24
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      A machine learning algorithm predicts molecular subtypes in pancreatic ductal adenocarcinoma with differential response to gemcitabine-based versus FOLFIRINOX chemotherapy

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Purpose

          Development of a supervised machine-learning model capable of predicting clinically relevant molecular subtypes of pancreatic ductal adenocarcinoma (PDAC) from diffusion-weighted-imaging-derived radiomic features.

          Methods

          The retrospective observational study assessed 55 surgical PDAC patients. Molecular subtypes were defined by immunohistochemical staining of KRT81. Tumors were manually segmented and 1606 radiomic features were extracted with PyRadiomics. A gradient-boosted-tree algorithm was trained on 70% of the patients (N = 28) and tested on 30% (N = 17) to predict KRT81+ vs. KRT81- tumor subtypes. A gradient-boosted survival regression model was fit to the disease-free and overall survival data. Chemotherapy response and survival were assessed stratified by subtype and radiomic signature. Radiomic feature importance was ranked.

          Results

          The mean±STDEV sensitivity, specificity and ROC-AUC were 0.90±0.07, 0.92±0.11, and 0.93±0.07, respectively. The mean±STDEV concordance indices between the disease-free and overall survival predicted by the model based on the radiomic parameters and actual patient survival were 0.76±0.05 and 0.71±0.06, respectively. Patients with a KRT81+ subtype experienced significantly diminished median overall survival compared to KRT81- patients (7.0 vs. 22.6 months, HR 4.03, log-rank-test P = <0.001) and a significantly improved response to gemcitabine-based chemotherapy over FOLFIRINOX (10.14 vs. 3.8 months median overall survival, HR 2.33, P = 0.037) compared to KRT81- patients, who responded significantly better to FOLFIRINOX over gemcitabine-based treatment (30.8 vs. 13.4 months median overall survival, HR 2.41, P = 0.027). Entropy was ranked as the most important radiomic feature.

          Conclusions

          The machine-learning based analysis of radiomic features enables the prediction of subtypes of PDAC, which are highly relevant for disease-free and overall patient survival and response to chemotherapy.

          Related collections

          Most cited references17

          • Record: found
          • Abstract: found
          • Article: found
          Is Open Access

          Repeatability and Reproducibility of Radiomic Features: A Systematic Review

          Purpose: An ever-growing number of predictive models used to inform clinical decision making have included quantitative, computer-extracted imaging biomarkers, or “radiomic features.” Broadly generalizable validity of radiomics-assisted models may be impeded by concerns about reproducibility. We offer a qualitative synthesis of 41 studies that specifically investigated the repeatability and reproducibility of radiomic features, derived from a systematic review of published peer-reviewed literature. Methods and Materials: The PubMed electronic database was searched using combinations of the broad Haynes and Ingui filters along with a set of text words specific to cancer, radiomics (including texture analyses), reproducibility, and repeatability. This review has been reported in compliance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. From each full-text article, information was extracted regarding cancer type, class of radiomic feature examined, reporting quality of key processing steps, and statistical metric used to segregate stable features. Results: Among 624 unique records, 41 full-text articles were subjected to review. The studies primarily addressed non-small cell lung cancer and oropharyngeal cancer. Only 7 studies addressed in detail every methodologic aspect related to image acquisition, preprocessing, and feature extraction. The repeatability and reproducibility of radiomic features are sensitive at various degrees to processing details such as image acquisition settings, image reconstruction algorithm, digital image preprocessing, and software used to extract radiomic features. First-order features were overall more reproducible than shape metrics and textural features. Entropy was consistently reported as one of the most stable first-order features. There was no emergent consensus regarding either shape metrics or textural features; however, coarseness and contrast appeared among the least reproducible. Conclusions: Investigations of feature repeatability and reproducibility are currently limited to a small number of cancer types. Reporting quality could be improved regarding details of feature extraction software, digital image manipulation (preprocessing), and the cutoff value used to distinguish stable features.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Genomics-Driven Precision Medicine for Advanced Pancreatic Cancer: Early Results from the COMPASS Trial

            Purpose: To perform real-time whole genome sequencing (WGS) and RNA sequencing (RNASeq) of advanced pancreatic ductal adenocarcinoma (PDAC) to identify predictive mutational and transcriptional features for better treatment selection.Experimental Design: Patients with advanced PDAC were prospectively recruited prior to first-line combination chemotherapy. Fresh tumor tissue was acquired by image-guided percutaneous core biopsy for WGS and RNASeq. Laser capture microdissection was performed for all cases. Primary endpoint was feasibility to report WGS results prior to first disease assessment CT scan at 8 weeks. The main secondary endpoint was discovery of patient subsets with predictive mutational and transcriptional signatures.Results: Sixty-three patients underwent a tumor biopsy between December 2015 and June 2017. WGS and RNASeq were successful in 62 (98%) and 60 (95%), respectively. Genomic results were reported at a median of 35 days (range, 19-52 days) from biopsy, meeting the primary feasibility endpoint. Objective responses to first-line chemotherapy were significantly better in patients with the classical PDAC RNA subtype compared with those with the basal-like subtype (P = 0.004). The best progression-free survival was observed in those with classical subtype treated with m-FOLFIRINOX. GATA6 expression in tumor measured by RNA in situ hybridization was found to be a robust surrogate biomarker for differentiating classical and basal-like PDAC subtypes. Potentially actionable genetic alterations were found in 30% of patients.Conclusions: Prospective genomic profiling of advanced PDAC is feasible, and our early data indicate that chemotherapy response differs among patients with different genomic/transcriptomic subtypes. Clin Cancer Res; 24(6); 1344-54. ©2017 AACR.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Evolutionary routes and KRAS dosage define pancreatic cancer phenotypes

              The poor correlation of mutational landscapes with phenotypes limits our understanding of pancreatic ductal adenocarcinoma (PDAC) pathogenesis and metastasis. Here we show a critical role of oncogenic dosage-variation in PDAC biology and phenotypic diversification. We found gene-dosage increase of mutant KRASMUT in human PDAC precursors, driving both early tumorigenesis and metastasis, thus rationalizing early PDAC dissemination. To overcome limitations posed to gene-dosage studies by PDAC´s stroma-richness we developed large cell culture resources of metastatic mouse PDAC. Integration of their genomes, transcriptomes and tumor phenotypes with functional studies and human data, revealed additional widespread effects of oncogenic dosage-variation on cell morphology/plasticity, histopathology and clinical outcome, with highest KrasMUT levels underlying aggressive undifferentiated phenotypes. We also identify alternative oncogenic gains (Myc, Yap1 or Nfkb2), which collaborate with heterozygous KrasMUT in driving tumorigenesis, yet with lower metastatic potential. Mechanistically, different oncogenic gains and dosages evolve along distinct evolutionary routes, licensed by defined allelic states and/or combinations of hallmark tumor-suppressor alterations (Cdkn2a, Trp53, Tgfβ-pathway). Thus, evolutionary constraints and contingencies direct oncogenic dosage gain and variation along defined routes to drive early progression and shape downstream PDAC biology. Our study uncovers universal principles in Ras-driven oncogenesis with potential relevance beyond pancreatic cancer.
                Bookmark

                Author and article information

                Contributors
                Role: ConceptualizationRole: Data curationRole: Formal analysisRole: InvestigationRole: MethodologyRole: SoftwareRole: ValidationRole: VisualizationRole: Writing – original draftRole: Writing – review & editing
                Role: Formal analysisRole: InvestigationRole: SoftwareRole: Writing – original draftRole: Writing – review & editing
                Role: Formal analysisRole: MethodologyRole: SupervisionRole: Writing – original draftRole: Writing – review & editing
                Role: Formal analysisRole: MethodologyRole: Visualization
                Role: Project administrationRole: Supervision
                Role: Formal analysisRole: InvestigationRole: Methodology
                Role: Formal analysisRole: InvestigationRole: MethodologyRole: Visualization
                Role: Project administrationRole: Supervision
                Role: Project administrationRole: Supervision
                Role: Project administrationRole: Supervision
                Role: Funding acquisitionRole: Project administrationRole: Supervision
                Role: ConceptualizationRole: InvestigationRole: SupervisionRole: ValidationRole: Writing – original draftRole: Writing – review & editing
                Role: ConceptualizationRole: Data curationRole: Funding acquisitionRole: MethodologyRole: Project administrationRole: SupervisionRole: ValidationRole: Writing – original draftRole: Writing – review & editing
                Role: Editor
                Journal
                PLoS One
                PLoS ONE
                plos
                plosone
                PLoS ONE
                Public Library of Science (San Francisco, CA USA )
                1932-6203
                2 October 2019
                2019
                : 14
                : 10
                : e0218642
                Affiliations
                [1 ] Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Munich, Germany
                [2 ] Department of Pathology, School of Medicine, Technical University of Munich, Munich, Germany
                [3 ] Department of Internal Medicine II, School of Medicine, Technical University of Munich, Munich, Germany
                [4 ] Department of Surgery, School of Medicine, Technical University of Munich, Munich, Germany
                [5 ] Division of Solid Tumor Translational Oncology, West German Cancer Center, University Hospital Essen, Essen, Germany
                [6 ] German Cancer Consortium (DKTK) and German Cancer Research Center (DKFZ), Heidelberg, Germany
                Centro Nacional de Investigaciones Oncologicas, SPAIN
                Author notes

                Competing Interests: The authors have declared that no competing interests exist.

                Author information
                http://orcid.org/0000-0001-8382-8062
                http://orcid.org/0000-0002-0414-1797
                Article
                PONE-D-19-15731
                10.1371/journal.pone.0218642
                6774515
                31577805
                223f1b21-bf43-4a03-b65c-4761afebf1e6
                © 2019 Kaissis et al

                This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

                History
                : 3 June 2019
                : 19 September 2019
                Page count
                Figures: 9, Tables: 3, Pages: 16
                Funding
                Funded by: Deutsche Forschungsgemeinschaft (DE)
                Award ID: SFB284 Project C6
                Award Recipient :
                Funded by: Deutsche Forschungsgemeinschaft (DE)
                Award ID: SFB824/Project Z2
                Award Recipient :
                This work was supported by funding of the German Research Foundation (DFG) within the SFB-Initiative 824 (collaborative research center), "Imaging for Selection, Monitoring and Individualization of Cancer Therapies" to RB (SFB824, project C6) and WW (project Z2). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
                Categories
                Research Article
                Medicine and Health Sciences
                Oncology
                Cancer Treatment
                Cancer Chemotherapy
                Medicine and Health Sciences
                Pharmaceutics
                Drug Therapy
                Chemotherapy
                Cancer Chemotherapy
                Medicine and Health Sciences
                Clinical Medicine
                Clinical Oncology
                Cancer Chemotherapy
                Medicine and Health Sciences
                Oncology
                Clinical Oncology
                Cancer Chemotherapy
                Medicine and Health Sciences
                Diagnostic Medicine
                Diagnostic Radiology
                Magnetic Resonance Imaging
                Research and Analysis Methods
                Imaging Techniques
                Diagnostic Radiology
                Magnetic Resonance Imaging
                Medicine and Health Sciences
                Radiology and Imaging
                Diagnostic Radiology
                Magnetic Resonance Imaging
                Physical Sciences
                Mathematics
                Applied Mathematics
                Algorithms
                Machine Learning Algorithms
                Research and Analysis Methods
                Simulation and Modeling
                Algorithms
                Machine Learning Algorithms
                Computer and Information Sciences
                Artificial Intelligence
                Machine Learning
                Machine Learning Algorithms
                Medicine and Health Sciences
                Pharmaceutics
                Drug Therapy
                Chemotherapy
                Medicine and Health Sciences
                Oncology
                Cancers and Neoplasms
                Carcinomas
                Adenocarcinomas
                Medicine and Health Sciences
                Oncology
                Cancer Treatment
                Physical Sciences
                Physics
                Thermodynamics
                Entropy
                Physical Sciences
                Mathematics
                Applied Mathematics
                Algorithms
                Research and Analysis Methods
                Simulation and Modeling
                Algorithms
                Custom metadata
                Data can be found at https://zenodo.org/record/3337876#.XS2dCi2Q2WY.

                Uncategorized
                Uncategorized

                Comments

                Comment on this article