Assessing robustness of radiomic features by image perturbation View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2019-12

AUTHORS

Alex Zwanenburg, Stefan Leger, Linda Agolli, Karoline Pilz, Esther G. C. Troost, Christian Richter, Steffen Löck

ABSTRACT

Image features need to be robust against differences in positioning, acquisition and segmentation to ensure reproducibility. Radiomic models that only include robust features can be used to analyse new images, whereas models with non-robust features may fail to predict the outcome of interest accurately. Test-retest imaging is recommended to assess robustness, but may not be available for the phenotype of interest. We therefore investigated 18 combinations of image perturbations to determine feature robustness, based on noise addition (N), translation (T), rotation (R), volume growth/shrinkage (V) and supervoxel-based contour randomisation (C). Test-retest and perturbation robustness were compared for combined total of 4032 morphological, statistical and texture features that were computed from the gross tumour volume in two cohorts with computed tomography imaging: I) 31 non-small-cell lung cancer (NSCLC) patients; II): 19 head-and-neck squamous cell carcinoma (HNSCC) patients. Robustness was determined using the 95% confidence interval (CI) of the intraclass correlation coefficient (1, 1). Features with CI ≥ 0:90 were considered robust. The NTCV, TCV, RNCV and RCV perturbation chain produced similar results and identified the fewest false positive robust features (NSCLC: 0.2-0.9%; HNSCC: 1.7-1.9%). Thus, these perturbation chains may be used as an alternative to test-retest imaging to assess feature robustness. More... »

PAGES

614

Identifiers

URI

http://scigraph.springernature.com/pub.10.1038/s41598-018-36938-4

DOI

http://dx.doi.org/10.1038/s41598-018-36938-4

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1111640491

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/30679599


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1112", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Oncology and Carcinogenesis", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/11", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Medical and Health Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "German Cancer Research Center", 
          "id": "https://www.grid.ac/institutes/grid.7497.d", 
          "name": [
            "OncoRay \u2013 National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany", 
            "National Center for Tumor Diseases (NCT), Partner Site Dresden, Dresden, Germany", 
            "German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zwanenburg", 
        "givenName": "Alex", 
        "id": "sg:person.0752571524.70", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0752571524.70"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "German Cancer Research Center", 
          "id": "https://www.grid.ac/institutes/grid.7497.d", 
          "name": [
            "OncoRay \u2013 National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany", 
            "National Center for Tumor Diseases (NCT), Partner Site Dresden, Dresden, Germany", 
            "German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Leger", 
        "givenName": "Stefan", 
        "id": "sg:person.010041235227.34", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010041235227.34"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "TU Dresden", 
          "id": "https://www.grid.ac/institutes/grid.4488.0", 
          "name": [
            "OncoRay \u2013 National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany", 
            "Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Agolli", 
        "givenName": "Linda", 
        "id": "sg:person.01013304244.70", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01013304244.70"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "TU Dresden", 
          "id": "https://www.grid.ac/institutes/grid.4488.0", 
          "name": [
            "OncoRay \u2013 National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany", 
            "Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Pilz", 
        "givenName": "Karoline", 
        "id": "sg:person.0661550641.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0661550641.37"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Helmholtz-Zentrum Dresden-Rossendorf", 
          "id": "https://www.grid.ac/institutes/grid.40602.30", 
          "name": [
            "OncoRay \u2013 National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany", 
            "National Center for Tumor Diseases (NCT), Partner Site Dresden, Dresden, Germany", 
            "German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany", 
            "Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Dresden, Germany", 
            "Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology \u2013 OncoRay, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Troost", 
        "givenName": "Esther G. C.", 
        "id": "sg:person.011250322677.36", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011250322677.36"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Helmholtz-Zentrum Dresden-Rossendorf", 
          "id": "https://www.grid.ac/institutes/grid.40602.30", 
          "name": [
            "OncoRay \u2013 National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany", 
            "German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany", 
            "Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology \u2013 OncoRay, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Richter", 
        "givenName": "Christian", 
        "id": "sg:person.01106600057.40", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01106600057.40"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "TU Dresden", 
          "id": "https://www.grid.ac/institutes/grid.4488.0", 
          "name": [
            "OncoRay \u2013 National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany", 
            "German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany", 
            "Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universit\u00e4t Dresden, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "L\u00f6ck", 
        "givenName": "Steffen", 
        "id": "sg:person.01006365753.93", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01006365753.93"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.2967/jnumed.114.144055", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007967674"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1148/radiol.2522081593", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1008413249"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/srep23428", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009204094", 
          "https://doi.org/10.1038/srep23428"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.mri.2012.06.010", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009925444"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.jcm.2016.02.012", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015497339"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2967/jnumed.111.099127", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017213627"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.mri.2003.09.001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018018059"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1593/tlo.13844", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022989144"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/rli.0000000000000180", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023605847"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/rli.0000000000000180", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023605847"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/rli.0000000000000180", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023605847"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.ejca.2011.11.036", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032206774"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/srep34921", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032506380", 
          "https://doi.org/10.1038/srep34921"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1037/0033-2909.86.2.420", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038345864"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1088/0031-9155/60/14/5471", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038681832"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1088/0031-9155/60/14/5471", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038681832"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3109/0284186x.2013.812798", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044026718"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10278-013-9622-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044365820", 
          "https://doi.org/10.1007/s10278-013-9622-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11307-016-0940-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048234611", 
          "https://doi.org/10.1007/s11307-016-0940-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11307-016-0940-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048234611", 
          "https://doi.org/10.1007/s11307-016-0940-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1088/0031-9155/61/13/r150", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1059031442"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/mci.2010.938364", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061392393"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2012.120", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061744236"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18383/j.tom.2016.00208", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1068635246"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2967/jnumed.116.180919", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1070928628"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/mp.12123", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1074215033"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.radonc.2017.08.010", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091307392"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.radonc.2017.08.010", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091307392"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/s41598-017-10371-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091356681", 
          "https://doi.org/10.1038/s41598-017-10371-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/s41598-017-10371-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091356681", 
          "https://doi.org/10.1038/s41598-017-10371-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/0284186x.2017.1351624", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091617872"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pone.0178524", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091890638"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nrclinonc.2017.141", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092061102", 
          "https://doi.org/10.1038/nrclinonc.2017.141"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/s41598-017-13448-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092152818", 
          "https://doi.org/10.1038/s41598-017-13448-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2967/jnumed.117.200501", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092989403"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2967/jnumed.117.200501", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092989403"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2967/jnumed.117.200501", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092989403"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/s41598-018-20713-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100726951", 
          "https://doi.org/10.1038/s41598-018-20713-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1117/1.jmi.5.1.011020", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101064199"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/0284186x.2018.1445283", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101368475"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.ijrobp.2018.05.053", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1104392450"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-12", 
    "datePublishedReg": "2019-12-01", 
    "description": "Image features need to be robust against differences in positioning, acquisition and segmentation to ensure reproducibility. Radiomic models that only include robust features can be used to analyse new images, whereas models with non-robust features may fail to predict the outcome of interest accurately. Test-retest imaging is recommended to assess robustness, but may not be available for the phenotype of interest. We therefore investigated 18 combinations of image perturbations to determine feature robustness, based on noise addition (N), translation (T), rotation (R), volume growth/shrinkage (V) and supervoxel-based contour randomisation (C). Test-retest and perturbation robustness were compared for combined total of 4032 morphological, statistical and texture features that were computed from the gross tumour volume in two cohorts with computed tomography imaging: I) 31 non-small-cell lung cancer (NSCLC) patients; II): 19 head-and-neck squamous cell carcinoma (HNSCC) patients. Robustness was determined using the 95% confidence interval (CI) of the intraclass correlation coefficient (1, 1). Features with CI\u2009\u2265\u20090:90 were considered robust. The NTCV, TCV, RNCV and RCV perturbation chain produced similar results and identified the fewest false positive robust features (NSCLC: 0.2-0.9%; HNSCC: 1.7-1.9%). Thus, these perturbation chains may be used as an alternative to test-retest imaging to assess feature robustness.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1038/s41598-018-36938-4", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1045337", 
        "issn": [
          "2045-2322"
        ], 
        "name": "Scientific Reports", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "9"
      }
    ], 
    "name": "Assessing robustness of radiomic features by image perturbation", 
    "pagination": "614", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "473b4804de6cf0a0a9015a4feb7425400ddf010c34aa00d1ffc41c995b354366"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "30679599"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "101563288"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1038/s41598-018-36938-4"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1111640491"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1038/s41598-018-36938-4", 
      "https://app.dimensions.ai/details/publication/pub.1111640491"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T08:58", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000326_0000000326/records_68472_00000000.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://www.nature.com/articles/s41598-018-36938-4"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1038/s41598-018-36938-4'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1038/s41598-018-36938-4'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1038/s41598-018-36938-4'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1038/s41598-018-36938-4'


 

This table displays all metadata directly associated to this object as RDF triples.

231 TRIPLES      21 PREDICATES      62 URIs      21 LITERALS      9 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1038/s41598-018-36938-4 schema:about anzsrc-for:11
2 anzsrc-for:1112
3 schema:author Nddbb613a0495441e99f764576e0763d2
4 schema:citation sg:pub.10.1007/s10278-013-9622-7
5 sg:pub.10.1007/s11307-016-0940-2
6 sg:pub.10.1038/nrclinonc.2017.141
7 sg:pub.10.1038/s41598-017-10371-5
8 sg:pub.10.1038/s41598-017-13448-3
9 sg:pub.10.1038/s41598-018-20713-6
10 sg:pub.10.1038/srep23428
11 sg:pub.10.1038/srep34921
12 https://doi.org/10.1002/mp.12123
13 https://doi.org/10.1016/j.ejca.2011.11.036
14 https://doi.org/10.1016/j.ijrobp.2018.05.053
15 https://doi.org/10.1016/j.jcm.2016.02.012
16 https://doi.org/10.1016/j.mri.2003.09.001
17 https://doi.org/10.1016/j.mri.2012.06.010
18 https://doi.org/10.1016/j.radonc.2017.08.010
19 https://doi.org/10.1037/0033-2909.86.2.420
20 https://doi.org/10.1080/0284186x.2017.1351624
21 https://doi.org/10.1080/0284186x.2018.1445283
22 https://doi.org/10.1088/0031-9155/60/14/5471
23 https://doi.org/10.1088/0031-9155/61/13/r150
24 https://doi.org/10.1097/rli.0000000000000180
25 https://doi.org/10.1109/mci.2010.938364
26 https://doi.org/10.1109/tpami.2012.120
27 https://doi.org/10.1117/1.jmi.5.1.011020
28 https://doi.org/10.1148/radiol.2522081593
29 https://doi.org/10.1371/journal.pone.0178524
30 https://doi.org/10.1593/tlo.13844
31 https://doi.org/10.18383/j.tom.2016.00208
32 https://doi.org/10.2967/jnumed.111.099127
33 https://doi.org/10.2967/jnumed.114.144055
34 https://doi.org/10.2967/jnumed.116.180919
35 https://doi.org/10.2967/jnumed.117.200501
36 https://doi.org/10.3109/0284186x.2013.812798
37 schema:datePublished 2019-12
38 schema:datePublishedReg 2019-12-01
39 schema:description Image features need to be robust against differences in positioning, acquisition and segmentation to ensure reproducibility. Radiomic models that only include robust features can be used to analyse new images, whereas models with non-robust features may fail to predict the outcome of interest accurately. Test-retest imaging is recommended to assess robustness, but may not be available for the phenotype of interest. We therefore investigated 18 combinations of image perturbations to determine feature robustness, based on noise addition (N), translation (T), rotation (R), volume growth/shrinkage (V) and supervoxel-based contour randomisation (C). Test-retest and perturbation robustness were compared for combined total of 4032 morphological, statistical and texture features that were computed from the gross tumour volume in two cohorts with computed tomography imaging: I) 31 non-small-cell lung cancer (NSCLC) patients; II): 19 head-and-neck squamous cell carcinoma (HNSCC) patients. Robustness was determined using the 95% confidence interval (CI) of the intraclass correlation coefficient (1, 1). Features with CI ≥ 0:90 were considered robust. The NTCV, TCV, RNCV and RCV perturbation chain produced similar results and identified the fewest false positive robust features (NSCLC: 0.2-0.9%; HNSCC: 1.7-1.9%). Thus, these perturbation chains may be used as an alternative to test-retest imaging to assess feature robustness.
40 schema:genre research_article
41 schema:inLanguage en
42 schema:isAccessibleForFree true
43 schema:isPartOf N98006d9e3f2542578f360fe2a179bd40
44 Na36231c98bdd4e57b74abbb7c124b53e
45 sg:journal.1045337
46 schema:name Assessing robustness of radiomic features by image perturbation
47 schema:pagination 614
48 schema:productId N37e76b7ffc344727bf195eeff62e2048
49 N806d15de3afb4a049fe7f964f83fbc08
50 Nc02a0af53f5d4bbb9f789e1b00071192
51 Nde4caf06a8df4a05805caf8449e950f5
52 Ne00956ab6c954eb88c5bc3b20ab1d186
53 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111640491
54 https://doi.org/10.1038/s41598-018-36938-4
55 schema:sdDatePublished 2019-04-11T08:58
56 schema:sdLicense https://scigraph.springernature.com/explorer/license/
57 schema:sdPublisher N69e1f45195554f25999256c9838c7eac
58 schema:url https://www.nature.com/articles/s41598-018-36938-4
59 sgo:license sg:explorer/license/
60 sgo:sdDataset articles
61 rdf:type schema:ScholarlyArticle
62 N0a124b98097b4059ade61e475d192c7a rdf:first sg:person.010041235227.34
63 rdf:rest N6a3dbb3d947947d8a4680ce01ee2116a
64 N37e76b7ffc344727bf195eeff62e2048 schema:name pubmed_id
65 schema:value 30679599
66 rdf:type schema:PropertyValue
67 N69e1f45195554f25999256c9838c7eac schema:name Springer Nature - SN SciGraph project
68 rdf:type schema:Organization
69 N6a3dbb3d947947d8a4680ce01ee2116a rdf:first sg:person.01013304244.70
70 rdf:rest Nee78189c78504f3186edb7482895a133
71 N806d15de3afb4a049fe7f964f83fbc08 schema:name nlm_unique_id
72 schema:value 101563288
73 rdf:type schema:PropertyValue
74 N88c6dc8901c644cdacb8c95627e59008 rdf:first sg:person.01106600057.40
75 rdf:rest Ne1285b9da7564df5823c9b880dcbe168
76 N98006d9e3f2542578f360fe2a179bd40 schema:issueNumber 1
77 rdf:type schema:PublicationIssue
78 Na36231c98bdd4e57b74abbb7c124b53e schema:volumeNumber 9
79 rdf:type schema:PublicationVolume
80 Nc02a0af53f5d4bbb9f789e1b00071192 schema:name dimensions_id
81 schema:value pub.1111640491
82 rdf:type schema:PropertyValue
83 Nd9bfe18f43e34b908164799711699e90 rdf:first sg:person.011250322677.36
84 rdf:rest N88c6dc8901c644cdacb8c95627e59008
85 Nddbb613a0495441e99f764576e0763d2 rdf:first sg:person.0752571524.70
86 rdf:rest N0a124b98097b4059ade61e475d192c7a
87 Nde4caf06a8df4a05805caf8449e950f5 schema:name readcube_id
88 schema:value 473b4804de6cf0a0a9015a4feb7425400ddf010c34aa00d1ffc41c995b354366
89 rdf:type schema:PropertyValue
90 Ne00956ab6c954eb88c5bc3b20ab1d186 schema:name doi
91 schema:value 10.1038/s41598-018-36938-4
92 rdf:type schema:PropertyValue
93 Ne1285b9da7564df5823c9b880dcbe168 rdf:first sg:person.01006365753.93
94 rdf:rest rdf:nil
95 Nee78189c78504f3186edb7482895a133 rdf:first sg:person.0661550641.37
96 rdf:rest Nd9bfe18f43e34b908164799711699e90
97 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
98 schema:name Medical and Health Sciences
99 rdf:type schema:DefinedTerm
100 anzsrc-for:1112 schema:inDefinedTermSet anzsrc-for:
101 schema:name Oncology and Carcinogenesis
102 rdf:type schema:DefinedTerm
103 sg:journal.1045337 schema:issn 2045-2322
104 schema:name Scientific Reports
105 rdf:type schema:Periodical
106 sg:person.010041235227.34 schema:affiliation https://www.grid.ac/institutes/grid.7497.d
107 schema:familyName Leger
108 schema:givenName Stefan
109 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010041235227.34
110 rdf:type schema:Person
111 sg:person.01006365753.93 schema:affiliation https://www.grid.ac/institutes/grid.4488.0
112 schema:familyName Löck
113 schema:givenName Steffen
114 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01006365753.93
115 rdf:type schema:Person
116 sg:person.01013304244.70 schema:affiliation https://www.grid.ac/institutes/grid.4488.0
117 schema:familyName Agolli
118 schema:givenName Linda
119 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01013304244.70
120 rdf:type schema:Person
121 sg:person.01106600057.40 schema:affiliation https://www.grid.ac/institutes/grid.40602.30
122 schema:familyName Richter
123 schema:givenName Christian
124 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01106600057.40
125 rdf:type schema:Person
126 sg:person.011250322677.36 schema:affiliation https://www.grid.ac/institutes/grid.40602.30
127 schema:familyName Troost
128 schema:givenName Esther G. C.
129 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011250322677.36
130 rdf:type schema:Person
131 sg:person.0661550641.37 schema:affiliation https://www.grid.ac/institutes/grid.4488.0
132 schema:familyName Pilz
133 schema:givenName Karoline
134 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0661550641.37
135 rdf:type schema:Person
136 sg:person.0752571524.70 schema:affiliation https://www.grid.ac/institutes/grid.7497.d
137 schema:familyName Zwanenburg
138 schema:givenName Alex
139 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0752571524.70
140 rdf:type schema:Person
141 sg:pub.10.1007/s10278-013-9622-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044365820
142 https://doi.org/10.1007/s10278-013-9622-7
143 rdf:type schema:CreativeWork
144 sg:pub.10.1007/s11307-016-0940-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048234611
145 https://doi.org/10.1007/s11307-016-0940-2
146 rdf:type schema:CreativeWork
147 sg:pub.10.1038/nrclinonc.2017.141 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092061102
148 https://doi.org/10.1038/nrclinonc.2017.141
149 rdf:type schema:CreativeWork
150 sg:pub.10.1038/s41598-017-10371-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091356681
151 https://doi.org/10.1038/s41598-017-10371-5
152 rdf:type schema:CreativeWork
153 sg:pub.10.1038/s41598-017-13448-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092152818
154 https://doi.org/10.1038/s41598-017-13448-3
155 rdf:type schema:CreativeWork
156 sg:pub.10.1038/s41598-018-20713-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100726951
157 https://doi.org/10.1038/s41598-018-20713-6
158 rdf:type schema:CreativeWork
159 sg:pub.10.1038/srep23428 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009204094
160 https://doi.org/10.1038/srep23428
161 rdf:type schema:CreativeWork
162 sg:pub.10.1038/srep34921 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032506380
163 https://doi.org/10.1038/srep34921
164 rdf:type schema:CreativeWork
165 https://doi.org/10.1002/mp.12123 schema:sameAs https://app.dimensions.ai/details/publication/pub.1074215033
166 rdf:type schema:CreativeWork
167 https://doi.org/10.1016/j.ejca.2011.11.036 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032206774
168 rdf:type schema:CreativeWork
169 https://doi.org/10.1016/j.ijrobp.2018.05.053 schema:sameAs https://app.dimensions.ai/details/publication/pub.1104392450
170 rdf:type schema:CreativeWork
171 https://doi.org/10.1016/j.jcm.2016.02.012 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015497339
172 rdf:type schema:CreativeWork
173 https://doi.org/10.1016/j.mri.2003.09.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018018059
174 rdf:type schema:CreativeWork
175 https://doi.org/10.1016/j.mri.2012.06.010 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009925444
176 rdf:type schema:CreativeWork
177 https://doi.org/10.1016/j.radonc.2017.08.010 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091307392
178 rdf:type schema:CreativeWork
179 https://doi.org/10.1037/0033-2909.86.2.420 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038345864
180 rdf:type schema:CreativeWork
181 https://doi.org/10.1080/0284186x.2017.1351624 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091617872
182 rdf:type schema:CreativeWork
183 https://doi.org/10.1080/0284186x.2018.1445283 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101368475
184 rdf:type schema:CreativeWork
185 https://doi.org/10.1088/0031-9155/60/14/5471 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038681832
186 rdf:type schema:CreativeWork
187 https://doi.org/10.1088/0031-9155/61/13/r150 schema:sameAs https://app.dimensions.ai/details/publication/pub.1059031442
188 rdf:type schema:CreativeWork
189 https://doi.org/10.1097/rli.0000000000000180 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023605847
190 rdf:type schema:CreativeWork
191 https://doi.org/10.1109/mci.2010.938364 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061392393
192 rdf:type schema:CreativeWork
193 https://doi.org/10.1109/tpami.2012.120 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744236
194 rdf:type schema:CreativeWork
195 https://doi.org/10.1117/1.jmi.5.1.011020 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101064199
196 rdf:type schema:CreativeWork
197 https://doi.org/10.1148/radiol.2522081593 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008413249
198 rdf:type schema:CreativeWork
199 https://doi.org/10.1371/journal.pone.0178524 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091890638
200 rdf:type schema:CreativeWork
201 https://doi.org/10.1593/tlo.13844 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022989144
202 rdf:type schema:CreativeWork
203 https://doi.org/10.18383/j.tom.2016.00208 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068635246
204 rdf:type schema:CreativeWork
205 https://doi.org/10.2967/jnumed.111.099127 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017213627
206 rdf:type schema:CreativeWork
207 https://doi.org/10.2967/jnumed.114.144055 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007967674
208 rdf:type schema:CreativeWork
209 https://doi.org/10.2967/jnumed.116.180919 schema:sameAs https://app.dimensions.ai/details/publication/pub.1070928628
210 rdf:type schema:CreativeWork
211 https://doi.org/10.2967/jnumed.117.200501 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092989403
212 rdf:type schema:CreativeWork
213 https://doi.org/10.3109/0284186x.2013.812798 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044026718
214 rdf:type schema:CreativeWork
215 https://www.grid.ac/institutes/grid.40602.30 schema:alternateName Helmholtz-Zentrum Dresden-Rossendorf
216 schema:name Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
217 German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany
218 Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology – OncoRay, Dresden, Germany
219 National Center for Tumor Diseases (NCT), Partner Site Dresden, Dresden, Germany
220 OncoRay – National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
221 rdf:type schema:Organization
222 https://www.grid.ac/institutes/grid.4488.0 schema:alternateName TU Dresden
223 schema:name Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
224 German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany
225 OncoRay – National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
226 rdf:type schema:Organization
227 https://www.grid.ac/institutes/grid.7497.d schema:alternateName German Cancer Research Center
228 schema:name German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany
229 National Center for Tumor Diseases (NCT), Partner Site Dresden, Dresden, Germany
230 OncoRay – National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
231 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...