Dataset Information

Deep learning model to predict Epstein-Barr virus associated gastric cancer in histology.

ABSTRACT: The detection of Epstein-Barr virus (EBV) in gastric cancer patients is crucial for clinical decision making, as it is related with specific treatment responses and prognoses. Despite its importance, the limited medical resources preclude universal EBV testing. Herein, we propose a deep learning-based EBV prediction method from H&E-stained whole-slide images (WSI). Our model was developed using 319 H&E stained WSI (26 EBV positive; TCGA dataset) from the Cancer Genome Atlas, and 108 WSI (8 EBV positive; ISH dataset) from an independent institution. Our deep learning model, EBVNet consists of two sequential components: a tumor classifier and an EBV classifier. We visualized the learned representation by the classifiers using UMAP. We externally validated the model using 60 additional WSI (7 being EBV positive; HGH dataset). We compared the model's performance with those of four pathologists. EBVNet achieved an AUPRC of 0.65, whereas the four pathologists yielded a mean AUPRC of 0.41. Moreover, EBVNet achieved an negative predictive value, sensitivity, specificity, precision, and F1-score of 0.98, 0.86, 0.92, 0.60, and 0.71, respectively. Our proposed model is expected to contribute to prescreen patients for confirmatory testing, potentially to save test-related cost and labor.

SUBMITTER: Jeong Y

PROVIDER: S-EPMC9630260 | biostudies-literature | 2022 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning model to predict Epstein-Barr virus associated gastric cancer in histology.

Jeong Yeojin Y Cho Cristina Eunbee CE Kim Ji-Eon JE Lee Jonghyun J Kim Namkug N Jung Woon Yong WY Sung Joohon J Kim Ju Han JH Lee Yoo Jin YJ Jung Jiyoon J Pyo Juyeon J Song Jisun J Park Jihwan J Moon Kyoung Min KM Ahn Sangjeong S

Scientific reports 20221102 1

The detection of Epstein-Barr virus (EBV) in gastric cancer patients is crucial for clinical decision making, as it is related with specific treatment responses and prognoses. Despite its importance, the limited medical resources preclude universal EBV testing. Herein, we propose a deep learning-based EBV prediction method from H&E-stained whole-slide images (WSI). Our model was developed using 319 H&E stained WSI (26 EBV positive; TCGA dataset) from the Cancer Genome Atlas, and 108 WSI (8 EBV p ...[more]

PMID: 36323712

Similar Datasets

Project description:ImportanceEpstein-Barr virus (EBV)-associated gastric cancer (EBV-GC) is 1 of 4 molecular subtypes of GC and is confirmed by an expensive molecular test, EBV-encoded small RNA in situ hybridization. EBV-GC has 2 histologic characteristics, lymphoid stroma and lace-like tumor pattern, but projecting EBV-GC at biopsy is difficult even for experienced pathologists.ObjectiveTo develop and validate a deep learning algorithm to predict EBV status from pathology images of GC biopsy.Design, setting, and participantsThis diagnostic study developed a deep learning classifier to predict EBV-GC using image patches of tissue microarray (TMA) and whole slide images (WSIs) of GC and applied it to GC biopsy specimens from GCs diagnosed at Kangbuk Samsung Hospital between 2011 and 2020. For a quantitative evaluation and EBV-GC prediction on biopsy specimens, the area of each class and the fraction in total tissue or tumor area were calculated. Data were analyzed from March 5, 2021, to February 10, 2022.Main outcomes and measuresEvaluation metrics of predictive model performance were assessed on accuracy, recall, precision, F1 score, area under the receiver operating characteristic curve (AUC), and κ coefficient.ResultsThis study included 137 184 image patches from 16 TMAs (708 tissue cores), 24 WSIs, and 286 biopsy images of GC. The classifier was able to classify EBV-GC image patches from TMAs and WSIs with 94.70% accuracy, 0.936 recall, 0.938 precision, 0.937 F1 score, and 0.909 κ coefficient. The classifier was used for predicting and measuring the area and fraction of EBV-GC on biopsy tissue specimens. A 10% cutoff value for the predicted fraction of EBV-GC to tissue (EBV-GC/tissue area) produced the best prediction results in EBV-GC biopsy specimens and showed the highest AUC value (0.8723; 95% CI, 0.7560-0.9501). That cutoff also obtained high sensitivity (0.895) and moderate specificity (0.745) compared with experienced pathologist sensitivity (0.842) and specificity (0.854) when using the presence of lymphoid stroma and a lace-like pattern as diagnostic criteria. On prediction maps, EBV-GCs with lace-like pattern and lymphoid stroma showed the same prediction results as EBV-GC, but cases lacking these histologic features revealed heterogeneous prediction results of EBV-GC and non-EBV-GC areas.Conclusions and relevanceThis study showed the feasibility of EBV-GC prediction using a deep learning algorithm, even in biopsy samples. Use of such an image-based classifier before a confirmatory molecular test will reduce costs and tissue waste.

Project description:Epstein-Barr virus (EBV) nuclear antigen 1 (EBNA1) is the only viral protein consistently expressed in all EBV-associated malignancies, and play a critical role in the onset, progression, and/or maintenance of these tumors. Based on the signature changes at amino acid residue 487, EBNA1 is classified into five distinct subtypes: P-ala, P-thr, V-leu, V-val and V-pro. In the present study, the sequence variations of EBNA1 in EBV-associated gastric carcinoma (EBVaGC) and throat washing (TW) samples of healthy EBV carriers in Guangzhou, southern China, where nasopharyngeal carcinoma (NPC) is endemic, were analyzed by PCR and DNA sequencing. V-val subtype was the most predominant (53.6%, 15/28) in EBVaGC, followed by P-ala (42.9%, 12/28) and V-leu (32.1%, 9/28) subtypes. In TWs of healthy EBV carriers, V-val subtype was also predominant (85.7%, 18/21). The sequence variations of EBNA1 in EBVaGC were similar to those in TW of healthy EBV carriers (p>0.05), suggesting that the EBV strains in EBVaGC might originate from the viral strains prevalent within the background population. The predominance of V-val subtype in EBVaGC in Guangzhou was similar to that in EBVaGC in northern China and Japan, but was different from that in EBVaGC in America, suggesting that the variations of EBNA1 in EBVaGC represent geographic-associated polymorphisms rather than tumor-specific mutations. In addition, the EBNA1 variations in EBVaGC in gastric remnant carcinoma were also determined. V-leu subtype was detected in all 4 (100%) cases, although 2 cases occurred as mixed infection with P-ala subtype. This is different from the predominant V-val subtype in EBVaGC in conventional gastric carcinoma, suggesting that V-leu might be a subtype that adapts particularly well to the microenvironment within the gastric stump and enters the remnant gastric mucosa epithelia easily. This, to our best knowledge, is the first investigation of EBNA1 polymorphisms in EBVaGC from endemic area of NPC.

Dataset Information

Deep learning model to predict Epstein-Barr virus associated gastric cancer in histology.

Publications

Deep learning model to predict Epstein-Barr virus associated gastric cancer in histology.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets