responding patients. To build on this, here we performed bulk RNA sequencing and found that B cell markers were the most differentially expressed genes in the tumours of responders versus non-responders. Our findings were corroborated using a computational method (MCP-counter18) to estimate the immune and stromal composition in this and two other ICB-treated cohorts (patients with melanoma and renal cell carcinoma). Histological evaluation highlighted the localization of B cells within tertiary lymphoid structures. We assessed the potential functional contributions of B cells via bulk and single-cell RNA sequencing, which demonstrate clonal expansion and unique functional states of B cells in responders. Mass cytometry showed that switched memory B cells were enriched in the tumours of responders. Together, these data provide insights into the potential role of B cells and tertiary lymphoid structures in the response to ICB treatment, with implications for the development of biomarkers and therapeutic targets.
| S-EPMC8762581 | biostudies-literature
Project description:Single image super-resolution is an important computer vision task with applications including remote sensing, medical imaging, and surveillance. Modern work on super-resolution utilizes deep learning to synthesize high resolution (HR) images from low resolution images (LR). With the increased utilization of digitized whole slide images (WSI) in pathology workflows, digital pathology has emerged as a promising domain for super-resolution. Despite extensive existing research into super-resolution, there remain challenges specific to digital pathology. Here, we investigated image augmentation techniques for hematoxylin and eosin (H&E) WSI super-resolution and model generalizability across diverse tissue types. In addition, we investigated shortcomings with common quality metrics (peak signal-to-noise ratio (PSNR), structure similarity index (SSIM)) by conducting a perceptual quality survey for super-resolved pathology images. High performing deep super-resolution models were used to generate 20X HR images from LR images (5X or 10X equivalent) for 11 different tissues and 30 human evaluators were asked to score the quality of the generated versus the ground truth 20X HR images. The scores given by a human rater and the PSNR or the SSIM were compared to investigate the correlation between model training parameters. We found that models trained on multiple tissues generalized better than those trained on a single tissue type. We also found that PSNR correlated with perceptual quality (R = 0.26) less accurately than did SSIM (R = 0.64), suggesting that the SSIM quality metric is insufficient. The methods proposed in this study can be used to virtually magnify H&E images with better perceptual quality than interpolation methods (i.e., bicubic interpolation) commonly implemented in digital pathology software. The impact of deep SISR methods is more notable when scaling to 4X is needed, such as in the case of super-resolving a low magnification WSI from 10X to 40X.
| S-EPMC9577134 | biostudies-literature
Project description:Deep learning applications are emerging as promising new tools that can support the diagnosis and classification of different cancer types. While such solutions hold great potential for hematological malignancies, there have been limited studies describing the use of such applications in this field. The rapid diagnosis of double/triple-hit lymphomas (DHLs/THLs) involving MYC, BCL2 and/or BCL6 rearrangements is obligatory for optimal patient care. Here, we present a novel deep learning tool for diagnosing DHLs/THLs directly from scanned images of biopsy slides. A total of 57 biopsies, including 32 in a training set (including five DH lymphoma cases) and 25 in a validation set (including 10 DH/TH cases), were included. The DHL-classifier demonstrated a sensitivity of 100%, a specificity of 87% and an AUC of 0.95, with only two false positive cases, compared to FISH. The DHL-classifier showed a 92% predictive value as a screening tool for performing conventional FISH analysis, over-performing currently used criteria. The work presented here provides the proof of concept for the potential use of an AI tool for the identification of DH/TH events. However, more extensive follow-up studies are required to assess the robustness of this tool and achieve high performances in a diverse population.
| S-EPMC10650414 | biostudies-literature
Project description:BackgroundIntratumoral tertiary lymphoid structures (iTLS) in hepatocellular carcinoma (HCC) are associated with improved survival and may influence treatment decisions. However, their non-invasive detection remains challenging in HCC. We aim to develop a non-invasive model using baseline contrast-enhanced MRI to predict the iTLS status.MethodsA total of 660 patients with HCC who underwent surgery were retrospectively recruited from four centers between October 2015 and January 2023 and divided into training, internal test, and external validation sets. After features dimensionality and selection, corresponding features were used to construct transfer learning radiomic (TLR) models for diagnosing iTLS, and model interpretability was explored with pathway analysis in The Cancer Genome Atlas-Liver HCC. The performances of models were assessed using the area under the receiver operating characteristic curve (AUC). The log-rank test was used to evaluate the prognostic value of the TLR model. The combination therapy set of 101 patients with advanced HCC treated with first-line anti-programmed death 1 or ligand 1 plus antiangiogenic treatment between January 2021 and January 2024 was used to investigate the value of the TLR model for evaluating the treatment response.ResultsThe presence of iTLS was identified in 46.0% (n=308) patients. The TLR model demonstrated excellent performance in predicting the presence of iTLS in training (AUC=0.91, 95% CI: 0.87, 0.94), internal test (AUC=0.85, 95% CI: 0.77, 0.93) and external validation set (AUC=0.85, 95% CI: 0.81, 0.90). The TLR model-predicted iTLS group has favorable overall survival (HR=0.66; 95% CI: 0.48, 0.90; p=0.007) and relapse-free survival (HR=0.64; 95% CI: 0.48, 0.85; p=0.001) in the external validation set. The model-predicted iTLS status was associated with inflammatory response and specific tumor-associated signaling activation (all p<0.001). The proportion of treatment responders was significantly higher in the model-predicted group with iTLS than in the group without iTLS (36% vs 13.73%, p=0.009).ConclusionThe TLR model has indicated accurate prediction of iTLS status, which may assist in the risk stratification for patients with HCC in clinical practice.
| S-EPMC11881188 | biostudies-literature
Project description:To investigate tumor immune microenvironment in cutaneous angiosarcoma, we performed comprehensive RNA sequencing using Next-generation sequencer
2022-12-03 | GSE203215 | GEO
Project description:BackgroundTertiary lymphoid structures (TLSs) are dense accumulations of lymphocytes in inflamed peripheral tissues, including cancer, and are associated with improved survival and response to immunotherapy in various solid tumors. Histological TLS quantification has been proposed as a novel predictive and prognostic biomarker, but lack of standardized methods of TLS characterization hampers assessment of TLS densities across different patients, diseases, and clinical centers.MethodsWe introduce an approach based on HookNet-TLS, a multi-resolution deep learning model, for automated and unbiased TLS quantification and identification of germinal centers in routine hematoxylin and eosin stained digital pathology slides. We developed HookNet-TLS using n = 1019 manually annotated TCGA slides from clear cell renal cell carcinoma, muscle-invasive bladder cancer, and lung squamous cell carcinoma.ResultsHere we show that HookNet-TLS automates TLS quantification across multiple cancer types achieving human-level performance and demonstrates prognostic associations similar to visual assessment.ConclusionsHookNet-TLS has the potential to be used as a tool for objective quantification of TLS in routine H&E digital pathology slides. We make HookNet-TLS publicly available to promote its use in research.
| S-EPMC10770129 | biostudies-literature