scholarly journals Detecting immunotherapy-sensitive subtype in gastric cancer using histologic image-based deep learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Munetoshi Hinata ◽  
Tetsuo Ushiku
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
External Validation ◽  
Area Under The Curve ◽  
The Cancer Genome Atlas ◽  
Molecular Testing ◽  
Favorable Result ◽  
Gastric Cancers ◽  
Barr Virus ◽  
Epstein Barr

AbstractImmune checkpoint inhibitor (ICI) therapy is widely used but effective only in a subset of gastric cancers. Epstein–Barr virus (EBV)-positive and microsatellite instability (MSI) / mismatch repair deficient (dMMR) tumors have been reported to be highly responsive to ICIs. However, detecting these subtypes requires costly techniques, such as immunohistochemistry and molecular testing. In the present study, we constructed a histology-based deep learning model that aimed to screen this immunotherapy-sensitive subgroup efficiently. We processed whole slide images of 408 cases of gastric adenocarcinoma, including 108 EBV, 58 MSI/dMMR, and 242 other subtypes. Many images generated by data augmentation of the learning set were used for training convolutional neural networks to establish an automatic detection platform for EBV and MSI/dMMR subtypes, and the test sets of images were used to verify the learning outcome. Our model detected the subgroup (EBV + MSI/dMMR tumors) with high accuracy in test cases with an area under the curve of 0.947 (0.901–0.992). This result was slightly better than when EBV and MSI/dMMR tumors were detected separately. In an external validation cohort including 244 gastric cancers from The Cancer Genome Atlas database, our model showed a favorable result for detecting the “EBV + MSI/dMMR” subgroup with an AUC of 0.870 (0.809–0.931). In addition, a visualization of the trained neural network highlighted intraepithelial lymphocytosis as the ground for prediction, suggesting that this feature is a discriminative characteristic shared by EBV and MSI/dMMR tumors. Histology-based deep learning models are expected to be used for detecting EBV and MSI/dMMR gastric cancers as economical and less time-consuming alternatives, which may help to effectively stratify patients who respond to ICIs.

scholarly journals Deep learning detects virus presence in cancer histology

2019 ◽  
Author(s):  
Jakob Nikolas Kather ◽  
Jefree Schulte ◽  
Heike I. Grabsch ◽  
Chiara Loeffler ◽  
Hannah Muti ◽  
...  
Keyword(s):  
Deep Learning ◽  
Epstein Barr Virus ◽  
Human Cancer ◽  
Low Cost ◽  
External Validation ◽  
Area Under The Curve ◽  
Oncogenic Viruses ◽  
Barr Virus ◽  
Molecular Tests ◽  
Epstein Barr

AbstractOncogenic viruses like human papilloma virus (HPV) or Epstein Barr virus (EBV) are a major cause of human cancer. Viral oncogenesis has a direct impact on treatment decisions because virus-associated tumors can demand a lower intensity of chemotherapy and radiation or can be more susceptible to immune check-point inhibition. However, molecular tests for HPV and EBV are not ubiquitously available.We hypothesized that the histopathological features of virus-driven and non-virus driven cancers are sufficiently different to be detectable by artificial intelligence (AI) through deep learning-based analysis of images from routine hematoxylin and eosin (HE) stained slides. We show that deep transfer learning can predict presence of HPV in head and neck cancer with a patient-level 3-fold cross validated area-under-the-curve (AUC) of 0.89 [0.82; 0.94]. The same workflow was used for Epstein-Barr virus (EBV) driven gastric cancer achieving a cross-validated AUC of 0.80 [0.70; 0.92] and a similar performance in external validation sets. Reverse-engineering our deep neural networks, we show that the key morphological features can be made understandable to humans.This workflow could enable a fast and low-cost method to identify virus-induced cancer in clinical trials or clinical routine. At the same time, our approach for feature visualization allows pathologists to look into the black box of deep learning, enabling them to check the plausibility of computer-based image classification.

scholarly journals MSI and EBV Positive Gastric Cancer’s Subgroups and Their Link with Novel Immunotherapy

2020 ◽  
Vol 9 (5) ◽  
pp. 1427 ◽  
Author(s):  
Maria Grazia Rodriquenz ◽  
Giandomenico Roviello ◽  
Alberto D’Angelo ◽  
Daniele Lavacchi ◽  
Franco Roviello ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Chromosomal Instability ◽  
Epstein Barr Virus ◽  
Genetic Alterations ◽  
The Cancer Genome Atlas ◽  
Gastric Cancers ◽  
Barr Virus ◽  
Cancer Genome Atlas ◽  
Epstein Barr ◽  
Genome Atlas

Gastric cancers have been historically classified based on histomorphologic features. The Cancer Genome Atlas network reported the comprehensive identification of genetic alterations associated with gastric cancer, identifying four distinct subtypes— Epstein-Barr virus (EBV)-positive, microsatellite-unstable/instability (MSI), genomically stable and chromosomal instability. In particular, EBV-positive and MSI gastric cancers seem responsive to novel immunotherapies drugs. The aim of this review is to describe MSI and EBV positive gastric cancer’s subgroups and their relationship with novel immunotherapy.

scholarly journals DeepRePath: Identifying the Prognostic Features of Early-Stage Lung Adenocarcinoma Using Multi-Scale Pathology Images and Deep Convolutional Neural Networks

Cancers ◽  
2021 ◽  
Vol 13 (13) ◽  
pp. 3308
Author(s):  
Won Sang Shim ◽  
Kwangil Yim ◽  
Tae-Jung Kim ◽  
Yeoun Eun Sung ◽  
Gyeongyun Lee ◽  
...  
Keyword(s):  
Lung Adenocarcinoma ◽  
Early Stage ◽  
External Validation ◽  
Area Under The Curve ◽  
The Cancer Genome Atlas ◽  
Deep Convolutional Neural Networks ◽  
Prognostic Features ◽  
Multi Scale ◽  
Model Based ◽  
Number Of Patients

The prognosis of patients with lung adenocarcinoma (LUAD), especially early-stage LUAD, is dependent on clinicopathological features. However, its predictive utility is limited. In this study, we developed and trained a DeepRePath model based on a deep convolutional neural network (CNN) using multi-scale pathology images to predict the prognosis of patients with early-stage LUAD. DeepRePath was pre-trained with 1067 hematoxylin and eosin-stained whole-slide images of LUAD from the Cancer Genome Atlas. DeepRePath was further trained and validated using two separate CNNs and multi-scale pathology images of 393 resected lung cancer specimens from patients with stage I and II LUAD. Of the 393 patients, 95 patients developed recurrence after surgical resection. The DeepRePath model showed average area under the curve (AUC) scores of 0.77 and 0.76 in cohort I and cohort II (external validation set), respectively. Owing to low performance, DeepRePath cannot be used as an automated tool in a clinical setting. When gradient-weighted class activation mapping was used, DeepRePath indicated the association between atypical nuclei, discohesive tumor cells, and tumor necrosis in pathology images showing recurrence. Despite the limitations associated with a relatively small number of patients, the DeepRePath model based on CNNs with transfer learning could predict recurrence after the curative resection of early-stage LUAD using multi-scale pathology images.

scholarly journals The prevalence of the most important viral infections in renal transplant recipients in Serbia

2012 ◽  
Vol 64 (4) ◽  
pp. 1285-1296 ◽  
Author(s):  
Maja Cupic ◽  
Ivana Lazarevic ◽  
Vera Pravica ◽  
Ana Banko ◽  
Danijela Karalic ◽  
...  
Keyword(s):  
Renal Transplant ◽  
Viral Infections ◽  
Opportunistic Infections ◽  
Uv Light ◽  
Molecular Testing ◽  
Renal Transplant Recipients ◽  
Transplant Recipients ◽  
Chi Square ◽  
Barr Virus ◽  
Epstein Barr

Viruses are the main cause of opportunistic infections after kidney transplantation. The aim of this study was to determine the prevalence of cytomegalovirus (CMV), Epstein-Barr virus (EBV), B. K. virus (BKV) and John Cunningham virus (JCV) infections in renal transplant recipients (RTR). This retrospective study of 112 RTR investigated the presence of CMV, EBV and polyomaviruses DNA in plasma and/or urine by PCR. The visualization of PCR products was performed by electrophoresis on 2% agarose gel stained with ethidium bromide and photographed under a UV light. The chi-square test was used for statistical analysis. CMV DNA was detected in 14/112 (12.5%), EBV DNA in 4/49 (8.16%), BKV DNA in 10/31 (32.26%) and JCV DNA in 3/31 (9.68%) RTR. These results show that CMV infection is more often present in RTR compared to other investigated viral infections. In the light of these results, molecular testing could be useful in identifying recipients at high risk of symptomatic post-transplant viral infection.

Comparison of Clinicopathologic Parameters and Survivals Between Epstein-Barr Virus–positive and Her2-positive Gastric Cancers

2017 ◽  
Vol 25 (9) ◽  
pp. 609-614 ◽  
Author(s):  
Cigdem Irkkan ◽  
Serdar Balci ◽  
Gaye Güler Tezel ◽  
Bülent Akinci ◽  
Bülent Yalcin ◽  
...  
Keyword(s):  
Epstein Barr Virus ◽  
Her2 Positive ◽  
Gastric Cancers ◽  
Barr Virus ◽  
Clinicopathologic Parameters ◽  
Epstein Barr

scholarly journals Epstein-Barr Virus-Positive Cancers Show Altered B-Cell Clonality

mSystems ◽  
2018 ◽  
Vol 3 (5) ◽  
Author(s):  
Sara R. Selitsky ◽  
David Marron ◽  
Lisle E. Mose ◽  
Joel S. Parker ◽  
Dirk P. Dittmer
Keyword(s):  
B Cells ◽  
B Cell ◽  
Epstein Barr Virus ◽  
The Cancer Genome Atlas ◽  
Barr Virus ◽  
Cancer Genome Atlas ◽  
Cancer Types ◽  
Epstein Barr ◽  
Tumor Types ◽  
Genome Atlas

ABSTRACTEpstein-Barr virus (EBV) is convincingly associated with gastric cancer, nasopharyngeal carcinoma, and certain lymphomas, but its role in other cancer types remains controversial. To test the hypothesis that there are additional cancer types with high prevalence of EBV, we determined EBV viral expression in all the Cancer Genome Atlas Project (TCGA) mRNA sequencing (mRNA-seq) samples (n= 10,396) from 32 different tumor types. We found that EBV was present in gastric adenocarcinoma and lymphoma, as expected, and was also present in >5% of samples in 10 additional tumor types. For most samples, EBV transcript levels were low, which suggests that EBV was likely present due to infected infiltrating B cells. In order to determine if there was a difference in the B-cell populations, we assembled B-cell receptors for each sample and found B-cell receptor abundance (P≤ 1.4 × 10−20) and diversity (P≤ 8.3 × 10−27) were significantly higher in EBV-positive samples. Moreover, diversity was independent of B-cell abundance, suggesting that the presence of EBV was associated with an increased and altered B-cell population.IMPORTANCEAround 20% of human cancers are associated with viruses. Epstein-Barr virus (EBV) contributes to gastric cancer, nasopharyngeal carcinoma, and certain lymphomas, but its role in other cancer types remains controversial. We assessed the prevalence of EBV in RNA-seq from 32 tumor types in the Cancer Genome Atlas Project (TCGA) and found EBV to be present in >5% of samples in 12 tumor types. EBV infects epithelial cells and B cells and in B cells causes proliferation. We hypothesized that the low expression of EBV in most of the tumor types was due to infiltration of B cells into the tumor. The increase in B-cell abundance and diversity in subjects where EBV was detected in the tumors strengthens this hypothesis. Overall, we found that EBV was associated with an increased and altered immune response. This result is not evidence of causality, but a potential novel biomarker for tumor immune status.

scholarly journals Epstein-Barr Virus miR-BART17-5p Promotes Migration and Anchorage-Independent Growth by Targeting Kruppel-Like Factor 2 in Gastric Cancer

2020 ◽  
Vol 8 (2) ◽  
pp. 258 ◽  
Author(s):  
Jae Hee Yoon ◽  
Kyoungmi Min ◽  
Suk Kyeong Lee
Keyword(s):  
Gastric Cancer ◽  
Gastric Carcinoma ◽  
Epstein Barr Virus ◽  
The Cancer Genome Atlas ◽  
Sequencing Data ◽  
Ags Cells ◽  
Anchorage Independent Growth ◽  
Barr Virus ◽  
Epstein Barr ◽  
Bart Mirnas

Epstein-Barr virus (EBV) infects more than 90% of the global population and is associated with a variety of tumors including nasopharyngeal carcinoma, Hodgkin lymphoma, natural killer/T lymphoma, and gastric carcinoma. In EBV-associated gastric cancer (EBVaGC), highly expressed EBV BamHI A rightward transcripts (BART) miRNAs may contribute to tumorigenesis with limited viral antigens. Despite previous studies on the targets of BART miRNAs, the functions of all 44 BART miRNAs have not been fully clarified. Here, we used RNA sequencing data from the Cancer Genome Atlas to find genes with decreased expression in EBVaGC. Furthermore, we used AGS cells infected with EBV to determine whether expression was reduced by BART miRNA. We showed that the expression of Kruppel-like factor 2 (KLF2) is lower in AGS-EBV cells than in the AGS control. Using bioinformatics analysis, four BART miRNAs were selected to check whether they suppress KLF2 expression. We found that only miR-BART17-5p directly down-regulated KLF2 and promoted gastric carcinoma cell migration and anchorage-independent growth. Our data suggest that KLF2 functions as a tumor suppressor in EBVaGC and that miR-BART17-5p may be a valuable target for effective EBVaGC treatment.

PD-L1 expression in Epstein-Barr virus-infected gastric cancers.

2016 ◽  
Vol 34 (15_suppl) ◽  
pp. 4052-4052 ◽  
Author(s):  
Sarah Derks ◽  
Xiaoyun Liao ◽  
Xinsen Xu ◽  
M. Constanza Camargo ◽  
Anna M Chiaravalli ◽  
...  
Keyword(s):  
Epstein Barr Virus ◽  
Gastric Cancers ◽  
Barr Virus ◽  
Epstein Barr

Clinicopathological features of Epstein–Barr virus associated gastric carcinoma with submucosal invasion.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. 4029-4029
Author(s):  
Hiroki Osumi ◽  
Hiroshi Kawachi ◽  
Toshiyuki Yoshio ◽  
Satoshi Ida ◽  
Yusuke Horiuchi ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Lymph Node ◽  
Epstein Barr Virus ◽  
Lymphovascular Invasion ◽  
Submucosal Invasion ◽  
The Cancer Genome Atlas ◽  
Research Network ◽  
Barr Virus ◽  
Regional Lymph Node Dissection ◽  
Epstein Barr

4029 Background: The incidence of lymph node metastasis (LNM) in pathological T1b (pT1b) gastric cancer (GC) is around 20% and the majority of them have no LNM. The Cancer Genome Atlas Research Network proposed the concept of molecular phenotype classifying GC into 4 phenotypes including Epstein-Barr virus-CIMP (EBV). EBV positive gastric cancer (EBVGC) is associated with a low prevalence of LNM; however, EBV status is not considered in the present indication of endoscopic resection (ER). We aimed to clarify the implication of EBV status for ER of pT1b GC. Methods: Consecutive cases of pT1b GCs treated with curative surgery between 2005 and 2014 were retrospectively analyzed. Tissue microarray was made and EBV-encoded RNA in situ hybridization was performed for evaluation of EBV status. Clinicopathological factors and LNM status were compared between EBVGC and non-EBVGC groups. Results: Among the 1221 pT1b GCs that underwent gastrectomy with regional lymph node dissection, 898 pT1bGCs were eligible in this study. EBVGC accounted for 7.9% (71 of 898) cases. Compared to non-EBVGC, EBVGC was more frequent in males (p = 0.0055), the upper third region (p < 0.0001), showed elevated growth features (p = 0.0059), and was associated with a lower frequency of accompanying ulceration (p = 0.002), greater depth of submucosal invasion (p = 0.017), and lower frequency of lymphatic invasion (p < 0.0001). Frequency of LNM was significantly lower in EBVGC than in non-EBVGC (4.2% vs. 21.9%, p < 0.0001). In EBVGC, tumors without lymphovascular invasion showed significantly lower frequency of LNM than those with lymphovascular invasion (0 of 50, 0%; vs 3 of 21, 14.3%; p = 0.023). Histologically, 84.5% (60 of 71) of EBVGC included carcinomas with lymphoid stroma and/or lace pattern components. Conclusions: pT1b EBVGC is a convincing candidate for ER, regardless of risk factors other than lymphovascular invasion.

scholarly journals Case Report: Epstein-Barr virus Positive Gastric Carcinoma

2019 ◽  
pp. 145-151
Author(s):  
Gasenko E ◽  
Hegmane A ◽  
Plate S ◽  
Zvirbule Z ◽  
Elsberga E ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Overall Survival ◽  
Epstein Barr Virus ◽  
Symptom Control ◽  
Locally Advanced ◽  
Disease Stabilisation ◽  
The Cancer Genome Atlas ◽  
Barr Virus ◽  
Potential Biomarker ◽  
Epstein Barr

In 2014, The Cancer Genome Atlas provided a molecular classification defining Epstein-Barr virus (EBV)-positive gastric cancer as a separate subtype. While its prognostic role is still debatable, emerging potential biomarker role for personalized treatment strategies is already recognized by international guidelines. We report a case with successful combined therapy of a 64-year-old EBV-positive gastric cancer male patient. Patient initially presented with locally advanced gastric cancer, which was treated surgically; three years later patient developed recurrence within the remnant stomach and was treated surgically. Two years after operation patient developed distant metastases and was enrolled in a clinical trials’ (NCT01630083) arm 2: receiving chemotherapy and monoclonal antibody claudiximab. This treatment induced durable disease stabilisation for 34 months. After progression, second line chemotherapy with docetaxel and cisplatin provided additional disease stabilisation and symptom control for 8 months. Patient’s overall survival reached 9.1 years. Presented report shows EBV- ositive gastric cancer case with better overall survival compared to reported average, which contributes to the meaningfulness of its distinction as a separate subtype, evidence that targeted therapy is more effective in selected patient groups, and EBV as an emerging biomarker.

Sign in / Sign up

Export Citation Format

Share Document