Dataset Information

Image-Based Molecular Phenotyping of Pancreatic Ductal Adenocarcinoma.

ABSTRACT: To bridge the translational gap between recent discoveries of distinct molecular phenotypes of pancreatic cancer and tangible improvements in patient outcome, there is an urgent need to develop strategies and tools informing and improving the clinical decision process. Radiomics and machine learning approaches can offer non-invasive whole tumor analytics for clinical imaging data-based classification. The retrospective study assessed baseline computed tomography (CT) from 207 patients with proven pancreatic ductal adenocarcinoma (PDAC). Following expert level manual annotation, Pyradiomics was used for the extraction of 1474 radiomic features. The molecular tumor subtype was defined by immunohistochemical staining for KRT81 and HNF1a as quasi-mesenchymal (QM) vs. non-quasi-mesenchymal (non-QM). A Random Forest machine learning algorithm was developed to predict the molecular subtype from the radiomic features. The algorithm was then applied to an independent cohort of histopathologically unclassifiable tumors with distinct clinical outcomes. The classification algorithm achieved a sensitivity, specificity and ROC-AUC (area under the receiver operating characteristic curve) of 0.84 ± 0.05, 0.92 ± 0.01 and 0.93 ± 0.01, respectively. The median overall survival for predicted QM and non-QM tumors was 16.1 and 20.9 months, respectively, log-rank-test p = 0.02, harzard ratio (HR) 1.59. The application of the algorithm to histopathologically unclassifiable tumors revealed two groups with significantly different survival (8.9 and 39.8 months, log-rank-test p < 0.001, HR 4.33). The machine learning-based analysis of preoperative (CT) imaging allows the prediction of molecular PDAC subtypes highly relevant for patient survival, allowing advanced pre-operative patient stratification for precision medicine applications.

SUBMITTER: Kaissis GA

PROVIDER: S-EPMC7141256 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Image-Based Molecular Phenotyping of Pancreatic Ductal Adenocarcinoma.

Kaissis Georgios A GA Ziegelmayer Sebastian S Lohöfer Fabian K FK Harder Felix N FN Jungmann Friederike F Sasse Daniel D Muckenhuber Alexander A Yen Hsi-Yu HY Steiger Katja K Siveke Jens J Friess Helmut H Schmid Roland R Weichert Wilko W Makowski Marcus R MR Braren Rickmer F RF

Journal of clinical medicine 20200307 3

To bridge the translational gap between recent discoveries of distinct molecular phenotypes of pancreatic cancer and tangible improvements in patient outcome, there is an urgent need to develop strategies and tools informing and improving the clinical decision process. Radiomics and machine learning approaches can offer non-invasive whole tumor analytics for clinical imaging data-based classification. The retrospective study assessed baseline computed tomography (CT) from 207 patients with prove ...[more]

PMID: 32155990

Similar Datasets

Project description:Pancreatic ductal adenocarcinoma (PDAC) is a malignancy characterized by a poor prognosis and high mortality rate. Genetic mutations and altered molecular pathways serve as targets in precise therapy. Using next-generation sequencing (NGS), these aberrant alterations can be identified and used to develop strategies that will selectively kill cancerous cells in patients with PDAC. The realization of targeted therapies in patients with PDAC may be summarized by three approaches. First, because oncogenes play a pivotal role in tumorigenesis, inhibition of dysregulated oncogenes is a promising method (Table 3). Numerous researchers are developing strategies to target oncogenes, such as KRAS, NRG1, and NTRK and related molecules, although most of the results are unsatisfactory. Accordingly, emerging strategies are being developed to target these oncogenes, including simultaneously inhibiting multiple molecules or pathways, modification of mutant residues by small molecules, and RNA interference. Second, researchers have attempted to reactivate inactivated tumour suppressors or modulate related molecules. TP53, CDKN2A and SMAD4 are three major tumour suppressors involved in PDAC. Advances have been achieved in clinical and preclinical trials of therapies targeting these three genes, and further investigations are warranted. The TGF-β-SMAD4 signalling pathway plays a dual role in PDAC tumorigenesis and participates in mediating tumour-stroma crosstalk and modulating the tumour microenvironment (TME); thus, molecular subtyping of pancreatic cancer according to the SMAD4 mutation status may be a promising precision oncology technique. Finally, genes such as KDM6A and BRCA have vital roles in maintaining the structural stability and physiological functions of normal chromosomes and are deficient in some patients with PDAC, thus serving as potential targets for correcting these deficiencies and precisely killing these aberrant tumour cells. Recent clinical trials, such as the POLO (Pancreas Cancer Olaparib Ongoing) trial, have reported encouraging outcomes. In addition to genetic event-guided treatment, immunotherapies such as chimeric antigen receptor T cells (CAR-T), antibody-drug conjugates, and immune checkpoint inhibitors also exhibit the potential to target tumours precisely, although the clinical value of immunotherapies as treatments for PDAC is still limited. In this review, we focus on recent preclinical and clinical advances in therapies targeting aberrant genes and pathways and predict the future trend of precision oncology for PDAC.

Project description:Background:Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest solid tumors. The rapid progression of PDAC results in an advanced stage of patients when diagnosed. However, the dynamic molecular mechanism underlying PDAC progression remains far from clear. Methods:The microarray GSE62165 containing PDAC staging samples was obtained from Gene Expression Omnibus and the differentially expressed genes (DEGs) between normal tissue and PDAC of different stages were profiled using R software, respectively. The software program Short Time-series Expression Miner was applied to cluster, compare, and visualize gene expression differences between PDAC stages. Then, function annotation and pathway enrichment of DEGs were conducted by Database for Annotation Visualization and Integrated Discovery. Further, the Cytoscape plugin DyNetViewer was applied to construct the dynamic protein-protein interaction networks and to analyze different topological variation of nodes and clusters over time. The phosphosite markers of stage-specific protein kinases were predicted by PhosphoSitePlus database. Moreover, survival analysis of candidate genes and pathways was performed by Kaplan-Meier plotter. Finally, candidate genes were validated by immunohistochemistry in PDAC tissues. Results:Compared with normal tissues, the total DEGs number for each PDAC stage were 994 (stage I), 967 (stage IIa), 965 (stage IIb), 1027 (stage III), 925 (stage IV), respectively. The stage-course gene expression analysis showed that 30 distinct expressional models were clustered. Kyoto Encyclopedia of Genes and Genomes analysis indicated that the up-regulated DEGs were commonly enriched in five fundamental pathways throughout five stages, including pathways in cancer, small cell lung cancer, ECM-receptor interaction, amoebiasis, focal adhesion. Except for amoebiasis, these pathways were associated with poor PDAC overall survival. Meanwhile, LAMA3, LAMB3, LAMC2, COL4A1 and FN1 were commonly shared by these five pathways and were unfavorable factors for prognosis. Furthermore, by constructing the stage-course dynamic protein interaction network, 45 functional molecular modules and 19 nodes were identified as featured regulators for all PDAC stages, among which the collagen family and integrins were considered as two main regulators for facilitating aggressive progression. Additionally, the clinical relevance analysis suggested that the stage IV featured nodes MLF1IP and ITGB4 were significantly correlated with shorter overall survival. Moreover, 15 stage-specific protein kinases were identified from the dynamic network and CHEK1 was particularly activated at stage IV. Experimental validation showed that MLF1IP, LAMA3 and LAMB3 were progressively increased from tumor initiation to progression. Conclusions:Our study provided a view for a better understanding of the dynamic landscape of molecular interaction networks during PDAC progression and offered potential targets for therapeutic intervention.

Dataset Information

Image-Based Molecular Phenotyping of Pancreatic Ductal Adenocarcinoma.

Publications

Image-Based Molecular Phenotyping of Pancreatic Ductal Adenocarcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets