Comparison of radiomics machine-learning classifiers and feature selection for differentiation of sacral chordoma and sacral giant cell tumour based on ... View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-04

AUTHORS

Ping Yin, Ning Mao, Chao Zhao, Jiangfen Wu, Chao Sun, Lei Chen, Nan Hong

ABSTRACT

OBJECTIVE: We aimed to identify optimal machine-learning methods for preoperative differentiation of sacral chordoma (SC) and sacral giant cell tumour (SGCT) based on 3D non-enhanced computed tomography (CT) and CT-enhanced (CTE) features. METHODS: A total of 95 patients were divided into a training set and a validation set. Three best feature selection methods (Relief, least absolute shrinkage and selection operator (LASSO) and Random Forest (RF)) and three classification methods, including generalised linear models (GLM), support vector machines (SVM) and RF, were compared for their performance in distinguishing SC and SGCT. The performance of the radiomics model was investigated via area under the receiver-operating characteristic curve (AUC) and accuracy (ACC) analysis. RESULTS: The selection method LASSO + classifier GLM had the highest AUC of 0.984 and ACC of 0.897 in the validating set, followed by Relief + GLM (AUC = 0.909, ACC = 0.862) and LASSO + SVM (AUC = 0.900, ACC = 0.862) based on CTE features. For CT features, RF + GLM had the highest AUC of 0.889, while LASSO + GLM achieved a high ACC of 0.793 in the validating set. Regardless of the methods, CTE features significantly outperformed those from CT for the differentiation of SC and SGCT (ZAUC = -3.029, ZACC = -4.553; p < 0.05). CONCLUSIONS: Our study demonstrated CTE features performed better than CT features. The selection method LASSO + classifier GLM had the best performance in differentiation of SC and SGCT, which could enhance the application of radiomics methods in sacral tumours. KEY POINTS: • Sacral chordoma and sacral giant cell tumour are the two most common primary tumours of the sacrum with many common clinical and imaging characteristics. • A radiomics model helps clinicians to identify the histology of a sacral tumour. • CTE features should be preferred. More... »

PAGES

1841-1847

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00330-018-5730-6

DOI

http://dx.doi.org/10.1007/s00330-018-5730-6

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1107361289

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/30280245


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/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Peking University People's Hospital", 
          "id": "https://www.grid.ac/institutes/grid.411634.5", 
          "name": [
            "Department of Radiology, Peking University People\u2019s Hospital, 11 Xizhimen Nandajie, Xicheng District, 100044, Beijing, People\u2019s Republic of China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Yin", 
        "givenName": "Ping", 
        "id": "sg:person.016636177415.97", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016636177415.97"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Yuhuangding Hospital", 
          "id": "https://www.grid.ac/institutes/grid.440323.2", 
          "name": [
            "Department of Radiology, Peking University People\u2019s Hospital, 11 Xizhimen Nandajie, Xicheng District, 100044, Beijing, People\u2019s Republic of China", 
            "Department of Radiology, Qindao University Medical College Affiliated Yantai Yuhuangding Hospital, Yantai, Shandong, People\u2019s Republic of China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Mao", 
        "givenName": "Ning", 
        "id": "sg:person.0715163031.86", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0715163031.86"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Peking University People's Hospital", 
          "id": "https://www.grid.ac/institutes/grid.411634.5", 
          "name": [
            "Department of Radiology, Peking University People\u2019s Hospital, 11 Xizhimen Nandajie, Xicheng District, 100044, Beijing, People\u2019s Republic of China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhao", 
        "givenName": "Chao", 
        "id": "sg:person.010463626560.59", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010463626560.59"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "GE Healthcare, Shanghai, People\u2019s Republic of China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wu", 
        "givenName": "Jiangfen", 
        "id": "sg:person.011127517134.39", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011127517134.39"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Peking University People's Hospital", 
          "id": "https://www.grid.ac/institutes/grid.411634.5", 
          "name": [
            "Department of Radiology, Peking University People\u2019s Hospital, 11 Xizhimen Nandajie, Xicheng District, 100044, Beijing, People\u2019s Republic of China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sun", 
        "givenName": "Chao", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Peking University People's Hospital", 
          "id": "https://www.grid.ac/institutes/grid.411634.5", 
          "name": [
            "Department of Radiology, Peking University People\u2019s Hospital, 11 Xizhimen Nandajie, Xicheng District, 100044, Beijing, People\u2019s Republic of China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Chen", 
        "givenName": "Lei", 
        "id": "sg:person.016360033651.69", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016360033651.69"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Peking University People's Hospital", 
          "id": "https://www.grid.ac/institutes/grid.411634.5", 
          "name": [
            "Department of Radiology, Peking University People\u2019s Hospital, 11 Xizhimen Nandajie, Xicheng District, 100044, Beijing, People\u2019s Republic of China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hong", 
        "givenName": "Nan", 
        "id": "sg:person.015105560271.08", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015105560271.08"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.3389/fonc.2015.00272", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000390901"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.artmed.2008.04.007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001839150"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.ejrad.2013.08.034", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004714161"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00586-015-4276-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1013766917", 
          "https://doi.org/10.1007/s00586-015-4276-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/access.2014.2373335", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020544337"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/23808993.2016.1164013", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022908029"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1010933404324", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024739340", 
          "https://doi.org/10.1023/a:1010933404324"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/jmri.25156", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034126892"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/jmri.25156", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034126892"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/srep13087", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036587522", 
          "https://doi.org/10.1038/srep13087"
        ], 
        "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/10.3389/fonc.2016.00071", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040319901"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00256-007-0413-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041603166", 
          "https://doi.org/10.1007/s00256-007-0413-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pone.0099567", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044957353"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11999-016-4773-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1046554814", 
          "https://doi.org/10.1007/s11999-016-4773-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11999-016-4773-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1046554814", 
          "https://doi.org/10.1007/s11999-016-4773-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1007/s11999-016-4773-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1046554814"
        ], 
        "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/10.1259/bjr.20160665", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064566189"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1259/bjr/25247602", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064568624"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1148/radiol.2016160845", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1079288591"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.artmed.2017.03.004", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1084060045"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1158/1078-0432.ccr-16-2910", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1084230888"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1158/1078-0432.ccr-16-2910", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1084230888"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00330-017-4855-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085440427", 
          "https://doi.org/10.1007/s00330-017-4855-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00330-017-4855-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085440427", 
          "https://doi.org/10.1007/s00330-017-4855-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00330-017-4855-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085440427", 
          "https://doi.org/10.1007/s00330-017-4855-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.ejmp.2017.05.071", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085909267"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.canlet.2017.06.004", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085967174"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.canlet.2017.06.004", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085967174"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s13550-017-0310-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090901083", 
          "https://doi.org/10.1186/s13550-017-0310-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s13550-017-0310-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090901083", 
          "https://doi.org/10.1186/s13550-017-0310-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/s41598-017-09315-w", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091232499", 
          "https://doi.org/10.1038/s41598-017-09315-w"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/s41598-017-09315-w", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091232499", 
          "https://doi.org/10.1038/s41598-017-09315-w"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/s41598-017-09315-w", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091232499", 
          "https://doi.org/10.1038/s41598-017-09315-w"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1158/1078-0432.ccr-17-1510", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091613442"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1148/rg.2017170056", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091621070"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.tranon.2017.08.007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091841385"
        ], 
        "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": "https://doi.org/10.1002/jmri.25874", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092246265"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.22038/abjs.2017.19899.1548", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100455206"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/jmri.25969", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100989882"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00330-017-5221-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101056577", 
          "https://doi.org/10.1007/s00330-017-5221-1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00330-017-5221-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101056577", 
          "https://doi.org/10.1007/s00330-017-5221-1"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-04", 
    "datePublishedReg": "2019-04-01", 
    "description": "OBJECTIVE: We aimed to identify optimal machine-learning methods for preoperative differentiation of sacral chordoma (SC) and sacral giant cell tumour (SGCT) based on 3D non-enhanced computed tomography (CT) and CT-enhanced (CTE) features.\nMETHODS: A total of 95 patients were divided into a training set and a validation set. Three best feature selection methods (Relief, least absolute shrinkage and selection operator (LASSO) and Random Forest (RF)) and three classification methods, including generalised linear models (GLM), support vector machines (SVM) and RF, were compared for their performance in distinguishing SC and SGCT. The performance of the radiomics model was investigated via area under the receiver-operating characteristic curve (AUC) and accuracy (ACC) analysis.\nRESULTS: The selection method LASSO + classifier GLM had the highest AUC of 0.984 and ACC of 0.897 in the validating set, followed by Relief + GLM (AUC = 0.909, ACC = 0.862) and LASSO + SVM (AUC = 0.900, ACC = 0.862) based on CTE features. For CT features, RF + GLM had the highest AUC of 0.889, while LASSO + GLM achieved a high ACC of 0.793 in the validating set. Regardless of the methods, CTE features significantly outperformed those from CT for the differentiation of SC and SGCT (ZAUC = -3.029, ZACC = -4.553; p < 0.05).\nCONCLUSIONS: Our study demonstrated CTE features performed better than CT features. The selection method LASSO + classifier GLM had the best performance in differentiation of SC and SGCT, which could enhance the application of radiomics methods in sacral tumours.\nKEY POINTS: \u2022 Sacral chordoma and sacral giant cell tumour are the two most common primary tumours of the sacrum with many common clinical and imaging characteristics. \u2022 A radiomics model helps clinicians to identify the histology of a sacral tumour. \u2022 CTE features should be preferred.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s00330-018-5730-6", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1289120", 
        "issn": [
          "0938-7994", 
          "1432-1084"
        ], 
        "name": "European Radiology", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "4", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "29"
      }
    ], 
    "name": "Comparison of radiomics machine-learning classifiers and feature selection for differentiation of sacral chordoma and sacral giant cell tumour based on 3D computed tomography features", 
    "pagination": "1841-1847", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "d331f16505b3bfea5d5d5417b1e026a1ec8095e93a9ca8dffe41b23a6f23c0b8"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "30280245"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "9114774"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00330-018-5730-6"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1107361289"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00330-018-5730-6", 
      "https://app.dimensions.ai/details/publication/pub.1107361289"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T13:19", 
    "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/v90/0000000368_0000000368/records_78950_00000001.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs00330-018-5730-6"
  }
]
 

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/s00330-018-5730-6'

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/s00330-018-5730-6'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00330-018-5730-6'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00330-018-5730-6'


 

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

228 TRIPLES      21 PREDICATES      63 URIs      21 LITERALS      9 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00330-018-5730-6 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N7fb630294996497583da0c21ca39ec75
4 schema:citation sg:pub.10.1007/s00256-007-0413-4
5 sg:pub.10.1007/s00330-017-4855-3
6 sg:pub.10.1007/s00330-017-5221-1
7 sg:pub.10.1007/s00586-015-4276-4
8 sg:pub.10.1007/s11999-016-4773-8
9 sg:pub.10.1023/a:1010933404324
10 sg:pub.10.1038/nrclinonc.2017.141
11 sg:pub.10.1038/s41598-017-09315-w
12 sg:pub.10.1038/srep13087
13 sg:pub.10.1186/s13550-017-0310-3
14 https://doi.org/10.1002/jmri.25156
15 https://doi.org/10.1002/jmri.25874
16 https://doi.org/10.1002/jmri.25969
17 https://doi.org/10.1007/s11999-016-4773-8
18 https://doi.org/10.1016/j.artmed.2008.04.007
19 https://doi.org/10.1016/j.artmed.2017.03.004
20 https://doi.org/10.1016/j.canlet.2017.06.004
21 https://doi.org/10.1016/j.ejmp.2017.05.071
22 https://doi.org/10.1016/j.ejrad.2013.08.034
23 https://doi.org/10.1016/j.tranon.2017.08.007
24 https://doi.org/10.1080/23808993.2016.1164013
25 https://doi.org/10.1088/0031-9155/60/14/5471
26 https://doi.org/10.1088/0031-9155/61/13/r150
27 https://doi.org/10.1109/access.2014.2373335
28 https://doi.org/10.1148/radiol.2016160845
29 https://doi.org/10.1148/rg.2017170056
30 https://doi.org/10.1158/1078-0432.ccr-16-2910
31 https://doi.org/10.1158/1078-0432.ccr-17-1510
32 https://doi.org/10.1259/bjr.20160665
33 https://doi.org/10.1259/bjr/25247602
34 https://doi.org/10.1371/journal.pone.0099567
35 https://doi.org/10.22038/abjs.2017.19899.1548
36 https://doi.org/10.3389/fonc.2015.00272
37 https://doi.org/10.3389/fonc.2016.00071
38 schema:datePublished 2019-04
39 schema:datePublishedReg 2019-04-01
40 schema:description OBJECTIVE: We aimed to identify optimal machine-learning methods for preoperative differentiation of sacral chordoma (SC) and sacral giant cell tumour (SGCT) based on 3D non-enhanced computed tomography (CT) and CT-enhanced (CTE) features. METHODS: A total of 95 patients were divided into a training set and a validation set. Three best feature selection methods (Relief, least absolute shrinkage and selection operator (LASSO) and Random Forest (RF)) and three classification methods, including generalised linear models (GLM), support vector machines (SVM) and RF, were compared for their performance in distinguishing SC and SGCT. The performance of the radiomics model was investigated via area under the receiver-operating characteristic curve (AUC) and accuracy (ACC) analysis. RESULTS: The selection method LASSO + classifier GLM had the highest AUC of 0.984 and ACC of 0.897 in the validating set, followed by Relief + GLM (AUC = 0.909, ACC = 0.862) and LASSO + SVM (AUC = 0.900, ACC = 0.862) based on CTE features. For CT features, RF + GLM had the highest AUC of 0.889, while LASSO + GLM achieved a high ACC of 0.793 in the validating set. Regardless of the methods, CTE features significantly outperformed those from CT for the differentiation of SC and SGCT (ZAUC = -3.029, ZACC = -4.553; p < 0.05). CONCLUSIONS: Our study demonstrated CTE features performed better than CT features. The selection method LASSO + classifier GLM had the best performance in differentiation of SC and SGCT, which could enhance the application of radiomics methods in sacral tumours. KEY POINTS: • Sacral chordoma and sacral giant cell tumour are the two most common primary tumours of the sacrum with many common clinical and imaging characteristics. • A radiomics model helps clinicians to identify the histology of a sacral tumour. • CTE features should be preferred.
41 schema:genre research_article
42 schema:inLanguage en
43 schema:isAccessibleForFree false
44 schema:isPartOf Ndb0dc8b65a8f47c5ada9a9e65b5ce83f
45 Ndfe3651f15e049c6990a2f4f94283324
46 sg:journal.1289120
47 schema:name Comparison of radiomics machine-learning classifiers and feature selection for differentiation of sacral chordoma and sacral giant cell tumour based on 3D computed tomography features
48 schema:pagination 1841-1847
49 schema:productId N0f90d36eacdf40afa6cc5245dd172d13
50 N2ea910db504d462683573e88d1f599da
51 N2fdf88e76d61452da466aa51f46194c4
52 N4415a6c116324e92ac5e62cfb91d5711
53 N751034431d26404791eba6d654ddaf40
54 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107361289
55 https://doi.org/10.1007/s00330-018-5730-6
56 schema:sdDatePublished 2019-04-11T13:19
57 schema:sdLicense https://scigraph.springernature.com/explorer/license/
58 schema:sdPublisher N845509dc2d1b44d192d721a1b3b5c0ab
59 schema:url https://link.springer.com/10.1007%2Fs00330-018-5730-6
60 sgo:license sg:explorer/license/
61 sgo:sdDataset articles
62 rdf:type schema:ScholarlyArticle
63 N0f90d36eacdf40afa6cc5245dd172d13 schema:name readcube_id
64 schema:value d331f16505b3bfea5d5d5417b1e026a1ec8095e93a9ca8dffe41b23a6f23c0b8
65 rdf:type schema:PropertyValue
66 N2ea910db504d462683573e88d1f599da schema:name doi
67 schema:value 10.1007/s00330-018-5730-6
68 rdf:type schema:PropertyValue
69 N2fdf88e76d61452da466aa51f46194c4 schema:name dimensions_id
70 schema:value pub.1107361289
71 rdf:type schema:PropertyValue
72 N4415a6c116324e92ac5e62cfb91d5711 schema:name nlm_unique_id
73 schema:value 9114774
74 rdf:type schema:PropertyValue
75 N4b1ce76334a0471e8eb4bf4f64079f6f rdf:first sg:person.015105560271.08
76 rdf:rest rdf:nil
77 N60d4d3f005e14beda7373f83a6531f30 schema:affiliation https://www.grid.ac/institutes/grid.411634.5
78 schema:familyName Sun
79 schema:givenName Chao
80 rdf:type schema:Person
81 N6b4191d0695246c99ece3db3ae0ec7e4 rdf:first sg:person.010463626560.59
82 rdf:rest N86fb1565f37b418886d88e7336aeda7f
83 N751034431d26404791eba6d654ddaf40 schema:name pubmed_id
84 schema:value 30280245
85 rdf:type schema:PropertyValue
86 N7fb630294996497583da0c21ca39ec75 rdf:first sg:person.016636177415.97
87 rdf:rest N83c029db99fa449a85980a32bb14d624
88 N83c029db99fa449a85980a32bb14d624 rdf:first sg:person.0715163031.86
89 rdf:rest N6b4191d0695246c99ece3db3ae0ec7e4
90 N845509dc2d1b44d192d721a1b3b5c0ab schema:name Springer Nature - SN SciGraph project
91 rdf:type schema:Organization
92 N86fb1565f37b418886d88e7336aeda7f rdf:first sg:person.011127517134.39
93 rdf:rest Ned9a01ec7459473e98c4c6cb369aea24
94 N8dfe62524ce44d618a8598ceffb791fe schema:name GE Healthcare, Shanghai, People’s Republic of China
95 rdf:type schema:Organization
96 Nd130d6cd31204b81a76703e71a3150a6 rdf:first sg:person.016360033651.69
97 rdf:rest N4b1ce76334a0471e8eb4bf4f64079f6f
98 Ndb0dc8b65a8f47c5ada9a9e65b5ce83f schema:issueNumber 4
99 rdf:type schema:PublicationIssue
100 Ndfe3651f15e049c6990a2f4f94283324 schema:volumeNumber 29
101 rdf:type schema:PublicationVolume
102 Ned9a01ec7459473e98c4c6cb369aea24 rdf:first N60d4d3f005e14beda7373f83a6531f30
103 rdf:rest Nd130d6cd31204b81a76703e71a3150a6
104 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
105 schema:name Information and Computing Sciences
106 rdf:type schema:DefinedTerm
107 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
108 schema:name Artificial Intelligence and Image Processing
109 rdf:type schema:DefinedTerm
110 sg:journal.1289120 schema:issn 0938-7994
111 1432-1084
112 schema:name European Radiology
113 rdf:type schema:Periodical
114 sg:person.010463626560.59 schema:affiliation https://www.grid.ac/institutes/grid.411634.5
115 schema:familyName Zhao
116 schema:givenName Chao
117 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010463626560.59
118 rdf:type schema:Person
119 sg:person.011127517134.39 schema:affiliation N8dfe62524ce44d618a8598ceffb791fe
120 schema:familyName Wu
121 schema:givenName Jiangfen
122 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011127517134.39
123 rdf:type schema:Person
124 sg:person.015105560271.08 schema:affiliation https://www.grid.ac/institutes/grid.411634.5
125 schema:familyName Hong
126 schema:givenName Nan
127 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015105560271.08
128 rdf:type schema:Person
129 sg:person.016360033651.69 schema:affiliation https://www.grid.ac/institutes/grid.411634.5
130 schema:familyName Chen
131 schema:givenName Lei
132 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016360033651.69
133 rdf:type schema:Person
134 sg:person.016636177415.97 schema:affiliation https://www.grid.ac/institutes/grid.411634.5
135 schema:familyName Yin
136 schema:givenName Ping
137 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016636177415.97
138 rdf:type schema:Person
139 sg:person.0715163031.86 schema:affiliation https://www.grid.ac/institutes/grid.440323.2
140 schema:familyName Mao
141 schema:givenName Ning
142 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0715163031.86
143 rdf:type schema:Person
144 sg:pub.10.1007/s00256-007-0413-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041603166
145 https://doi.org/10.1007/s00256-007-0413-4
146 rdf:type schema:CreativeWork
147 sg:pub.10.1007/s00330-017-4855-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085440427
148 https://doi.org/10.1007/s00330-017-4855-3
149 rdf:type schema:CreativeWork
150 sg:pub.10.1007/s00330-017-5221-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101056577
151 https://doi.org/10.1007/s00330-017-5221-1
152 rdf:type schema:CreativeWork
153 sg:pub.10.1007/s00586-015-4276-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013766917
154 https://doi.org/10.1007/s00586-015-4276-4
155 rdf:type schema:CreativeWork
156 sg:pub.10.1007/s11999-016-4773-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046554814
157 https://doi.org/10.1007/s11999-016-4773-8
158 rdf:type schema:CreativeWork
159 sg:pub.10.1023/a:1010933404324 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024739340
160 https://doi.org/10.1023/a:1010933404324
161 rdf:type schema:CreativeWork
162 sg:pub.10.1038/nrclinonc.2017.141 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092061102
163 https://doi.org/10.1038/nrclinonc.2017.141
164 rdf:type schema:CreativeWork
165 sg:pub.10.1038/s41598-017-09315-w schema:sameAs https://app.dimensions.ai/details/publication/pub.1091232499
166 https://doi.org/10.1038/s41598-017-09315-w
167 rdf:type schema:CreativeWork
168 sg:pub.10.1038/srep13087 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036587522
169 https://doi.org/10.1038/srep13087
170 rdf:type schema:CreativeWork
171 sg:pub.10.1186/s13550-017-0310-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090901083
172 https://doi.org/10.1186/s13550-017-0310-3
173 rdf:type schema:CreativeWork
174 https://doi.org/10.1002/jmri.25156 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034126892
175 rdf:type schema:CreativeWork
176 https://doi.org/10.1002/jmri.25874 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092246265
177 rdf:type schema:CreativeWork
178 https://doi.org/10.1002/jmri.25969 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100989882
179 rdf:type schema:CreativeWork
180 https://doi.org/10.1007/s11999-016-4773-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046554814
181 rdf:type schema:CreativeWork
182 https://doi.org/10.1016/j.artmed.2008.04.007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001839150
183 rdf:type schema:CreativeWork
184 https://doi.org/10.1016/j.artmed.2017.03.004 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084060045
185 rdf:type schema:CreativeWork
186 https://doi.org/10.1016/j.canlet.2017.06.004 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085967174
187 rdf:type schema:CreativeWork
188 https://doi.org/10.1016/j.ejmp.2017.05.071 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085909267
189 rdf:type schema:CreativeWork
190 https://doi.org/10.1016/j.ejrad.2013.08.034 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004714161
191 rdf:type schema:CreativeWork
192 https://doi.org/10.1016/j.tranon.2017.08.007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091841385
193 rdf:type schema:CreativeWork
194 https://doi.org/10.1080/23808993.2016.1164013 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022908029
195 rdf:type schema:CreativeWork
196 https://doi.org/10.1088/0031-9155/60/14/5471 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038681832
197 rdf:type schema:CreativeWork
198 https://doi.org/10.1088/0031-9155/61/13/r150 schema:sameAs https://app.dimensions.ai/details/publication/pub.1059031442
199 rdf:type schema:CreativeWork
200 https://doi.org/10.1109/access.2014.2373335 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020544337
201 rdf:type schema:CreativeWork
202 https://doi.org/10.1148/radiol.2016160845 schema:sameAs https://app.dimensions.ai/details/publication/pub.1079288591
203 rdf:type schema:CreativeWork
204 https://doi.org/10.1148/rg.2017170056 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091621070
205 rdf:type schema:CreativeWork
206 https://doi.org/10.1158/1078-0432.ccr-16-2910 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084230888
207 rdf:type schema:CreativeWork
208 https://doi.org/10.1158/1078-0432.ccr-17-1510 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091613442
209 rdf:type schema:CreativeWork
210 https://doi.org/10.1259/bjr.20160665 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064566189
211 rdf:type schema:CreativeWork
212 https://doi.org/10.1259/bjr/25247602 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064568624
213 rdf:type schema:CreativeWork
214 https://doi.org/10.1371/journal.pone.0099567 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044957353
215 rdf:type schema:CreativeWork
216 https://doi.org/10.22038/abjs.2017.19899.1548 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100455206
217 rdf:type schema:CreativeWork
218 https://doi.org/10.3389/fonc.2015.00272 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000390901
219 rdf:type schema:CreativeWork
220 https://doi.org/10.3389/fonc.2016.00071 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040319901
221 rdf:type schema:CreativeWork
222 https://www.grid.ac/institutes/grid.411634.5 schema:alternateName Peking University People's Hospital
223 schema:name Department of Radiology, Peking University People’s Hospital, 11 Xizhimen Nandajie, Xicheng District, 100044, Beijing, People’s Republic of China
224 rdf:type schema:Organization
225 https://www.grid.ac/institutes/grid.440323.2 schema:alternateName Yuhuangding Hospital
226 schema:name Department of Radiology, Peking University People’s Hospital, 11 Xizhimen Nandajie, Xicheng District, 100044, Beijing, People’s Republic of China
227 Department of Radiology, Qindao University Medical College Affiliated Yantai Yuhuangding Hospital, Yantai, Shandong, People’s Republic of China
228 rdf:type schema:Organization
 




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


...