Sparse-View CT Reconstruction Using Wasserstein GANs View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2018

AUTHORS

Franz Thaler , Kerstin Hammernik , Christian Payer , Martin Urschler , Darko Štern

ABSTRACT

We propose a 2D computed tomography (CT) slice image reconstruction method from a limited number of projection images using Wasserstein generative adversarial networks (wGAN). Our wGAN optimizes the 2D CT image reconstruction by utilizing an adversarial loss to improve the perceived image quality as well as an \(L_1\) content loss to enforce structural similarity to the target image. We evaluate our wGANs using different weight factors between the two loss functions and compare to a convolutional neural network (CNN) optimized on \(L_1\) and the Filtered Backprojection (FBP) method. The evaluation shows that the results generated by the machine learning based approaches are substantially better than those from the FBP method. In contrast to the blurrier looking images generated by the CNNs trained on \(L_1\), the wGANs results appear sharper and seem to contain more structural information. We show that a certain amount of projection data is needed to get a correct representation of the anatomical correspondences. More... »

PAGES

75-82

References to SciGraph publications

  • 2018. Adversarial and Perceptual Refinement for Compressed Sensing MRI Reconstruction in MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION – MICCAI 2018
  • 2018-12. Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction in SCIENTIFIC REPORTS
  • 2018-12. Low-dose x-ray tomography through a deep convolutional neural network in SCIENTIFIC REPORTS
  • 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation in MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION – MICCAI 2015
  • Book

    TITLE

    Machine Learning for Medical Image Reconstruction

    ISBN

    978-3-030-00128-5
    978-3-030-00129-2

    Author Affiliations

    From Grant

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-030-00129-2_9

    DOI

    http://dx.doi.org/10.1007/978-3-030-00129-2_9

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1106929170


    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": "Graz University of Technology", 
              "id": "https://www.grid.ac/institutes/grid.410413.3", 
              "name": [
                "Graz University of Technology"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Thaler", 
            "givenName": "Franz", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Graz University of Technology", 
              "id": "https://www.grid.ac/institutes/grid.410413.3", 
              "name": [
                "Graz University of Technology"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Hammernik", 
            "givenName": "Kerstin", 
            "id": "sg:person.0651127353.54", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0651127353.54"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Graz University of Technology", 
              "id": "https://www.grid.ac/institutes/grid.410413.3", 
              "name": [
                "Graz University of Technology"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Payer", 
            "givenName": "Christian", 
            "id": "sg:person.015110704055.73", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015110704055.73"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Ludwig Boltzmann Institute for Clinical Forensic Imaging"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Urschler", 
            "givenName": "Martin", 
            "id": "sg:person.01263233742.39", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01263233742.39"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Graz University of Technology", 
              "id": "https://www.grid.ac/institutes/grid.410413.3", 
              "name": [
                "Graz University of Technology", 
                "Ludwig Boltzmann Institute for Clinical Forensic Imaging"
              ], 
              "type": "Organization"
            }, 
            "familyName": "\u0160tern", 
            "givenName": "Darko", 
            "id": "sg:person.01314472152.26", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01314472152.26"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-319-24574-4_28", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017774818", 
              "https://doi.org/10.1007/978-3-319-24574-4_28"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tip.2017.2713099", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1086050371"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1002/mp.12344", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092192337"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2017.19", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095836438"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tmi.2017.2785879", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099908308"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41598-018-19426-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100780758", 
              "https://doi.org/10.1038/s41598-018-19426-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tmi.2018.2827462", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1103542566"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41598-018-25153-w", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1103687248", 
              "https://doi.org/10.1038/s41598-018-25153-w"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-00928-1_27", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107023368", 
              "https://doi.org/10.1007/978-3-030-00928-1_27"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018", 
        "datePublishedReg": "2018-01-01", 
        "description": "We propose a 2D computed tomography (CT) slice image reconstruction method from a limited number of projection images using Wasserstein generative adversarial networks (wGAN). Our wGAN optimizes the 2D CT image reconstruction by utilizing an adversarial loss to improve the perceived image quality as well as an \\(L_1\\) content loss to enforce structural similarity to the target image. We evaluate our wGANs using different weight factors between the two loss functions and compare to a convolutional neural network (CNN) optimized on \\(L_1\\) and the Filtered Backprojection (FBP) method. The evaluation shows that the results generated by the machine learning based approaches are substantially better than those from the FBP method. In contrast to the blurrier looking images generated by the CNNs trained on \\(L_1\\), the wGANs results appear sharper and seem to contain more structural information. We show that a certain amount of projection data is needed to get a correct representation of the anatomical correspondences.", 
        "editor": [
          {
            "familyName": "Knoll", 
            "givenName": "Florian", 
            "type": "Person"
          }, 
          {
            "familyName": "Maier", 
            "givenName": "Andreas", 
            "type": "Person"
          }, 
          {
            "familyName": "Rueckert", 
            "givenName": "Daniel", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-030-00129-2_9", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.6207595", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": {
          "isbn": [
            "978-3-030-00128-5", 
            "978-3-030-00129-2"
          ], 
          "name": "Machine Learning for Medical Image Reconstruction", 
          "type": "Book"
        }, 
        "name": "Sparse-View CT Reconstruction Using Wasserstein GANs", 
        "pagination": "75-82", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-030-00129-2_9"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "9fe77b9009fb6978095a50ec6349ab13132e3b878275db5c33b9a519711c039b"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1106929170"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-030-00129-2_9", 
          "https://app.dimensions.ai/details/publication/pub.1106929170"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T16:57", 
        "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/v90/0000000001_0000000264/records_8675_00000605.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-030-00129-2_9"
      }
    ]
     

    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.10.1007/978-3-030-00129-2_9'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-00129-2_9'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-00129-2_9'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-00129-2_9'


     

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

    138 TRIPLES      23 PREDICATES      36 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-030-00129-2_9 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N88a26dc70ffb4aa2a964c9eff1be0f24
    4 schema:citation sg:pub.10.1007/978-3-030-00928-1_27
    5 sg:pub.10.1007/978-3-319-24574-4_28
    6 sg:pub.10.1038/s41598-018-19426-7
    7 sg:pub.10.1038/s41598-018-25153-w
    8 https://doi.org/10.1002/mp.12344
    9 https://doi.org/10.1109/cvpr.2017.19
    10 https://doi.org/10.1109/tip.2017.2713099
    11 https://doi.org/10.1109/tmi.2017.2785879
    12 https://doi.org/10.1109/tmi.2018.2827462
    13 schema:datePublished 2018
    14 schema:datePublishedReg 2018-01-01
    15 schema:description We propose a 2D computed tomography (CT) slice image reconstruction method from a limited number of projection images using Wasserstein generative adversarial networks (wGAN). Our wGAN optimizes the 2D CT image reconstruction by utilizing an adversarial loss to improve the perceived image quality as well as an \(L_1\) content loss to enforce structural similarity to the target image. We evaluate our wGANs using different weight factors between the two loss functions and compare to a convolutional neural network (CNN) optimized on \(L_1\) and the Filtered Backprojection (FBP) method. The evaluation shows that the results generated by the machine learning based approaches are substantially better than those from the FBP method. In contrast to the blurrier looking images generated by the CNNs trained on \(L_1\), the wGANs results appear sharper and seem to contain more structural information. We show that a certain amount of projection data is needed to get a correct representation of the anatomical correspondences.
    16 schema:editor N959e70cffaa54de89fde64eb49ff8586
    17 schema:genre chapter
    18 schema:inLanguage en
    19 schema:isAccessibleForFree false
    20 schema:isPartOf Nc7b061ee06964739879d248c4f17684a
    21 schema:name Sparse-View CT Reconstruction Using Wasserstein GANs
    22 schema:pagination 75-82
    23 schema:productId N3202bac299f8484790abce621e47e157
    24 N3b13ec1ecef1473fa4f080c119019f01
    25 Ne454ab2d550c41d9a21e273877856aeb
    26 schema:publisher N77013bf1f63d46298403d5862cc25ee3
    27 schema:sameAs https://app.dimensions.ai/details/publication/pub.1106929170
    28 https://doi.org/10.1007/978-3-030-00129-2_9
    29 schema:sdDatePublished 2019-04-15T16:57
    30 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    31 schema:sdPublisher N4c527dcc42d249fda0b143ab5da12c22
    32 schema:url http://link.springer.com/10.1007/978-3-030-00129-2_9
    33 sgo:license sg:explorer/license/
    34 sgo:sdDataset chapters
    35 rdf:type schema:Chapter
    36 N2d72bfa4dd65451fbfa4f6ce7e747418 rdf:first N46600a95d2a34fd497e2688cfa2b4d00
    37 rdf:rest N617c1d458c5641ebae7517b6662ca075
    38 N3202bac299f8484790abce621e47e157 schema:name readcube_id
    39 schema:value 9fe77b9009fb6978095a50ec6349ab13132e3b878275db5c33b9a519711c039b
    40 rdf:type schema:PropertyValue
    41 N3b13ec1ecef1473fa4f080c119019f01 schema:name doi
    42 schema:value 10.1007/978-3-030-00129-2_9
    43 rdf:type schema:PropertyValue
    44 N46600a95d2a34fd497e2688cfa2b4d00 schema:familyName Maier
    45 schema:givenName Andreas
    46 rdf:type schema:Person
    47 N4c527dcc42d249fda0b143ab5da12c22 schema:name Springer Nature - SN SciGraph project
    48 rdf:type schema:Organization
    49 N54c2481a208e47a4954793c863310e84 rdf:first sg:person.01314472152.26
    50 rdf:rest rdf:nil
    51 N617c1d458c5641ebae7517b6662ca075 rdf:first Ncb2075a3f4c842e9ae12ff04e4b3d15d
    52 rdf:rest rdf:nil
    53 N6e1892a29afc44129dd22d3168d76047 rdf:first sg:person.015110704055.73
    54 rdf:rest N92518910f6a74fbfafa94e6222ff4198
    55 N77013bf1f63d46298403d5862cc25ee3 schema:location Cham
    56 schema:name Springer International Publishing
    57 rdf:type schema:Organisation
    58 N798976682d8f41f7ac835f4928e0ca3d schema:name Ludwig Boltzmann Institute for Clinical Forensic Imaging
    59 rdf:type schema:Organization
    60 N88a26dc70ffb4aa2a964c9eff1be0f24 rdf:first Nae603c9a5f5f4d61b1247323f9426569
    61 rdf:rest N8b6ffec28f754ba0be413671ed66c279
    62 N8b6ffec28f754ba0be413671ed66c279 rdf:first sg:person.0651127353.54
    63 rdf:rest N6e1892a29afc44129dd22d3168d76047
    64 N92518910f6a74fbfafa94e6222ff4198 rdf:first sg:person.01263233742.39
    65 rdf:rest N54c2481a208e47a4954793c863310e84
    66 N959e70cffaa54de89fde64eb49ff8586 rdf:first Nd0f296b447b14865872dff91e375505c
    67 rdf:rest N2d72bfa4dd65451fbfa4f6ce7e747418
    68 Nae603c9a5f5f4d61b1247323f9426569 schema:affiliation https://www.grid.ac/institutes/grid.410413.3
    69 schema:familyName Thaler
    70 schema:givenName Franz
    71 rdf:type schema:Person
    72 Nc7b061ee06964739879d248c4f17684a schema:isbn 978-3-030-00128-5
    73 978-3-030-00129-2
    74 schema:name Machine Learning for Medical Image Reconstruction
    75 rdf:type schema:Book
    76 Ncb2075a3f4c842e9ae12ff04e4b3d15d schema:familyName Rueckert
    77 schema:givenName Daniel
    78 rdf:type schema:Person
    79 Nd0f296b447b14865872dff91e375505c schema:familyName Knoll
    80 schema:givenName Florian
    81 rdf:type schema:Person
    82 Ne454ab2d550c41d9a21e273877856aeb schema:name dimensions_id
    83 schema:value pub.1106929170
    84 rdf:type schema:PropertyValue
    85 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    86 schema:name Information and Computing Sciences
    87 rdf:type schema:DefinedTerm
    88 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    89 schema:name Artificial Intelligence and Image Processing
    90 rdf:type schema:DefinedTerm
    91 sg:grant.6207595 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-030-00129-2_9
    92 rdf:type schema:MonetaryGrant
    93 sg:person.01263233742.39 schema:affiliation N798976682d8f41f7ac835f4928e0ca3d
    94 schema:familyName Urschler
    95 schema:givenName Martin
    96 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01263233742.39
    97 rdf:type schema:Person
    98 sg:person.01314472152.26 schema:affiliation https://www.grid.ac/institutes/grid.410413.3
    99 schema:familyName Štern
    100 schema:givenName Darko
    101 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01314472152.26
    102 rdf:type schema:Person
    103 sg:person.015110704055.73 schema:affiliation https://www.grid.ac/institutes/grid.410413.3
    104 schema:familyName Payer
    105 schema:givenName Christian
    106 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015110704055.73
    107 rdf:type schema:Person
    108 sg:person.0651127353.54 schema:affiliation https://www.grid.ac/institutes/grid.410413.3
    109 schema:familyName Hammernik
    110 schema:givenName Kerstin
    111 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0651127353.54
    112 rdf:type schema:Person
    113 sg:pub.10.1007/978-3-030-00928-1_27 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107023368
    114 https://doi.org/10.1007/978-3-030-00928-1_27
    115 rdf:type schema:CreativeWork
    116 sg:pub.10.1007/978-3-319-24574-4_28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017774818
    117 https://doi.org/10.1007/978-3-319-24574-4_28
    118 rdf:type schema:CreativeWork
    119 sg:pub.10.1038/s41598-018-19426-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100780758
    120 https://doi.org/10.1038/s41598-018-19426-7
    121 rdf:type schema:CreativeWork
    122 sg:pub.10.1038/s41598-018-25153-w schema:sameAs https://app.dimensions.ai/details/publication/pub.1103687248
    123 https://doi.org/10.1038/s41598-018-25153-w
    124 rdf:type schema:CreativeWork
    125 https://doi.org/10.1002/mp.12344 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092192337
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1109/cvpr.2017.19 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095836438
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1109/tip.2017.2713099 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086050371
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1109/tmi.2017.2785879 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099908308
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1109/tmi.2018.2827462 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103542566
    134 rdf:type schema:CreativeWork
    135 https://www.grid.ac/institutes/grid.410413.3 schema:alternateName Graz University of Technology
    136 schema:name Graz University of Technology
    137 Ludwig Boltzmann Institute for Clinical Forensic Imaging
    138 rdf:type schema:Organization
     




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


    ...