Machine learning concepts, concerns and opportunities for a pediatric radiologist View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-04

AUTHORS

Michael M. Moore, Einat Slonimsky, Aaron D. Long, Raymond W. Sze, Ramesh S. Iyer

ABSTRACT

Machine learning, a subfield of artificial intelligence, is a rapidly evolving technology that offers great potential for expanding the quality and value of pediatric radiology. We describe specific types of learning, including supervised, unsupervised and semisupervised. Subsequently, we illustrate two core concepts for the reader: data partitioning and under/overfitting. We also provide an expanded discussion of the challenges of implementing machine learning in children's imaging. These include the requirement for very large data sets, the need to accurately label these images with a relatively small number of pediatric imagers, technical and regulatory hurdles, as well as the opaque character of convolution neural networks. We review machine learning cases in radiology including detection, classification and segmentation. Last, three pediatric radiologists from the Society for Pediatric Radiology Quality and Safety Committee share perspectives for potential areas of development. More... »

PAGES

509-516

References to SciGraph publications

  • 2015-05. Deep learning in NATURE
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s00247-018-4277-7

    DOI

    http://dx.doi.org/10.1007/s00247-018-4277-7

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1113063416

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/30923883


    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": {
              "name": [
                "Department of Radiology, Penn State Health, Mail Code H066, 500 University Drive, P.O. Box 850, 17033-0850, Hershey, PA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Moore", 
            "givenName": "Michael M.", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Department of Radiology, Penn State Health, Mail Code H066, 500 University Drive, P.O. Box 850, 17033-0850, Hershey, PA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Slonimsky", 
            "givenName": "Einat", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Department of Radiology, Penn State Health, Mail Code H066, 500 University Drive, P.O. Box 850, 17033-0850, Hershey, PA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Long", 
            "givenName": "Aaron D.", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Children's Hospital of Philadelphia", 
              "id": "https://www.grid.ac/institutes/grid.239552.a", 
              "name": [
                "Department of Radiology, Children\u2019s Hospital of Philadelphia, Philadelphia, PA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Sze", 
            "givenName": "Raymond W.", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Seattle Children's Hospital", 
              "id": "https://www.grid.ac/institutes/grid.240741.4", 
              "name": [
                "Department of Radiology, Seattle Children\u2019s Hospital, Seattle, WA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Iyer", 
            "givenName": "Ramesh S.", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1155/2012/792079", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1000796165"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature14539", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1010020120", 
              "https://doi.org/10.1038/nature14539"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1118/1.4948498", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020296549"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2200/s00196ed1v01y200906aim006", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1069288077"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1148/rg.2017160130", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1083846665"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.jacr.2017.02.019", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1084083884"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1148/radiol.2017162326", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085056202"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1001/jama.2017.7797", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1090830597"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.media.2017.07.005", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1090904008"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2741/4606", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091930620"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1148/radiol.2017170236", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092517712"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1148/rg.2017170077", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092685376"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.jacr.2017.12.024", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100793474"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.jacr.2017.11.035", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100828247"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.7551/mitpress/9780262033589.001.0001", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1108730677"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2019-04", 
        "datePublishedReg": "2019-04-01", 
        "description": "Machine learning, a subfield of artificial intelligence, is a rapidly evolving technology that offers great potential for expanding the quality and value of pediatric radiology. We describe specific types of learning, including supervised, unsupervised and semisupervised. Subsequently, we illustrate two core concepts for the reader: data partitioning and under/overfitting. We also provide an expanded discussion of the challenges of implementing machine learning in children's imaging. These include the requirement for very large data sets, the need to accurately label these images with a relatively small number of pediatric imagers, technical and regulatory hurdles, as well as the opaque character of convolution neural networks. We review machine learning cases in radiology including detection, classification and segmentation. Last, three pediatric radiologists from the Society for Pediatric Radiology Quality and Safety Committee share perspectives for potential areas of development.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s00247-018-4277-7", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1016713", 
            "issn": [
              "0301-0449", 
              "1432-1998"
            ], 
            "name": "Pediatric Radiology", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "4", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "49"
          }
        ], 
        "name": "Machine learning concepts, concerns and opportunities for a pediatric radiologist", 
        "pagination": "509-516", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "18a15d3e01effc543a17c943800dcb287bbbb1dc73268e661bd811412791ee88"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "30923883"
            ]
          }, 
          {
            "name": "nlm_unique_id", 
            "type": "PropertyValue", 
            "value": [
              "0365332"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s00247-018-4277-7"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1113063416"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s00247-018-4277-7", 
          "https://app.dimensions.ai/details/publication/pub.1113063416"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T13:33", 
        "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/v90/0000000370_0000000370/records_46766_00000003.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1007%2Fs00247-018-4277-7"
      }
    ]
     

    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/s00247-018-4277-7'

    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/s00247-018-4277-7'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00247-018-4277-7'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00247-018-4277-7'


     

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

    147 TRIPLES      21 PREDICATES      44 URIs      21 LITERALS      9 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s00247-018-4277-7 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N3f97b37bf9c24d1ba2ede80b7d3ca0e8
    4 schema:citation sg:pub.10.1038/nature14539
    5 https://doi.org/10.1001/jama.2017.7797
    6 https://doi.org/10.1016/j.jacr.2017.02.019
    7 https://doi.org/10.1016/j.jacr.2017.11.035
    8 https://doi.org/10.1016/j.jacr.2017.12.024
    9 https://doi.org/10.1016/j.media.2017.07.005
    10 https://doi.org/10.1118/1.4948498
    11 https://doi.org/10.1148/radiol.2017162326
    12 https://doi.org/10.1148/radiol.2017170236
    13 https://doi.org/10.1148/rg.2017160130
    14 https://doi.org/10.1148/rg.2017170077
    15 https://doi.org/10.1155/2012/792079
    16 https://doi.org/10.2200/s00196ed1v01y200906aim006
    17 https://doi.org/10.2741/4606
    18 https://doi.org/10.7551/mitpress/9780262033589.001.0001
    19 schema:datePublished 2019-04
    20 schema:datePublishedReg 2019-04-01
    21 schema:description Machine learning, a subfield of artificial intelligence, is a rapidly evolving technology that offers great potential for expanding the quality and value of pediatric radiology. We describe specific types of learning, including supervised, unsupervised and semisupervised. Subsequently, we illustrate two core concepts for the reader: data partitioning and under/overfitting. We also provide an expanded discussion of the challenges of implementing machine learning in children's imaging. These include the requirement for very large data sets, the need to accurately label these images with a relatively small number of pediatric imagers, technical and regulatory hurdles, as well as the opaque character of convolution neural networks. We review machine learning cases in radiology including detection, classification and segmentation. Last, three pediatric radiologists from the Society for Pediatric Radiology Quality and Safety Committee share perspectives for potential areas of development.
    22 schema:genre research_article
    23 schema:inLanguage en
    24 schema:isAccessibleForFree false
    25 schema:isPartOf N07f591da1b2c46738389c28b10662f92
    26 Nd1b0a319823044709853893675c3a42f
    27 sg:journal.1016713
    28 schema:name Machine learning concepts, concerns and opportunities for a pediatric radiologist
    29 schema:pagination 509-516
    30 schema:productId N2aa5b17b4e6b4cc194d3110776ff34ed
    31 N8017e86b653c4ed39e25ae541777dcd8
    32 Na302a9f300df4160be30e7fc42a12e7f
    33 Nc103a776e1c942d9a223065f1743215b
    34 Nd6dc94411ffe4b138758b9575075d28d
    35 schema:sameAs https://app.dimensions.ai/details/publication/pub.1113063416
    36 https://doi.org/10.1007/s00247-018-4277-7
    37 schema:sdDatePublished 2019-04-11T13:33
    38 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    39 schema:sdPublisher Na9304a67c4c744e9b00bd3bf4997714f
    40 schema:url https://link.springer.com/10.1007%2Fs00247-018-4277-7
    41 sgo:license sg:explorer/license/
    42 sgo:sdDataset articles
    43 rdf:type schema:ScholarlyArticle
    44 N07f591da1b2c46738389c28b10662f92 schema:issueNumber 4
    45 rdf:type schema:PublicationIssue
    46 N259902cab4e94812bbcce7e9aef5c25e schema:affiliation https://www.grid.ac/institutes/grid.239552.a
    47 schema:familyName Sze
    48 schema:givenName Raymond W.
    49 rdf:type schema:Person
    50 N2aa5b17b4e6b4cc194d3110776ff34ed schema:name dimensions_id
    51 schema:value pub.1113063416
    52 rdf:type schema:PropertyValue
    53 N33ac3b6d1d284241b7c1f8dcdeeb4fa5 schema:affiliation N839ef9235f774eeb9b3d3f8f02890682
    54 schema:familyName Long
    55 schema:givenName Aaron D.
    56 rdf:type schema:Person
    57 N3f97b37bf9c24d1ba2ede80b7d3ca0e8 rdf:first Nc40f91bfb83e41f3ac9ca11700b02dee
    58 rdf:rest N808a391fc2f84587bfd9acb6dac65963
    59 N5349ee814e5b46cc8ce38aa7b3fa8fe2 schema:name Department of Radiology, Penn State Health, Mail Code H066, 500 University Drive, P.O. Box 850, 17033-0850, Hershey, PA, USA
    60 rdf:type schema:Organization
    61 N6dd512c9154844bea0df11a3f32b9825 rdf:first Na1116de087014dbc8d111e7038db0067
    62 rdf:rest rdf:nil
    63 N8017e86b653c4ed39e25ae541777dcd8 schema:name readcube_id
    64 schema:value 18a15d3e01effc543a17c943800dcb287bbbb1dc73268e661bd811412791ee88
    65 rdf:type schema:PropertyValue
    66 N808a391fc2f84587bfd9acb6dac65963 rdf:first Na6fb7d7919284af99d85253c98a24877
    67 rdf:rest Nc4b0a70d87344f828eda4bafdf63c252
    68 N839ef9235f774eeb9b3d3f8f02890682 schema:name Department of Radiology, Penn State Health, Mail Code H066, 500 University Drive, P.O. Box 850, 17033-0850, Hershey, PA, USA
    69 rdf:type schema:Organization
    70 N8e87be5e12234ab69c893bc3287b6655 rdf:first N259902cab4e94812bbcce7e9aef5c25e
    71 rdf:rest N6dd512c9154844bea0df11a3f32b9825
    72 Na1116de087014dbc8d111e7038db0067 schema:affiliation https://www.grid.ac/institutes/grid.240741.4
    73 schema:familyName Iyer
    74 schema:givenName Ramesh S.
    75 rdf:type schema:Person
    76 Na302a9f300df4160be30e7fc42a12e7f schema:name nlm_unique_id
    77 schema:value 0365332
    78 rdf:type schema:PropertyValue
    79 Na6fb7d7919284af99d85253c98a24877 schema:affiliation N5349ee814e5b46cc8ce38aa7b3fa8fe2
    80 schema:familyName Slonimsky
    81 schema:givenName Einat
    82 rdf:type schema:Person
    83 Na9304a67c4c744e9b00bd3bf4997714f schema:name Springer Nature - SN SciGraph project
    84 rdf:type schema:Organization
    85 Nc103a776e1c942d9a223065f1743215b schema:name doi
    86 schema:value 10.1007/s00247-018-4277-7
    87 rdf:type schema:PropertyValue
    88 Nc40f91bfb83e41f3ac9ca11700b02dee schema:affiliation Nff7c433ce29248ec82a125d706e6452d
    89 schema:familyName Moore
    90 schema:givenName Michael M.
    91 rdf:type schema:Person
    92 Nc4b0a70d87344f828eda4bafdf63c252 rdf:first N33ac3b6d1d284241b7c1f8dcdeeb4fa5
    93 rdf:rest N8e87be5e12234ab69c893bc3287b6655
    94 Nd1b0a319823044709853893675c3a42f schema:volumeNumber 49
    95 rdf:type schema:PublicationVolume
    96 Nd6dc94411ffe4b138758b9575075d28d schema:name pubmed_id
    97 schema:value 30923883
    98 rdf:type schema:PropertyValue
    99 Nff7c433ce29248ec82a125d706e6452d schema:name Department of Radiology, Penn State Health, Mail Code H066, 500 University Drive, P.O. Box 850, 17033-0850, Hershey, PA, USA
    100 rdf:type schema:Organization
    101 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    102 schema:name Information and Computing Sciences
    103 rdf:type schema:DefinedTerm
    104 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    105 schema:name Artificial Intelligence and Image Processing
    106 rdf:type schema:DefinedTerm
    107 sg:journal.1016713 schema:issn 0301-0449
    108 1432-1998
    109 schema:name Pediatric Radiology
    110 rdf:type schema:Periodical
    111 sg:pub.10.1038/nature14539 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010020120
    112 https://doi.org/10.1038/nature14539
    113 rdf:type schema:CreativeWork
    114 https://doi.org/10.1001/jama.2017.7797 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090830597
    115 rdf:type schema:CreativeWork
    116 https://doi.org/10.1016/j.jacr.2017.02.019 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084083884
    117 rdf:type schema:CreativeWork
    118 https://doi.org/10.1016/j.jacr.2017.11.035 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100828247
    119 rdf:type schema:CreativeWork
    120 https://doi.org/10.1016/j.jacr.2017.12.024 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100793474
    121 rdf:type schema:CreativeWork
    122 https://doi.org/10.1016/j.media.2017.07.005 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090904008
    123 rdf:type schema:CreativeWork
    124 https://doi.org/10.1118/1.4948498 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020296549
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.1148/radiol.2017162326 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085056202
    127 rdf:type schema:CreativeWork
    128 https://doi.org/10.1148/radiol.2017170236 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092517712
    129 rdf:type schema:CreativeWork
    130 https://doi.org/10.1148/rg.2017160130 schema:sameAs https://app.dimensions.ai/details/publication/pub.1083846665
    131 rdf:type schema:CreativeWork
    132 https://doi.org/10.1148/rg.2017170077 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092685376
    133 rdf:type schema:CreativeWork
    134 https://doi.org/10.1155/2012/792079 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000796165
    135 rdf:type schema:CreativeWork
    136 https://doi.org/10.2200/s00196ed1v01y200906aim006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069288077
    137 rdf:type schema:CreativeWork
    138 https://doi.org/10.2741/4606 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091930620
    139 rdf:type schema:CreativeWork
    140 https://doi.org/10.7551/mitpress/9780262033589.001.0001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1108730677
    141 rdf:type schema:CreativeWork
    142 https://www.grid.ac/institutes/grid.239552.a schema:alternateName Children's Hospital of Philadelphia
    143 schema:name Department of Radiology, Children’s Hospital of Philadelphia, Philadelphia, PA, USA
    144 rdf:type schema:Organization
    145 https://www.grid.ac/institutes/grid.240741.4 schema:alternateName Seattle Children's Hospital
    146 schema:name Department of Radiology, Seattle Children’s Hospital, Seattle, WA, USA
    147 rdf:type schema:Organization
     




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


    ...