Study of the quantitative evaluation factors for a deep learning-based improved magnetic resonance imaging View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2021-10-25

AUTHORS

Denis Yoo, C. J. Rah, Eric Lee, J. H. Kim, Byung Jun Min, Eun Ho Kim

ABSTRACT

Our research focused on the feasibility of improving the low-field T2 magnetic resonance (MR) images in terms of using a complex and in-depth learning-related algorithm. Set of unpaired images (T2-weighted 0.06 T MR image and 1.5 T MR image for separate individuals) were utilized in two clinical trials/sequences. The trials were conducted to identify deformations in a 1.5 T MR image according to the 0.06 T MR image to fit the image and size of the unpaired set. Afterwards, the cyclic-generative adversarial network (GAN) was applied to produce an artificial MR image of the 0.06 T MR image with reference to the original or the deformed 1.5 T MR image. In the end, an improved 0.06 T MR image was produced using the traditional GAN supplemented by the artificial MR image. T2 and flair MR images were verified for matching T1 and T2 testing models in the context of the traditional GAN. The outcomes relating to the optimized trial based on the improved MR image indicated a measurable improvement of the signal with a positive relationship between the original and the improved images. Quantitative variables were applied to assess the quality of the images, along with other settings, such as the signal improvement ratio and the signal-to-noise ratio (SNR), as well as the variable between the original and the improved MR images. The combination of assessment variables demonstrated that T2 photographs were better in terms of the T1 testing model compared to the T2 testing model. More... »

PAGES

885-893

References to SciGraph publications

  • 2007. Contrast Enhancement of MRI Images in 3RD KUALA LUMPUR INTERNATIONAL CONFERENCE ON BIOMEDICAL ENGINEERING 2006
  • 2015-10-15. Low-Cost High-Performance MRI in SCIENTIFIC REPORTS
  • 2015-07-14. Converting from CT- to MRI-only-based target definition in radiotherapy of localized prostate cancer in STRAHLENTHERAPIE UND ONKOLOGIE
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s40042-021-00291-z

    DOI

    http://dx.doi.org/10.1007/s40042-021-00291-z

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1142154955


    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/2008/01", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Mathematical Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/02", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Physical Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Artificial Intelligent Research Lab, Talos, 999077, Sheung Wan, Hong Kong", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Artificial Intelligent Research Lab, Talos, 999077, Sheung Wan, Hong Kong"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Yoo", 
            "givenName": "Denis", 
            "id": "sg:person.07645223465.46", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07645223465.46"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Artificial Intelligent Research Lab, Talos, 999077, Sheung Wan, Hong Kong", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Artificial Intelligent Research Lab, Talos, 999077, Sheung Wan, Hong Kong"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Rah", 
            "givenName": "C. J.", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Artificial Intelligent Research Lab, Talos, 999077, Sheung Wan, Hong Kong", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Artificial Intelligent Research Lab, Talos, 999077, Sheung Wan, Hong Kong"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Lee", 
            "givenName": "Eric", 
            "id": "sg:person.07761452065.12", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07761452065.12"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Artificial Intelligent Research Lab, Talos, 999077, Sheung Wan, Hong Kong", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Artificial Intelligent Research Lab, Talos, 999077, Sheung Wan, Hong Kong"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kim", 
            "givenName": "J. H.", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Radiation Oncology, Chungbuk National University Hospital, 28644, Cheongju, South Korea", 
              "id": "http://www.grid.ac/institutes/grid.411725.4", 
              "name": [
                "Department of Radiation Oncology, Chungbuk National University Hospital, 28644, Cheongju, South Korea"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Min", 
            "givenName": "Byung Jun", 
            "id": "sg:person.016623006567.07", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016623006567.07"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Biochemistry, School of Medicine, Daegu Catholic University, 38430, Daegu, South Korea", 
              "id": "http://www.grid.ac/institutes/grid.411947.e", 
              "name": [
                "Department of Biochemistry, School of Medicine, Daegu Catholic University, 38430, Daegu, South Korea"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kim", 
            "givenName": "Eun Ho", 
            "id": "sg:person.01066653102.20", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066653102.20"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-540-68017-8_66", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1049174226", 
              "https://doi.org/10.1007/978-3-540-68017-8_66"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/srep15177", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037945730", 
              "https://doi.org/10.1038/srep15177"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00066-015-0868-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017778510", 
              "https://doi.org/10.1007/s00066-015-0868-5"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2021-10-25", 
        "datePublishedReg": "2021-10-25", 
        "description": "Our research focused on the feasibility of improving the low-field T2 magnetic resonance (MR) images in terms of using a complex and in-depth learning-related algorithm. Set of unpaired images (T2-weighted 0.06\u00a0T MR image and 1.5\u00a0T MR image for separate individuals) were utilized in two clinical trials/sequences. The trials were conducted to identify deformations in a 1.5\u00a0T MR image according to the 0.06\u00a0T MR image to fit the image and size of the unpaired set. Afterwards, the cyclic-generative adversarial network (GAN) was applied to produce an artificial MR image of the 0.06\u00a0T MR image with reference to the original or the deformed 1.5\u00a0T MR image. In the end, an improved 0.06\u00a0T MR image was produced using the traditional GAN supplemented by the artificial MR image. T2 and flair MR images were verified for matching T1 and T2 testing models in the context of the traditional GAN. The outcomes relating to the optimized trial based on the improved MR image indicated a measurable improvement of the signal with a positive relationship between the original and the improved images. Quantitative variables were applied to assess the quality of the images, along with other settings, such as the signal improvement ratio and the signal-to-noise ratio (SNR), as well as the variable between the original and the improved MR images. The combination of assessment variables demonstrated that T2 photographs were better in terms of the T1 testing model compared to the T2 testing model.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s40042-021-00291-z", 
        "inLanguage": "en", 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1042000", 
            "issn": [
              "0374-4884", 
              "1976-8524"
            ], 
            "name": "Journal of the Korean Physical Society", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "10", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "79"
          }
        ], 
        "keywords": [
          "unpaired image", 
          "adversarial network", 
          "MR images", 
          "traditional GAN", 
          "testing models", 
          "Improved Magnetic Resonance Imaging", 
          "images", 
          "unpaired sets", 
          "FLAIR MR images", 
          "magnetic resonance images", 
          "improvement ratio", 
          "resonance images", 
          "evaluation factors", 
          "T2 magnetic resonance images", 
          "algorithm", 
          "network", 
          "noise ratio", 
          "model", 
          "set", 
          "measurable improvement", 
          "feasibility", 
          "terms", 
          "signals", 
          "quality", 
          "context", 
          "research", 
          "improvement", 
          "end", 
          "sequence", 
          "quantitative variables", 
          "photographs", 
          "variables", 
          "setting", 
          "reference", 
          "GaN", 
          "combination", 
          "assessment variables", 
          "size", 
          "magnetic resonance imaging", 
          "imaging", 
          "resonance imaging", 
          "relationship", 
          "ratio", 
          "study", 
          "factors", 
          "deformation", 
          "outcomes", 
          "trials", 
          "T2", 
          "T1", 
          "positive relationship", 
          "quantitative evaluation factors", 
          "low-field T2 magnetic resonance (MR) images", 
          "depth learning-related algorithm", 
          "learning-related algorithm", 
          "clinical trials/sequences", 
          "trials/sequences", 
          "cyclic-generative adversarial network", 
          "artificial MR image", 
          "T2 testing models", 
          "signal improvement ratio", 
          "T2 photographs", 
          "T1 testing model", 
          "deep learning-based improved magnetic resonance imaging", 
          "learning-based improved magnetic resonance imaging"
        ], 
        "name": "Study of the quantitative evaluation factors for a deep learning-based improved magnetic resonance imaging", 
        "pagination": "885-893", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1142154955"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s40042-021-00291-z"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s40042-021-00291-z", 
          "https://app.dimensions.ai/details/publication/pub.1142154955"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-01-01T19:01", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/article/article_903.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s40042-021-00291-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/s40042-021-00291-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/s40042-021-00291-z'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s40042-021-00291-z'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s40042-021-00291-z'


     

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

    174 TRIPLES      22 PREDICATES      93 URIs      82 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s40042-021-00291-z schema:about anzsrc-for:01
    2 anzsrc-for:02
    3 schema:author N05f28e1250cb4e90921a7a492b9d2652
    4 schema:citation sg:pub.10.1007/978-3-540-68017-8_66
    5 sg:pub.10.1007/s00066-015-0868-5
    6 sg:pub.10.1038/srep15177
    7 schema:datePublished 2021-10-25
    8 schema:datePublishedReg 2021-10-25
    9 schema:description Our research focused on the feasibility of improving the low-field T2 magnetic resonance (MR) images in terms of using a complex and in-depth learning-related algorithm. Set of unpaired images (T2-weighted 0.06 T MR image and 1.5 T MR image for separate individuals) were utilized in two clinical trials/sequences. The trials were conducted to identify deformations in a 1.5 T MR image according to the 0.06 T MR image to fit the image and size of the unpaired set. Afterwards, the cyclic-generative adversarial network (GAN) was applied to produce an artificial MR image of the 0.06 T MR image with reference to the original or the deformed 1.5 T MR image. In the end, an improved 0.06 T MR image was produced using the traditional GAN supplemented by the artificial MR image. T2 and flair MR images were verified for matching T1 and T2 testing models in the context of the traditional GAN. The outcomes relating to the optimized trial based on the improved MR image indicated a measurable improvement of the signal with a positive relationship between the original and the improved images. Quantitative variables were applied to assess the quality of the images, along with other settings, such as the signal improvement ratio and the signal-to-noise ratio (SNR), as well as the variable between the original and the improved MR images. The combination of assessment variables demonstrated that T2 photographs were better in terms of the T1 testing model compared to the T2 testing model.
    10 schema:genre article
    11 schema:inLanguage en
    12 schema:isAccessibleForFree false
    13 schema:isPartOf N98d13c72032347f280477b4647e7ca02
    14 Naa15df2f9b2e4d35ac4ec6e7bc5591d2
    15 sg:journal.1042000
    16 schema:keywords FLAIR MR images
    17 GaN
    18 Improved Magnetic Resonance Imaging
    19 MR images
    20 T1
    21 T1 testing model
    22 T2
    23 T2 magnetic resonance images
    24 T2 photographs
    25 T2 testing models
    26 adversarial network
    27 algorithm
    28 artificial MR image
    29 assessment variables
    30 clinical trials/sequences
    31 combination
    32 context
    33 cyclic-generative adversarial network
    34 deep learning-based improved magnetic resonance imaging
    35 deformation
    36 depth learning-related algorithm
    37 end
    38 evaluation factors
    39 factors
    40 feasibility
    41 images
    42 imaging
    43 improvement
    44 improvement ratio
    45 learning-based improved magnetic resonance imaging
    46 learning-related algorithm
    47 low-field T2 magnetic resonance (MR) images
    48 magnetic resonance images
    49 magnetic resonance imaging
    50 measurable improvement
    51 model
    52 network
    53 noise ratio
    54 outcomes
    55 photographs
    56 positive relationship
    57 quality
    58 quantitative evaluation factors
    59 quantitative variables
    60 ratio
    61 reference
    62 relationship
    63 research
    64 resonance images
    65 resonance imaging
    66 sequence
    67 set
    68 setting
    69 signal improvement ratio
    70 signals
    71 size
    72 study
    73 terms
    74 testing models
    75 traditional GAN
    76 trials
    77 trials/sequences
    78 unpaired image
    79 unpaired sets
    80 variables
    81 schema:name Study of the quantitative evaluation factors for a deep learning-based improved magnetic resonance imaging
    82 schema:pagination 885-893
    83 schema:productId N8f70cc33b4f1426bbb99a305bafbfaff
    84 N9e9e7c774ce04ef899a1b302422a7905
    85 schema:sameAs https://app.dimensions.ai/details/publication/pub.1142154955
    86 https://doi.org/10.1007/s40042-021-00291-z
    87 schema:sdDatePublished 2022-01-01T19:01
    88 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    89 schema:sdPublisher N9624e68b35e94efeb3f2905d736d7a91
    90 schema:url https://doi.org/10.1007/s40042-021-00291-z
    91 sgo:license sg:explorer/license/
    92 sgo:sdDataset articles
    93 rdf:type schema:ScholarlyArticle
    94 N05f28e1250cb4e90921a7a492b9d2652 rdf:first sg:person.07645223465.46
    95 rdf:rest N8221d9b74b684d4493bdb7b4322de7c5
    96 N23c6a786151546658bf6c0288c60fb41 rdf:first N4720ad9f77db4c9bb50ca51b1acd783a
    97 rdf:rest Na76b9eb6f5ac4e399140c97882a7d78f
    98 N4720ad9f77db4c9bb50ca51b1acd783a schema:affiliation grid-institutes:None
    99 schema:familyName Kim
    100 schema:givenName J. H.
    101 rdf:type schema:Person
    102 N8221d9b74b684d4493bdb7b4322de7c5 rdf:first N83f6f31e7e484829a53c034461f16718
    103 rdf:rest Nd2b70433f3a94884b9d73b74f64993f9
    104 N83f6f31e7e484829a53c034461f16718 schema:affiliation grid-institutes:None
    105 schema:familyName Rah
    106 schema:givenName C. J.
    107 rdf:type schema:Person
    108 N8f70cc33b4f1426bbb99a305bafbfaff schema:name doi
    109 schema:value 10.1007/s40042-021-00291-z
    110 rdf:type schema:PropertyValue
    111 N9624e68b35e94efeb3f2905d736d7a91 schema:name Springer Nature - SN SciGraph project
    112 rdf:type schema:Organization
    113 N98d13c72032347f280477b4647e7ca02 schema:volumeNumber 79
    114 rdf:type schema:PublicationVolume
    115 N9e9e7c774ce04ef899a1b302422a7905 schema:name dimensions_id
    116 schema:value pub.1142154955
    117 rdf:type schema:PropertyValue
    118 Na76b9eb6f5ac4e399140c97882a7d78f rdf:first sg:person.016623006567.07
    119 rdf:rest Nf8c13fe8c3444eab8689b7d351d9928b
    120 Naa15df2f9b2e4d35ac4ec6e7bc5591d2 schema:issueNumber 10
    121 rdf:type schema:PublicationIssue
    122 Nd2b70433f3a94884b9d73b74f64993f9 rdf:first sg:person.07761452065.12
    123 rdf:rest N23c6a786151546658bf6c0288c60fb41
    124 Nf8c13fe8c3444eab8689b7d351d9928b rdf:first sg:person.01066653102.20
    125 rdf:rest rdf:nil
    126 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
    127 schema:name Mathematical Sciences
    128 rdf:type schema:DefinedTerm
    129 anzsrc-for:02 schema:inDefinedTermSet anzsrc-for:
    130 schema:name Physical Sciences
    131 rdf:type schema:DefinedTerm
    132 sg:journal.1042000 schema:issn 0374-4884
    133 1976-8524
    134 schema:name Journal of the Korean Physical Society
    135 schema:publisher Springer Nature
    136 rdf:type schema:Periodical
    137 sg:person.01066653102.20 schema:affiliation grid-institutes:grid.411947.e
    138 schema:familyName Kim
    139 schema:givenName Eun Ho
    140 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01066653102.20
    141 rdf:type schema:Person
    142 sg:person.016623006567.07 schema:affiliation grid-institutes:grid.411725.4
    143 schema:familyName Min
    144 schema:givenName Byung Jun
    145 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016623006567.07
    146 rdf:type schema:Person
    147 sg:person.07645223465.46 schema:affiliation grid-institutes:None
    148 schema:familyName Yoo
    149 schema:givenName Denis
    150 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07645223465.46
    151 rdf:type schema:Person
    152 sg:person.07761452065.12 schema:affiliation grid-institutes:None
    153 schema:familyName Lee
    154 schema:givenName Eric
    155 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07761452065.12
    156 rdf:type schema:Person
    157 sg:pub.10.1007/978-3-540-68017-8_66 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049174226
    158 https://doi.org/10.1007/978-3-540-68017-8_66
    159 rdf:type schema:CreativeWork
    160 sg:pub.10.1007/s00066-015-0868-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017778510
    161 https://doi.org/10.1007/s00066-015-0868-5
    162 rdf:type schema:CreativeWork
    163 sg:pub.10.1038/srep15177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037945730
    164 https://doi.org/10.1038/srep15177
    165 rdf:type schema:CreativeWork
    166 grid-institutes:None schema:alternateName Artificial Intelligent Research Lab, Talos, 999077, Sheung Wan, Hong Kong
    167 schema:name Artificial Intelligent Research Lab, Talos, 999077, Sheung Wan, Hong Kong
    168 rdf:type schema:Organization
    169 grid-institutes:grid.411725.4 schema:alternateName Department of Radiation Oncology, Chungbuk National University Hospital, 28644, Cheongju, South Korea
    170 schema:name Department of Radiation Oncology, Chungbuk National University Hospital, 28644, Cheongju, South Korea
    171 rdf:type schema:Organization
    172 grid-institutes:grid.411947.e schema:alternateName Department of Biochemistry, School of Medicine, Daegu Catholic University, 38430, Daegu, South Korea
    173 schema:name Department of Biochemistry, School of Medicine, Daegu Catholic University, 38430, Daegu, South Korea
    174 rdf:type schema:Organization
     




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


    ...