Dataset Information

Comprehensive Computational Pathological Image Analysis Predicts Lung Cancer Prognosis.

ABSTRACT: Pathological examination of histopathological slides is a routine clinical procedure for lung cancer diagnosis and prognosis. Although the classification of lung cancer has been updated to become more specific, only a small subset of the total morphological features are taken into consideration. The vast majority of the detailed morphological features of tumor tissues, particularly tumor cells' surrounding microenvironment, are not fully analyzed. The heterogeneity of tumor cells and close interactions between tumor cells and their microenvironments are closely related to tumor development and progression. The goal of this study is to develop morphological feature-based prediction models for the prognosis of patients with lung cancer.We developed objective and quantitative computational approaches to analyze the morphological features of pathological images for patients with NSCLC. Tissue pathological images were analyzed for 523 patients with adenocarcinoma (ADC) and 511 patients with squamous cell carcinoma (SCC) from The Cancer Genome Atlas lung cancer cohorts. The features extracted from the pathological images were used to develop statistical models that predict patients' survival outcomes in ADC and SCC, respectively.We extracted 943 morphological features from pathological images of hematoxylin and eosin-stained tissue and identified morphological features that are significantly associated with prognosis in ADC and SCC, respectively. Statistical models based on these extracted features stratified NSCLC patients into high-risk and low-risk groups. The models were developed from training sets and validated in independent testing sets: a predicted high-risk group versus a predicted low-risk group (for patients with ADC: hazard ratio = 2.34, 95% confidence interval: 1.12-4.91, p = 0.024; for patients with SCC: hazard ratio = 2.22, 95% confidence interval: 1.15-4.27, p = 0.017) after adjustment for age, sex, smoking status, and pathologic tumor stage.The results suggest that the quantitative morphological features of tumor pathological images predict prognosis in patients with lung cancer.

SUBMITTER: Luo X

PROVIDER: S-EPMC5462113 | biostudies-literature | 2017 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comprehensive Computational Pathological Image Analysis Predicts Lung Cancer Prognosis.

Luo Xin X Zang Xiao X Yang Lin L Huang Junzhou J Liang Faming F Rodriguez-Canales Jaime J Wistuba Ignacio I II Gazdar Adi A Xie Yang Y Xiao Guanghua G

Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer 20161104 3

<h4>Introduction</h4>Pathological examination of histopathological slides is a routine clinical procedure for lung cancer diagnosis and prognosis. Although the classification of lung cancer has been updated to become more specific, only a small subset of the total morphological features are taken into consideration. The vast majority of the detailed morphological features of tumor tissues, particularly tumor cells' surrounding microenvironment, are not fully analyzed. The heterogeneity of tumor ...[more]

PMID: 27826035

Similar Datasets

Project description:PurposeExploring the molecular mechanisms of lung adenocarcinoma (LUAD) is beneficial for developing new therapeutic strategies and predicting prognosis. This study was performed to select core genes related to LUAD and to analyze their prognostic value.MethodsMicroarray datasets from the GEO (GSE75037) and TCGA-LUAD datasets were analyzed to identify differentially coexpressed genes in LUAD using weighted gene coexpression network analysis (WGCNA) and differential gene expression analysis. Functional enrichment analysis was conducted, and a protein-protein interaction (PPI) network was established. Subsequently, hub genes were identified using the CytoHubba plug-in. Overall survival (OS) analyses of hub genes were performed. The Clinical Proteomic Tumor Analysis Consortium (CPTAC) and the Human Protein Atlas (THPA) databases were used to validate our findings. Gene set enrichment analysis (GSEA) of survival-related hub genes were conducted. Immunohistochemistry (IHC) was carried out to validate our findings.ResultsWe identified 486 differentially coexpressed genes. Functional enrichment analysis suggested these genes were primarily enriched in the regulation of epithelial cell proliferation, collagen-containing extracellular matrix, transforming growth factor beta binding, and signaling pathways regulating the pluripotency of stem cells. Ten hub genes were detected using the maximal clique centrality (MCC) algorithm, and four genes were closely associated with OS. The CPTAC and THPA databases revealed that CHRDL1 and SPARCL1 were downregulated at the mRNA and protein expression levels in LUAD, whereas SPP1 was upregulated. GSEA demonstrated that DNA-dependent DNA replication and catalytic activity acting on RNA were correlated with CHRDL1 and SPARCL1 expression, respectively. The IHC results suggested that CHRDL1 and SPARCL1 were significantly downregulated in LUAD.ConclusionsOur study revealed that survival-related hub genes closely correlated with the initiation and progression of LUAD. Furthermore, CHRDL1 and SPARCL1 are potential therapeutic and prognostic indicators of LUAD.

Project description:BackgroundThe long non-coding RNA cancer susceptibility candidate (CASC) has abnormal expression in lung cancer tissues and may correlate with lung cancer prognosis. This study aimed to comprehensively evaluate the association between CASC expression and the cancer prognosis.MethodsPubMed, Embase, Web of Science, Google Scholar, Cochrane Library, and China National Knowledge Infrastructure databases were searched until April 1, 2023, to obtain the relevant literature. Studies that met the predefined eligibility criteria were included, and their quality was independently assessed by 2 investigators according to the Newcastle-Ottawa Scale (NOS) score. Detailed information was obtained, such as first author, year of publication, and number of patients. Hazard ratio (HR) with a 95% confidence interval (CI) was extracted and grouped to assess the relationship between CASC expression and cancer prognosis. The dichotomous data was merged and shown as the odds ratio (OR) with a 95% CI was extracted to assess the relationship between CASC expression and clinicopathological parameters.ResultsA total of 12 studies with 746 patients with lung cancer were included in the meta-analysis. The expression levels of lncRNA CASC2 and CASC7 were decreased, while those of CASC9, 11, 15, and 19 were induced in lung cancer tissues compared with paracancerous tissues. In the population with low CASC expression (CASC2 and CASC7), high CASC expression indicated a good lung cancer prognosis (HR = 0.469; 95% CI, 0.271-0.668). Conversely, in the population with high CASC expression (CASC9, 11, 15, and 19), high CASC expression predicted a poor lung cancer outcome (HR = 1.910; 95% CI, 1.628-2.192). High CASC expression also predicted worse disease-free survival (DFS) (HR = 2.803; 95% CI, 1.804-6.319). Combined OR with 95% CI revealed an insignificant positive association between high CASC expression and advanced TNM stage (OR = 1.061; 95% CI, 0.775-1.454), LNM (OR = 0.962; 95% CI, 0.724-1.277), tumor size (OR = 0.942; 95% CI, 0.667-1.330), and histological grade (OR = 1.022; 95% CI, 0.689-1.517).ConclusionThe CASC expression levels negatively correlate with lung cancer prognosis. Therefore, CASC expression may serve as a prognostic marker and a potential therapeutic target for lung cancer.

Project description:Background: The long non-coding RNA Linc00152 stimulates tumor progression in cancer. However, its clinical significance and biological functions in lung adenocarcinoma remains unknown. We evaluate the expression of Linc00152 in lung adenocarcinoma and its possible correlation with clinicopathologic features and patient survival to reveal its biological effects in cancer progression and prognosis. Methods: Total RNA extraction was performed on 110 pairs of lung adenocarcinoma and adjacent normal tissue samples, and then RT-qPCR was conducted. Chi-square test analysis was used to calculate the correlation between pathological parameters and the Linc00152 mRNA levels. Kaplan-Meier and Cox proportional hazards analyses were used to analyze the overall survival (OS) and disease-free survival (DFS) rates. We also detected the potential functional effects of overexpression and knockdown of Linc00152 in vitro cell proliferation, tumor cell invasion and migration, as well as in vivo nude mouse xenograft and metastasis models. Results: The Linc00152 expression levels were higher in lung adenocarcinoma samples than in the adjacent normal tissues. Linc00152 expression levels tightly correlated with lymph node metastasis station, remote metastasis and TNM staging. The Kaplan-Meier analysis suggested that high Linc00152 expression caused significantly poorer OS and DFS rates, and a multivariate analysis revealed that Linc00152 was an independent risk factor for both DFS and OS. Overexpression of Linc00152 in lung cancer cells stimulated proliferation, tumor cell invasion and migration. Knockdown of Linc00152 inhibited cell growth and cell invasion and migration. Finally, Linc00152 knockdown inhibited lung tumor growth and tumor metastasis in nude mice models. Conclusions: Our study suggests that Linc00152 independently predicts poor prognosis and promotes tumor progression in lung adenocarcinoma. Linc00152 needs to be considered as a potential molecular target in future cancer pharmacology.

Dataset Information

Comprehensive Computational Pathological Image Analysis Predicts Lung Cancer Prognosis.

Publications

Comprehensive Computational Pathological Image Analysis Predicts Lung Cancer Prognosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets