Dataset Information

Integrative Models of Histopathological Image Features and Omics Data Predict Survival in Head and Neck Squamous Cell Carcinoma.

ABSTRACT: Background:Both histopathological image features and genomics data were associated with survival outcome of cancer patients. However, integrating features of histopathological images, genomics and other omics for improving prognosis prediction has not been reported in head and neck squamous cell carcinoma (HNSCC). Methods:A dataset of 216 HNSCC patients was derived from the Cancer Genome Atlas (TCGA) with information of clinical characteristics, genetic mutation, RNA sequencing, protein expression and histopathological images. Patients were randomly assigned into training (n = 108) or validation (n = 108) sets. We extracted 593 quantitative image features, and used random forest algorithm with 10-fold cross-validation to build prognostic models for overall survival (OS) in training set, then compared the area under the time-dependent receiver operating characteristic curve (AUC) in validation set. Results:In validation set, histopathological image features had significant predictive value for OS (5-year AUC = 0.784). The histopathology + omics models showed better predictive performance than genomics, transcriptomics or proteomics alone. Moreover, the multi-omics model incorporating image features, genomics, transcriptomics and proteomics reached the maximal 1-, 3-, and 5-year AUC of 0.871, 0.908, and 0.929, with most significant survival difference (HR = 10.66, 95%CI: 5.06-26.8, p < 0.001). Decision curve analysis also revealed a better net benefit of multi-omics model. Conclusion:The histopathological images could provide complementary features to improve prognostic performance for HNSCC patients. The integrative model of histopathological image features and omics data might serve as an effective tool for survival prediction and risk stratification in clinical practice.

SUBMITTER: Zeng H

PROVIDER: S-EPMC7658095 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Integrative Models of Histopathological Image Features and Omics Data Predict Survival in Head and Neck Squamous Cell Carcinoma.

Zeng Hao H Chen Linyan L Huang Yeqian Y Luo Yuling Y Ma Xuelei X

Frontiers in cell and developmental biology 20201029

<h4>Background</h4>Both histopathological image features and genomics data were associated with survival outcome of cancer patients. However, integrating features of histopathological images, genomics and other omics for improving prognosis prediction has not been reported in head and neck squamous cell carcinoma (HNSCC).<h4>Methods</h4>A dataset of 216 HNSCC patients was derived from the Cancer Genome Atlas (TCGA) with information of clinical characteristics, genetic mutation, RNA sequencing, p ...[more]

PMID: 33195188

Similar Datasets

Project description:UnlabelledEpidermal growth factor receptor (EGFR) is a well-characterized protooncogene that has been shown to promote tumor progression in solid cancers. Clinical results for EGFR targeting with specific monoclonal antibodies (mAbs) such as cetuximab and panitumumab are promising; however, most studies indicate that only a subgroup of patients receiving the mAbs benefit from the immunotherapy, independent of EGFR expression level. To understand the in vivo kinetics of antibody delivery and localization, we performed small-animal PET studies with (64)Cu-labeled panitumumab in xenografts derived from 3 cell lines of human head and neck squamous cell carcinoma (HNSCC).MethodsNude mice bearing HNSCC tumors with different levels of EGFR expression were imaged with small-animal PET using (64)Cu-1,4,7,10-tetraazacyclododecane-N,N',N'',N'''-tetraacetic acid (DOTA)-panitumumab. Antibody distribution in the tumors was confirmed by ex vivo immunostaining using panitumumab and fluorescein 5(6)-isothiocyanate (FITC) panitumumab. CD31 immunostaining and Evans blue assay were also performed to assess the tumor vascular density and permeability.ResultsAmong these 3 tumor models, UM-SCC-22B tumors with the lowest EGFR protein expression showed the highest (64)Cu-DOTA-panitumumab accumulation, whereas SQB20 tumors with the highest EGFR expression showed the lowest (64)Cu-DOTA-panitumumab accumulation. Ex vivo staining demonstrated that SQB20 cells still had extremely high EGFR expression after forming tumors in nude mice, indicating that the low uptake of (64)Cu-DOTA-panitumumab in SQB20 tumors was not due to the loss of EGFR expression. The results from CD31 immunostaining and Evans blue permeability assay suggest that the low vessel density, poor vascular permeability, and binding site barrier are likely responsible for the overall low tumor uptake of the highly EGFR-expressing SQB20 tumors.ConclusionThe results from this study provide a possible explanation for the lack of an observed correlation between therapeutic efficacy of cetuximab and panitumumab and EGFR expression level as determined by immunohistochemistry or fluorescent in situ hybridization and may shed new light on the complications of anti-EGFR mAb therapy for HNSCC and other malignancies.

Dataset Information

Integrative Models of Histopathological Image Features and Omics Data Predict Survival in Head and Neck Squamous Cell Carcinoma.

Publications

Integrative Models of Histopathological Image Features and Omics Data Predict Survival in Head and Neck Squamous Cell Carcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure