Preoperative prediction of perineural invasion and KRAS mutation in colon cancer using machine learning View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2020-08-10

AUTHORS

Yu Li, Aydin Eresen, Junjie Shangguan, Jia Yang, Al B. Benson, Vahid Yaghmai, Zhuoli Zhang

ABSTRACT

PurposePreoperative prediction of perineural invasion (PNI) and Kirsten RAS (KRAS) mutation in colon cancer is critical for treatment planning and patient management. We developed machine learning models for diagnosis of PNI and KRAS mutation in colon cancer patients by interpreting preoperative CT.MethodsThis retrospective study included 207 patients who received surgical resection in our institution. The underlying tumor characteristics were described by analyzing CT image texture quantitatively. The key radiomics features were determined with similarity analysis followed by RELIEFF method among 306 CT imaging features. Eight kernel-based support vector machines classifiers were constructed using individual (II, III, or IV) or multi-stage (II + III + IV) patient cohorts for predicting PNI and KRAS mutation. The model performances were evaluated using accuracy, receiver operating curve, and decision curve analyses.ResultsMulti-stage classifiers obtained AUC of 0.793 and 0.862 for detecting PNI and KRAS mutation for test cohort. Moreover, individual-stage classifiers demonstrated significantly improved diagnostic performance at all stages (IIAUC: [0.86; 0.99], IIIAUC: [0.99; 0.99], and IVAUC: [1.00; 1.00], respectively, for PNI and KRAS mutation in test cohort). Besides, stage II tumor is better described with coarse texture features while more detailed features are required for better characterization of advanced-stage tumors (III and IV) for diagnoses of PNI or KRAS mutation.ConclusionMachine learning models developed using preoperative CT data can predict PNI and KRAS mutation in colon cancer patients with satisfactory performance. Individual-stage models better-characterized the relationship between CT features and PNI or KRAS mutation than multi-stage models and demonstrated good prediction scores. More... »

PAGES

3165-3174

References to SciGraph publications

  • 2017. AJCC Cancer Staging Manual in NONE
  • 2018-03-13. Targeting KRAS in metastatic colorectal cancer: current strategies and emerging opportunities in JOURNAL OF EXPERIMENTAL & CLINICAL CANCER RESEARCH
  • 2016-11-10. Radiomics based targeted radiotherapy planning (Rad-TRaP): a computational framework for prostate cancer treatment planning with MRI in RADIATION ONCOLOGY
  • 2019-11-29. Decision tree algorithm in locally advanced rectal cancer: an example of over-interpretation and misuse of a machine learning approach in JOURNAL OF CANCER RESEARCH AND CLINICAL ONCOLOGY
  • 2017-10-04. Radiomics: the bridge between medical imaging and personalized medicine in NATURE REVIEWS CLINICAL ONCOLOGY
  • 2019-01-02. A novel histologic grading system based on lymphovascular invasion, perineural invasion, and tumor budding in colorectal cancer in JOURNAL OF CANCER RESEARCH AND CLINICAL ONCOLOGY
  • 2012-06-13. Emergence of KRAS mutations and acquired resistance to anti-EGFR therapy in colorectal cancer in NATURE
  • 2020-06-25. A machine learning-based prognostic predictor for stage III colon cancer in SCIENTIFIC REPORTS
  • 1997-01. Overcoming the Myopia of Inductive Learning Algorithms with RELIEFF in APPLIED INTELLIGENCE
  • 2015-02-07. Prognostic Value of Perineural Invasion in Colorectal Cancer: A Meta-Analysis in JOURNAL OF GASTROINTESTINAL SURGERY
  • 2018-06-21. CT prediction of resectability and prognosis in patients with pancreatic ductal adenocarcinoma after neoadjuvant treatment using image findings and texture analysis in EUROPEAN RADIOLOGY
  • 2019-02-04. Radiomics-based machine learning methods for isocitrate dehydrogenase genotype prediction of diffuse gliomas in JOURNAL OF CANCER RESEARCH AND CLINICAL ONCOLOGY
  • 2020-02-10. MRI radiomics for early prediction of response to vaccine therapy in a transgenic mouse model of pancreatic ductal adenocarcinoma in JOURNAL OF TRANSLATIONAL MEDICINE
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s00432-020-03354-z

    DOI

    http://dx.doi.org/10.1007/s00432-020-03354-z

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1130018892

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/32779023


    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/2008/11", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Medical and Health Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "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"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Adult", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Cohort Studies", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Colonic Neoplasms", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Colorectal Neoplasms", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Female", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Humans", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Machine Learning", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Male", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Middle Aged", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Mutation", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Neoplasm Invasiveness", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Neoplasm Staging", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Prognosis", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Proto-Oncogene Proteins p21(ras)", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Support Vector Machine", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Tomography, X-Ray Computed", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA", 
              "id": "http://www.grid.ac/institutes/grid.16753.36", 
              "name": [
                "Department of Gastrointestinal Surgery, Affiliated Hospital of Qingdao University, Qingdao, Shandong, China", 
                "Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Li", 
            "givenName": "Yu", 
            "id": "sg:person.0757632010.58", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0757632010.58"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA", 
              "id": "http://www.grid.ac/institutes/grid.16753.36", 
              "name": [
                "Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Eresen", 
            "givenName": "Aydin", 
            "id": "sg:person.0673022574.02", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0673022574.02"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA", 
              "id": "http://www.grid.ac/institutes/grid.16753.36", 
              "name": [
                "Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Shangguan", 
            "givenName": "Junjie", 
            "id": "sg:person.01035705477.86", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01035705477.86"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA", 
              "id": "http://www.grid.ac/institutes/grid.16753.36", 
              "name": [
                "Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Yang", 
            "givenName": "Jia", 
            "id": "sg:person.013172121233.61", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013172121233.61"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Robert Lurie Comprehensive Cancer Center of Northwestern University, Chicago, IL, USA", 
              "id": "http://www.grid.ac/institutes/grid.16753.36", 
              "name": [
                "Division of Hematology and Oncology, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA", 
                "Robert Lurie Comprehensive Cancer Center of Northwestern University, Chicago, IL, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Benson", 
            "givenName": "Al B.", 
            "id": "sg:person.013621452577.37", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013621452577.37"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Radiological Sciences, University of California, Orange, Irvine, CA, USA", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA", 
                "Robert Lurie Comprehensive Cancer Center of Northwestern University, Chicago, IL, USA", 
                "Department of Radiological Sciences, University of California, Orange, Irvine, CA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Yaghmai", 
            "givenName": "Vahid", 
            "id": "sg:person.01134174205.19", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01134174205.19"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Robert Lurie Comprehensive Cancer Center of Northwestern University, Chicago, IL, USA", 
              "id": "http://www.grid.ac/institutes/grid.16753.36", 
              "name": [
                "Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA", 
                "Robert Lurie Comprehensive Cancer Center of Northwestern University, Chicago, IL, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhang", 
            "givenName": "Zhuoli", 
            "id": "sg:person.013232656557.16", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013232656557.16"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-319-40618-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1108910915", 
              "https://doi.org/10.1007/978-3-319-40618-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00432-018-2804-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1111057432", 
              "https://doi.org/10.1007/s00432-018-2804-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature11156", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024120060", 
              "https://doi.org/10.1038/nature11156"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1008280620621", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050540325", 
              "https://doi.org/10.1023/a:1008280620621"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00432-019-03102-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1123020890", 
              "https://doi.org/10.1007/s00432-019-03102-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41598-020-67178-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1128742711", 
              "https://doi.org/10.1038/s41598-020-67178-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00330-018-5574-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1105052211", 
              "https://doi.org/10.1007/s00330-018-5574-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11605-015-2761-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015184303", 
              "https://doi.org/10.1007/s11605-015-2761-z"
            ], 
            "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.10.1186/s13046-018-0719-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101523019", 
              "https://doi.org/10.1186/s13046-018-0719-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s12967-020-02246-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1124777619", 
              "https://doi.org/10.1186/s12967-020-02246-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00432-018-2787-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1111914663", 
              "https://doi.org/10.1007/s00432-018-2787-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13014-016-0718-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1049972050", 
              "https://doi.org/10.1186/s13014-016-0718-3"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2020-08-10", 
        "datePublishedReg": "2020-08-10", 
        "description": "PurposePreoperative prediction of perineural invasion (PNI) and Kirsten RAS (KRAS) mutation in colon cancer is critical for treatment planning and patient management. We developed machine learning models for diagnosis of PNI and KRAS mutation in colon cancer patients by interpreting preoperative CT.MethodsThis retrospective study included 207 patients who received surgical resection in our institution. The underlying tumor characteristics were described by analyzing CT image texture quantitatively. The key radiomics features were determined with similarity analysis followed by RELIEFF method among 306 CT imaging features. Eight kernel-based support vector machines classifiers were constructed using individual (II, III, or IV) or multi-stage (II\u2009+\u2009III\u2009+\u2009IV) patient cohorts for predicting PNI and KRAS mutation. The model performances were evaluated using accuracy, receiver operating curve, and decision curve analyses.ResultsMulti-stage classifiers obtained AUC of 0.793 and 0.862 for detecting PNI and KRAS mutation for test cohort. Moreover, individual-stage classifiers demonstrated significantly improved diagnostic performance at all stages (IIAUC: [0.86; 0.99], IIIAUC: [0.99; 0.99], and IVAUC: [1.00; 1.00], respectively, for PNI and KRAS mutation in test cohort). Besides, stage II tumor is better described with coarse texture features while more detailed features are required for better characterization of advanced-stage tumors (III and IV) for diagnoses of PNI or KRAS mutation.ConclusionMachine learning models developed using preoperative CT data can predict PNI and KRAS mutation in colon cancer patients with satisfactory performance. Individual-stage models better-characterized the relationship between CT features and PNI or KRAS mutation than multi-stage models and demonstrated good prediction scores.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s00432-020-03354-z", 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.5504653", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.4104005", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1313647", 
            "issn": [
              "0171-5216", 
              "1432-1335"
            ], 
            "name": "Journal of Cancer Research and Clinical Oncology", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "12", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "146"
          }
        ], 
        "keywords": [
          "kernel-based Support Vector Machine (SVM) classifier", 
          "perineural invasion", 
          "diagnosis of PNI", 
          "KRAS mutations", 
          "support vector machine classifier", 
          "colon cancer patients", 
          "good prediction scores", 
          "vector machine classifier", 
          "cancer patients", 
          "colon cancer", 
          "texture features", 
          "preoperative CT data", 
          "machine classifier", 
          "image texture", 
          "stage II tumors", 
          "MethodsThis retrospective study", 
          "CT imaging features", 
          "classifier", 
          "decision curve analysis", 
          "advanced stage tumors", 
          "ReliefF method", 
          "satisfactory performance", 
          "surgical resection", 
          "retrospective study", 
          "tumor characteristics", 
          "II tumors", 
          "patient cohort", 
          "receiver operating curves", 
          "imaging features", 
          "patient management", 
          "machine", 
          "preoperative CT", 
          "CT data", 
          "preoperative prediction", 
          "RAS mutations", 
          "test cohort", 
          "patients", 
          "model performance", 
          "radiomic features", 
          "curve analysis", 
          "diagnostic performance", 
          "prediction score", 
          "treatment planning", 
          "detailed features", 
          "multi-stage model", 
          "similarity analysis", 
          "cohort", 
          "tumors", 
          "cancer", 
          "diagnosis", 
          "CT", 
          "performance", 
          "features", 
          "operating curves", 
          "ConclusionMachine", 
          "invasion", 
          "mutations", 
          "resection", 
          "model", 
          "accuracy", 
          "better characterization", 
          "AUC", 
          "prediction", 
          "planning", 
          "scores", 
          "texture", 
          "management", 
          "data", 
          "study", 
          "method", 
          "analysis", 
          "stage", 
          "institutions", 
          "relationship", 
          "curves", 
          "characteristics", 
          "characterization"
        ], 
        "name": "Preoperative prediction of perineural invasion and KRAS mutation in colon cancer using machine learning", 
        "pagination": "3165-3174", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1130018892"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s00432-020-03354-z"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "32779023"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s00432-020-03354-z", 
          "https://app.dimensions.ai/details/publication/pub.1130018892"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-10-01T06:47", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221001/entities/gbq_results/article/article_847.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s00432-020-03354-z"
      }
    ]
     

    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.10.1007/s00432-020-03354-z'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s00432-020-03354-z'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00432-020-03354-z'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00432-020-03354-z'


     

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

    309 TRIPLES      21 PREDICATES      131 URIs      110 LITERALS      23 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s00432-020-03354-z schema:about N00e8f91e96ee463f93022fabf8aa4284
    2 N0a585e18db5949dd85d1730cd107af4e
    3 N0c4adc1c7f714645bbf9595f1d892039
    4 N1349ee0de8de47beb268b2469b7cf53e
    5 N3feee328ec54466ca12e2ccc39bb60b3
    6 N63fb7138c2174586836911109ec23a5a
    7 N6d284d460bd749bb8bb428300edabd39
    8 N826fe58adc0d4fe49cc80f3786164188
    9 N83422f0915474ca3bb28a4a68617948f
    10 N8434d231c682403088f044baf68ccc8f
    11 Na01bfba62cbf432784410a901bf9d31d
    12 Na180f32a6ea34728ba667f7d76e58195
    13 Nabd37bbc052947ce98511520bfc53bc7
    14 Ne6205b8c5ec64844928f5ac1fb0d235b
    15 Ne692118013564a0a940dc016d34fe051
    16 Nf0d8a3790a194c26a4f7cb61787fc01b
    17 anzsrc-for:11
    18 anzsrc-for:1112
    19 schema:author N257e16ec78dc4e2bbb65eab3653bb26b
    20 schema:citation sg:pub.10.1007/978-3-319-40618-3
    21 sg:pub.10.1007/s00330-018-5574-0
    22 sg:pub.10.1007/s00432-018-2787-1
    23 sg:pub.10.1007/s00432-018-2804-4
    24 sg:pub.10.1007/s00432-019-03102-y
    25 sg:pub.10.1007/s11605-015-2761-z
    26 sg:pub.10.1023/a:1008280620621
    27 sg:pub.10.1038/nature11156
    28 sg:pub.10.1038/nrclinonc.2017.141
    29 sg:pub.10.1038/s41598-020-67178-0
    30 sg:pub.10.1186/s12967-020-02246-7
    31 sg:pub.10.1186/s13014-016-0718-3
    32 sg:pub.10.1186/s13046-018-0719-1
    33 schema:datePublished 2020-08-10
    34 schema:datePublishedReg 2020-08-10
    35 schema:description PurposePreoperative prediction of perineural invasion (PNI) and Kirsten RAS (KRAS) mutation in colon cancer is critical for treatment planning and patient management. We developed machine learning models for diagnosis of PNI and KRAS mutation in colon cancer patients by interpreting preoperative CT.MethodsThis retrospective study included 207 patients who received surgical resection in our institution. The underlying tumor characteristics were described by analyzing CT image texture quantitatively. The key radiomics features were determined with similarity analysis followed by RELIEFF method among 306 CT imaging features. Eight kernel-based support vector machines classifiers were constructed using individual (II, III, or IV) or multi-stage (II + III + IV) patient cohorts for predicting PNI and KRAS mutation. The model performances were evaluated using accuracy, receiver operating curve, and decision curve analyses.ResultsMulti-stage classifiers obtained AUC of 0.793 and 0.862 for detecting PNI and KRAS mutation for test cohort. Moreover, individual-stage classifiers demonstrated significantly improved diagnostic performance at all stages (IIAUC: [0.86; 0.99], IIIAUC: [0.99; 0.99], and IVAUC: [1.00; 1.00], respectively, for PNI and KRAS mutation in test cohort). Besides, stage II tumor is better described with coarse texture features while more detailed features are required for better characterization of advanced-stage tumors (III and IV) for diagnoses of PNI or KRAS mutation.ConclusionMachine learning models developed using preoperative CT data can predict PNI and KRAS mutation in colon cancer patients with satisfactory performance. Individual-stage models better-characterized the relationship between CT features and PNI or KRAS mutation than multi-stage models and demonstrated good prediction scores.
    36 schema:genre article
    37 schema:isAccessibleForFree false
    38 schema:isPartOf Naccb40c4656b425188e39b4c3f091220
    39 Nd2deb68a2cb244eaa68bc98ff81381ba
    40 sg:journal.1313647
    41 schema:keywords AUC
    42 CT
    43 CT data
    44 CT imaging features
    45 ConclusionMachine
    46 II tumors
    47 KRAS mutations
    48 MethodsThis retrospective study
    49 RAS mutations
    50 ReliefF method
    51 accuracy
    52 advanced stage tumors
    53 analysis
    54 better characterization
    55 cancer
    56 cancer patients
    57 characteristics
    58 characterization
    59 classifier
    60 cohort
    61 colon cancer
    62 colon cancer patients
    63 curve analysis
    64 curves
    65 data
    66 decision curve analysis
    67 detailed features
    68 diagnosis
    69 diagnosis of PNI
    70 diagnostic performance
    71 features
    72 good prediction scores
    73 image texture
    74 imaging features
    75 institutions
    76 invasion
    77 kernel-based Support Vector Machine (SVM) classifier
    78 machine
    79 machine classifier
    80 management
    81 method
    82 model
    83 model performance
    84 multi-stage model
    85 mutations
    86 operating curves
    87 patient cohort
    88 patient management
    89 patients
    90 performance
    91 perineural invasion
    92 planning
    93 prediction
    94 prediction score
    95 preoperative CT
    96 preoperative CT data
    97 preoperative prediction
    98 radiomic features
    99 receiver operating curves
    100 relationship
    101 resection
    102 retrospective study
    103 satisfactory performance
    104 scores
    105 similarity analysis
    106 stage
    107 stage II tumors
    108 study
    109 support vector machine classifier
    110 surgical resection
    111 test cohort
    112 texture
    113 texture features
    114 treatment planning
    115 tumor characteristics
    116 tumors
    117 vector machine classifier
    118 schema:name Preoperative prediction of perineural invasion and KRAS mutation in colon cancer using machine learning
    119 schema:pagination 3165-3174
    120 schema:productId N13fd4a90ce8d466bad54e36d422ea8a9
    121 N76b73ce3f20f4017b79cfdb032216f37
    122 Nfa8d8304fecf4de7a6c8341e30a560eb
    123 schema:sameAs https://app.dimensions.ai/details/publication/pub.1130018892
    124 https://doi.org/10.1007/s00432-020-03354-z
    125 schema:sdDatePublished 2022-10-01T06:47
    126 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    127 schema:sdPublisher Ne83433d6c501457fabf2eacd24e62772
    128 schema:url https://doi.org/10.1007/s00432-020-03354-z
    129 sgo:license sg:explorer/license/
    130 sgo:sdDataset articles
    131 rdf:type schema:ScholarlyArticle
    132 N00e8f91e96ee463f93022fabf8aa4284 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    133 schema:name Mutation
    134 rdf:type schema:DefinedTerm
    135 N02b4546bceb34b42b3330f946a627a01 rdf:first sg:person.013621452577.37
    136 rdf:rest Nf50cf5d6ef734d3192d657427c2f7f28
    137 N0a585e18db5949dd85d1730cd107af4e schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    138 schema:name Middle Aged
    139 rdf:type schema:DefinedTerm
    140 N0c4adc1c7f714645bbf9595f1d892039 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    141 schema:name Support Vector Machine
    142 rdf:type schema:DefinedTerm
    143 N1349ee0de8de47beb268b2469b7cf53e schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    144 schema:name Neoplasm Invasiveness
    145 rdf:type schema:DefinedTerm
    146 N13fd4a90ce8d466bad54e36d422ea8a9 schema:name pubmed_id
    147 schema:value 32779023
    148 rdf:type schema:PropertyValue
    149 N257e16ec78dc4e2bbb65eab3653bb26b rdf:first sg:person.0757632010.58
    150 rdf:rest N7a9c4453dccd45318fa72bce3a74e8d7
    151 N3feee328ec54466ca12e2ccc39bb60b3 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    152 schema:name Adult
    153 rdf:type schema:DefinedTerm
    154 N5d452512f50649e2af8c7a0c7533c232 rdf:first sg:person.013232656557.16
    155 rdf:rest rdf:nil
    156 N63fb7138c2174586836911109ec23a5a schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    157 schema:name Machine Learning
    158 rdf:type schema:DefinedTerm
    159 N6c294301c442468abd40c240d7e4caf0 rdf:first sg:person.013172121233.61
    160 rdf:rest N02b4546bceb34b42b3330f946a627a01
    161 N6d284d460bd749bb8bb428300edabd39 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    162 schema:name Male
    163 rdf:type schema:DefinedTerm
    164 N76b73ce3f20f4017b79cfdb032216f37 schema:name doi
    165 schema:value 10.1007/s00432-020-03354-z
    166 rdf:type schema:PropertyValue
    167 N7a9c4453dccd45318fa72bce3a74e8d7 rdf:first sg:person.0673022574.02
    168 rdf:rest Nf7049c1bff8b4acaa068ec48540f725f
    169 N826fe58adc0d4fe49cc80f3786164188 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    170 schema:name Colorectal Neoplasms
    171 rdf:type schema:DefinedTerm
    172 N83422f0915474ca3bb28a4a68617948f schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    173 schema:name Prognosis
    174 rdf:type schema:DefinedTerm
    175 N8434d231c682403088f044baf68ccc8f schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    176 schema:name Neoplasm Staging
    177 rdf:type schema:DefinedTerm
    178 Na01bfba62cbf432784410a901bf9d31d schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    179 schema:name Female
    180 rdf:type schema:DefinedTerm
    181 Na180f32a6ea34728ba667f7d76e58195 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    182 schema:name Colonic Neoplasms
    183 rdf:type schema:DefinedTerm
    184 Nabd37bbc052947ce98511520bfc53bc7 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    185 schema:name Humans
    186 rdf:type schema:DefinedTerm
    187 Naccb40c4656b425188e39b4c3f091220 schema:issueNumber 12
    188 rdf:type schema:PublicationIssue
    189 Nd2deb68a2cb244eaa68bc98ff81381ba schema:volumeNumber 146
    190 rdf:type schema:PublicationVolume
    191 Ne6205b8c5ec64844928f5ac1fb0d235b schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    192 schema:name Proto-Oncogene Proteins p21(ras)
    193 rdf:type schema:DefinedTerm
    194 Ne692118013564a0a940dc016d34fe051 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    195 schema:name Tomography, X-Ray Computed
    196 rdf:type schema:DefinedTerm
    197 Ne83433d6c501457fabf2eacd24e62772 schema:name Springer Nature - SN SciGraph project
    198 rdf:type schema:Organization
    199 Nf0d8a3790a194c26a4f7cb61787fc01b schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    200 schema:name Cohort Studies
    201 rdf:type schema:DefinedTerm
    202 Nf50cf5d6ef734d3192d657427c2f7f28 rdf:first sg:person.01134174205.19
    203 rdf:rest N5d452512f50649e2af8c7a0c7533c232
    204 Nf7049c1bff8b4acaa068ec48540f725f rdf:first sg:person.01035705477.86
    205 rdf:rest N6c294301c442468abd40c240d7e4caf0
    206 Nfa8d8304fecf4de7a6c8341e30a560eb schema:name dimensions_id
    207 schema:value pub.1130018892
    208 rdf:type schema:PropertyValue
    209 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
    210 schema:name Medical and Health Sciences
    211 rdf:type schema:DefinedTerm
    212 anzsrc-for:1112 schema:inDefinedTermSet anzsrc-for:
    213 schema:name Oncology and Carcinogenesis
    214 rdf:type schema:DefinedTerm
    215 sg:grant.4104005 http://pending.schema.org/fundedItem sg:pub.10.1007/s00432-020-03354-z
    216 rdf:type schema:MonetaryGrant
    217 sg:grant.5504653 http://pending.schema.org/fundedItem sg:pub.10.1007/s00432-020-03354-z
    218 rdf:type schema:MonetaryGrant
    219 sg:journal.1313647 schema:issn 0171-5216
    220 1432-1335
    221 schema:name Journal of Cancer Research and Clinical Oncology
    222 schema:publisher Springer Nature
    223 rdf:type schema:Periodical
    224 sg:person.01035705477.86 schema:affiliation grid-institutes:grid.16753.36
    225 schema:familyName Shangguan
    226 schema:givenName Junjie
    227 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01035705477.86
    228 rdf:type schema:Person
    229 sg:person.01134174205.19 schema:affiliation grid-institutes:None
    230 schema:familyName Yaghmai
    231 schema:givenName Vahid
    232 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01134174205.19
    233 rdf:type schema:Person
    234 sg:person.013172121233.61 schema:affiliation grid-institutes:grid.16753.36
    235 schema:familyName Yang
    236 schema:givenName Jia
    237 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013172121233.61
    238 rdf:type schema:Person
    239 sg:person.013232656557.16 schema:affiliation grid-institutes:grid.16753.36
    240 schema:familyName Zhang
    241 schema:givenName Zhuoli
    242 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013232656557.16
    243 rdf:type schema:Person
    244 sg:person.013621452577.37 schema:affiliation grid-institutes:grid.16753.36
    245 schema:familyName Benson
    246 schema:givenName Al B.
    247 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013621452577.37
    248 rdf:type schema:Person
    249 sg:person.0673022574.02 schema:affiliation grid-institutes:grid.16753.36
    250 schema:familyName Eresen
    251 schema:givenName Aydin
    252 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0673022574.02
    253 rdf:type schema:Person
    254 sg:person.0757632010.58 schema:affiliation grid-institutes:grid.16753.36
    255 schema:familyName Li
    256 schema:givenName Yu
    257 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0757632010.58
    258 rdf:type schema:Person
    259 sg:pub.10.1007/978-3-319-40618-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1108910915
    260 https://doi.org/10.1007/978-3-319-40618-3
    261 rdf:type schema:CreativeWork
    262 sg:pub.10.1007/s00330-018-5574-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105052211
    263 https://doi.org/10.1007/s00330-018-5574-0
    264 rdf:type schema:CreativeWork
    265 sg:pub.10.1007/s00432-018-2787-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111914663
    266 https://doi.org/10.1007/s00432-018-2787-1
    267 rdf:type schema:CreativeWork
    268 sg:pub.10.1007/s00432-018-2804-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111057432
    269 https://doi.org/10.1007/s00432-018-2804-4
    270 rdf:type schema:CreativeWork
    271 sg:pub.10.1007/s00432-019-03102-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1123020890
    272 https://doi.org/10.1007/s00432-019-03102-y
    273 rdf:type schema:CreativeWork
    274 sg:pub.10.1007/s11605-015-2761-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1015184303
    275 https://doi.org/10.1007/s11605-015-2761-z
    276 rdf:type schema:CreativeWork
    277 sg:pub.10.1023/a:1008280620621 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050540325
    278 https://doi.org/10.1023/a:1008280620621
    279 rdf:type schema:CreativeWork
    280 sg:pub.10.1038/nature11156 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024120060
    281 https://doi.org/10.1038/nature11156
    282 rdf:type schema:CreativeWork
    283 sg:pub.10.1038/nrclinonc.2017.141 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092061102
    284 https://doi.org/10.1038/nrclinonc.2017.141
    285 rdf:type schema:CreativeWork
    286 sg:pub.10.1038/s41598-020-67178-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1128742711
    287 https://doi.org/10.1038/s41598-020-67178-0
    288 rdf:type schema:CreativeWork
    289 sg:pub.10.1186/s12967-020-02246-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1124777619
    290 https://doi.org/10.1186/s12967-020-02246-7
    291 rdf:type schema:CreativeWork
    292 sg:pub.10.1186/s13014-016-0718-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049972050
    293 https://doi.org/10.1186/s13014-016-0718-3
    294 rdf:type schema:CreativeWork
    295 sg:pub.10.1186/s13046-018-0719-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101523019
    296 https://doi.org/10.1186/s13046-018-0719-1
    297 rdf:type schema:CreativeWork
    298 grid-institutes:None schema:alternateName Department of Radiological Sciences, University of California, Orange, Irvine, CA, USA
    299 schema:name Department of Radiological Sciences, University of California, Orange, Irvine, CA, USA
    300 Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA
    301 Robert Lurie Comprehensive Cancer Center of Northwestern University, Chicago, IL, USA
    302 rdf:type schema:Organization
    303 grid-institutes:grid.16753.36 schema:alternateName Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA
    304 Robert Lurie Comprehensive Cancer Center of Northwestern University, Chicago, IL, USA
    305 schema:name Department of Gastrointestinal Surgery, Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
    306 Department of Radiology, Feinberg School of Medicine, Northwestern University, 737 N. Michigan Ave, Suite 1600, 60611, Chicago, IL, USA
    307 Division of Hematology and Oncology, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA
    308 Robert Lurie Comprehensive Cancer Center of Northwestern University, Chicago, IL, USA
    309 rdf:type schema:Organization
     




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


    ...