Development of a fully automatic deep learning system for L3 selection and body composition assessment on computed tomography View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2021-11-04

AUTHORS

Jiyeon Ha, Taeyong Park, Hong-Kyu Kim, Youngbin Shin, Yousun Ko, Dong Wook Kim, Yu Sub Sung, Jiwoo Lee, Su Jung Ham, Seungwoo Khang, Heeryeol Jeong, Kyoyeong Koo, Jeongjin Lee, Kyung Won Kim

ABSTRACT

As sarcopenia research has been gaining emphasis, the need for quantification of abdominal muscle on computed tomography (CT) is increasing. Thus, a fully automated system to select L3 slice and segment muscle in an end-to-end manner is demanded. We aimed to develop a deep learning model (DLM) to select the L3 slice with consideration of anatomic variations and to segment cross-sectional areas (CSAs) of abdominal muscle and fat. Our DLM, named L3SEG-net, was composed of a YOLOv3-based algorithm for selecting the L3 slice and a fully convolutional network (FCN)-based algorithm for segmentation. The YOLOv3-based algorithm was developed via supervised learning using a training dataset (n = 922), and the FCN-based algorithm was transferred from prior work. Our L3SEG-net was validated with internal (n = 496) and external validation (n = 586) datasets. Ground truth L3 level CT slice and anatomic variation were identified by a board-certified radiologist. L3 slice selection accuracy was evaluated by the distance difference between ground truths and DLM-derived results. Technical success for L3 slice selection was defined when the distance difference was < 10 mm. Overall segmentation accuracy was evaluated by CSA error and DSC value. The influence of anatomic variations on DLM performance was evaluated. In the internal and external validation datasets, the accuracy of automatic L3 slice selection was high, with mean distance differences of 3.7 ± 8.4 mm and 4.1 ± 8.3 mm, respectively, and with technical success rates of 93.1% and 92.3%, respectively. However, in the subgroup analysis of anatomic variations, the L3 slice selection accuracy decreased, with distance differences of 12.4 ± 15.4 mm and 12.1 ± 14.6 mm, respectively, and with technical success rates of 67.2% and 67.9%, respectively. The overall segmentation accuracy of abdominal muscle areas was excellent regardless of anatomic variation, with CSA errors of 1.38–3.10 cm2. A fully automatic system was developed for the selection of an exact axial CT slice at the L3 vertebral level and the segmentation of abdominal muscle areas. More... »

PAGES

21656

Identifiers

URI

http://scigraph.springernature.com/pub.10.1038/s41598-021-00161-5

DOI

http://dx.doi.org/10.1038/s41598-021-00161-5

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1142372124

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/34737340


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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Abdominal Muscles", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Algorithms", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Body Composition", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Computational Biology", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Databases, Factual", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Deep Learning", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Humans", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Image Processing, Computer-Assisted", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Lumbar Vertebrae", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Machine Learning", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Multidetector Computed Tomography", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Neural Networks, Computer", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Sarcopenia", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Tomography, X-Ray Computed", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro, 43-gil, Songpa-gu, 05505, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.413967.e", 
          "name": [
            "Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro, 43-gil, Songpa-gu, 05505, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ha", 
        "givenName": "Jiyeon", 
        "id": "sg:person.010625374353.81", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010625374353.81"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.267370.7", 
          "name": [
            "Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Park", 
        "givenName": "Taeyong", 
        "id": "sg:person.016160635401.76", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016160635401.76"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Health Screening and Promotion Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.413967.e", 
          "name": [
            "Health Screening and Promotion Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kim", 
        "givenName": "Hong-Kyu", 
        "id": "sg:person.0651135776.93", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0651135776.93"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.413967.e", 
          "name": [
            "Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shin", 
        "givenName": "Youngbin", 
        "id": "sg:person.010222413237.11", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010222413237.11"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.413967.e", 
          "name": [
            "Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ko", 
        "givenName": "Yousun", 
        "id": "sg:person.01137623345.18", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01137623345.18"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro, 43-gil, Songpa-gu, 05505, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.413967.e", 
          "name": [
            "Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro, 43-gil, Songpa-gu, 05505, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kim", 
        "givenName": "Dong Wook", 
        "id": "sg:person.012477731120.69", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012477731120.69"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Convergence Medicine, University of Ulsan College of Medicine, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.267370.7", 
          "name": [
            "Clinical Research Center, Asan Medical Center, Seoul, Korea", 
            "Department of Convergence Medicine, University of Ulsan College of Medicine, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sung", 
        "givenName": "Yu Sub", 
        "id": "sg:person.0671111600.05", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0671111600.05"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.413967.e", 
          "name": [
            "Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lee", 
        "givenName": "Jiwoo", 
        "id": "sg:person.015361710053.92", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015361710053.92"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro, 43-gil, Songpa-gu, 05505, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.413967.e", 
          "name": [
            "Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro, 43-gil, Songpa-gu, 05505, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ham", 
        "givenName": "Su Jung", 
        "id": "sg:person.0576122127.23", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0576122127.23"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Computer Science and Engineering, Soongsil University, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.263765.3", 
          "name": [
            "School of Computer Science and Engineering, Soongsil University, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Khang", 
        "givenName": "Seungwoo", 
        "id": "sg:person.016655052074.44", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016655052074.44"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Computer Science and Engineering, Soongsil University, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.263765.3", 
          "name": [
            "School of Computer Science and Engineering, Soongsil University, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jeong", 
        "givenName": "Heeryeol", 
        "id": "sg:person.014001312403.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014001312403.46"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Computer Science and Engineering, Soongsil University, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.263765.3", 
          "name": [
            "School of Computer Science and Engineering, Soongsil University, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Koo", 
        "givenName": "Kyoyeong", 
        "id": "sg:person.07455564201.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07455564201.65"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Computer Science and Engineering, Soongsil University, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.263765.3", 
          "name": [
            "School of Computer Science and Engineering, Soongsil University, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lee", 
        "givenName": "Jeongjin", 
        "id": "sg:person.01011505663.09", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01011505663.09"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro, 43-gil, Songpa-gu, 05505, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.413967.e", 
          "name": [
            "Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro, 43-gil, Songpa-gu, 05505, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kim", 
        "givenName": "Kyung Won", 
        "id": "sg:person.010061104677.90", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010061104677.90"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1245/s10434-014-4040-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053187502", 
          "https://doi.org/10.1245/s10434-014-4040-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-01201-4_22", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1107352150", 
          "https://doi.org/10.1007/978-3-030-01201-4_22"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/ejcn.2014.169", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042737966", 
          "https://doi.org/10.1038/ejcn.2014.169"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10120-015-0546-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003903397", 
          "https://doi.org/10.1007/s10120-015-0546-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s13244-013-0286-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050737797", 
          "https://doi.org/10.1007/s13244-013-0286-0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s12194-011-0127-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025763617", 
          "https://doi.org/10.1007/s12194-011-0127-0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10278-017-9988-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086357467", 
          "https://doi.org/10.1007/s10278-017-9988-z"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2021-11-04", 
    "datePublishedReg": "2021-11-04", 
    "description": "As sarcopenia research has been gaining emphasis, the need for quantification of abdominal muscle on computed tomography (CT) is increasing. Thus, a fully automated system to select L3 slice and segment muscle in an end-to-end manner is demanded. We aimed to develop a deep learning model (DLM) to select the L3 slice with consideration of anatomic variations and to segment cross-sectional areas (CSAs) of abdominal muscle and fat. Our DLM, named L3SEG-net, was composed of a YOLOv3-based algorithm for selecting the L3 slice and a fully convolutional network (FCN)-based algorithm for segmentation. The YOLOv3-based algorithm was developed via supervised learning using a training dataset (n\u2009=\u2009922), and the FCN-based algorithm was transferred from prior work. Our L3SEG-net was validated with internal (n\u2009=\u2009496) and external validation (n\u2009=\u2009586) datasets. Ground truth L3 level CT slice and anatomic variation were identified by a board-certified radiologist. L3 slice selection accuracy was evaluated by the distance difference between ground truths and DLM-derived results. Technical success for L3 slice selection was defined when the distance difference was\u2009<\u200910\u00a0mm. Overall segmentation accuracy was evaluated by CSA error and DSC value. The influence of anatomic variations on DLM performance was evaluated. In the internal and external validation datasets, the accuracy of automatic L3 slice selection was high, with mean distance differences of\u00a03.7\u2009\u00b1\u20098.4\u00a0mm and 4.1\u2009\u00b1\u20098.3\u00a0mm, respectively, and with technical success rates of 93.1% and 92.3%, respectively. However, in the subgroup analysis of anatomic variations, the L3 slice selection accuracy decreased, with distance differences of 12.4\u2009\u00b1\u200915.4\u00a0mm and 12.1\u2009\u00b1\u200914.6\u00a0mm, respectively, and with technical success rates of 67.2% and 67.9%, respectively. The overall segmentation accuracy of abdominal muscle areas was excellent regardless of anatomic variation, with CSA errors of 1.38\u20133.10 cm2. A fully automatic system was developed for the selection of an exact axial CT slice at the L3 vertebral level and the segmentation of abdominal muscle areas.", 
    "genre": "article", 
    "id": "sg:pub.10.1038/s41598-021-00161-5", 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1045337", 
        "issn": [
          "2045-2322"
        ], 
        "name": "Scientific Reports", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "11"
      }
    ], 
    "keywords": [
      "deep learning models", 
      "overall segmentation accuracy", 
      "L3 slice", 
      "segmentation accuracy", 
      "automatic deep learning system", 
      "deep learning system", 
      "selection accuracy", 
      "convolutional network", 
      "end manner", 
      "CT slices", 
      "supervised learning", 
      "DLM performance", 
      "learning model", 
      "training dataset", 
      "learning system", 
      "automatic system", 
      "validation dataset", 
      "distance difference", 
      "ground truth", 
      "slice selection", 
      "external validation dataset", 
      "algorithm", 
      "dataset", 
      "prior work", 
      "segmentation", 
      "mean distance difference", 
      "DSC values", 
      "accuracy", 
      "FCN", 
      "success rate", 
      "axial CT slices", 
      "system", 
      "network", 
      "board-certified radiologists", 
      "learning", 
      "selection", 
      "error", 
      "abdominal muscle area", 
      "segment muscles", 
      "slices", 
      "performance", 
      "truth", 
      "work", 
      "need", 
      "model", 
      "area", 
      "radiologists", 
      "research", 
      "manner", 
      "success", 
      "end", 
      "development", 
      "results", 
      "consideration", 
      "computed tomography", 
      "emphasis", 
      "analysis", 
      "L3 vertebral level", 
      "rate", 
      "assessment", 
      "variation", 
      "values", 
      "tomography", 
      "sarcopenia research", 
      "levels", 
      "quantification", 
      "composition assessment", 
      "differences", 
      "influence", 
      "anatomic variations", 
      "technical success rate", 
      "muscle area", 
      "body composition assessment", 
      "abdominal muscles", 
      "cross-sectional area", 
      "vertebral level", 
      "technical success", 
      "subgroup analysis", 
      "muscle", 
      "fat", 
      "cm2"
    ], 
    "name": "Development of a fully automatic deep learning system for L3 selection and body composition assessment on computed tomography", 
    "pagination": "21656", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1142372124"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1038/s41598-021-00161-5"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "34737340"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1038/s41598-021-00161-5", 
      "https://app.dimensions.ai/details/publication/pub.1142372124"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-10-01T06:49", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221001/entities/gbq_results/article/article_921.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1038/s41598-021-00161-5"
  }
]
 

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.10.1038/s41598-021-00161-5'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1038/s41598-021-00161-5'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1038/s41598-021-00161-5'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1038/s41598-021-00161-5'


 

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

329 TRIPLES      21 PREDICATES      127 URIs      112 LITERALS      21 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1038/s41598-021-00161-5 schema:about N04c4c8111bae4207a080ddd8124c254c
2 N1d1c23bcbd3540079902b846d6fa1bca
3 N2a7a08de358b40a38b02735d66f074d7
4 N3ea0847c06f94349b4d4a8a5883cfa96
5 N567aded7c9354d29b8dc266a9d824457
6 N59460195c0464228b610bf4e4d585d20
7 N652d0a9f98d84e9f9c1ee98a0c9f86c8
8 N7918b78c9a674aa684bd8d2274835bb6
9 N9d1e50f841df432c836ec220029bf06a
10 Nc2185217d26a4079b29d77cafdc12b6c
11 Ndbab78360a134f23873dbdc95c40af76
12 Ndbb2627eaefd4d56a55fe70c8e73f9ed
13 Ndc9a5ce233d14ade85388492b6c37ca7
14 Nf4925e4b7c034392b36e610457ca8f41
15 anzsrc-for:08
16 anzsrc-for:0801
17 schema:author N7d695fd11c474bc7b1e24a81c1753aea
18 schema:citation sg:pub.10.1007/978-3-030-01201-4_22
19 sg:pub.10.1007/s10120-015-0546-4
20 sg:pub.10.1007/s10278-017-9988-z
21 sg:pub.10.1007/s12194-011-0127-0
22 sg:pub.10.1007/s13244-013-0286-0
23 sg:pub.10.1038/ejcn.2014.169
24 sg:pub.10.1245/s10434-014-4040-8
25 schema:datePublished 2021-11-04
26 schema:datePublishedReg 2021-11-04
27 schema:description As sarcopenia research has been gaining emphasis, the need for quantification of abdominal muscle on computed tomography (CT) is increasing. Thus, a fully automated system to select L3 slice and segment muscle in an end-to-end manner is demanded. We aimed to develop a deep learning model (DLM) to select the L3 slice with consideration of anatomic variations and to segment cross-sectional areas (CSAs) of abdominal muscle and fat. Our DLM, named L3SEG-net, was composed of a YOLOv3-based algorithm for selecting the L3 slice and a fully convolutional network (FCN)-based algorithm for segmentation. The YOLOv3-based algorithm was developed via supervised learning using a training dataset (n = 922), and the FCN-based algorithm was transferred from prior work. Our L3SEG-net was validated with internal (n = 496) and external validation (n = 586) datasets. Ground truth L3 level CT slice and anatomic variation were identified by a board-certified radiologist. L3 slice selection accuracy was evaluated by the distance difference between ground truths and DLM-derived results. Technical success for L3 slice selection was defined when the distance difference was < 10 mm. Overall segmentation accuracy was evaluated by CSA error and DSC value. The influence of anatomic variations on DLM performance was evaluated. In the internal and external validation datasets, the accuracy of automatic L3 slice selection was high, with mean distance differences of 3.7 ± 8.4 mm and 4.1 ± 8.3 mm, respectively, and with technical success rates of 93.1% and 92.3%, respectively. However, in the subgroup analysis of anatomic variations, the L3 slice selection accuracy decreased, with distance differences of 12.4 ± 15.4 mm and 12.1 ± 14.6 mm, respectively, and with technical success rates of 67.2% and 67.9%, respectively. The overall segmentation accuracy of abdominal muscle areas was excellent regardless of anatomic variation, with CSA errors of 1.38–3.10 cm2. A fully automatic system was developed for the selection of an exact axial CT slice at the L3 vertebral level and the segmentation of abdominal muscle areas.
28 schema:genre article
29 schema:isAccessibleForFree true
30 schema:isPartOf N0ea8f77075eb4f638999ddf2f652f198
31 N483abcbb27dd4d5484a9a75cf5a22b21
32 sg:journal.1045337
33 schema:keywords CT slices
34 DLM performance
35 DSC values
36 FCN
37 L3 slice
38 L3 vertebral level
39 abdominal muscle area
40 abdominal muscles
41 accuracy
42 algorithm
43 analysis
44 anatomic variations
45 area
46 assessment
47 automatic deep learning system
48 automatic system
49 axial CT slices
50 board-certified radiologists
51 body composition assessment
52 cm2
53 composition assessment
54 computed tomography
55 consideration
56 convolutional network
57 cross-sectional area
58 dataset
59 deep learning models
60 deep learning system
61 development
62 differences
63 distance difference
64 emphasis
65 end
66 end manner
67 error
68 external validation dataset
69 fat
70 ground truth
71 influence
72 learning
73 learning model
74 learning system
75 levels
76 manner
77 mean distance difference
78 model
79 muscle
80 muscle area
81 need
82 network
83 overall segmentation accuracy
84 performance
85 prior work
86 quantification
87 radiologists
88 rate
89 research
90 results
91 sarcopenia research
92 segment muscles
93 segmentation
94 segmentation accuracy
95 selection
96 selection accuracy
97 slice selection
98 slices
99 subgroup analysis
100 success
101 success rate
102 supervised learning
103 system
104 technical success
105 technical success rate
106 tomography
107 training dataset
108 truth
109 validation dataset
110 values
111 variation
112 vertebral level
113 work
114 schema:name Development of a fully automatic deep learning system for L3 selection and body composition assessment on computed tomography
115 schema:pagination 21656
116 schema:productId Nd855dd2aa2584978ba8add633de6350f
117 Ne7f87c60fa57406aa2d9ec668949b98e
118 Ne88a3786542541f78b991be276951ddd
119 schema:sameAs https://app.dimensions.ai/details/publication/pub.1142372124
120 https://doi.org/10.1038/s41598-021-00161-5
121 schema:sdDatePublished 2022-10-01T06:49
122 schema:sdLicense https://scigraph.springernature.com/explorer/license/
123 schema:sdPublisher N9e733c03317349d3895a02d38809968d
124 schema:url https://doi.org/10.1038/s41598-021-00161-5
125 sgo:license sg:explorer/license/
126 sgo:sdDataset articles
127 rdf:type schema:ScholarlyArticle
128 N04c4c8111bae4207a080ddd8124c254c schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
129 schema:name Multidetector Computed Tomography
130 rdf:type schema:DefinedTerm
131 N0dc0c01ebd9447f0bdd1dab3484f7767 rdf:first sg:person.010222413237.11
132 rdf:rest N41f013b148d34b97937c827dc01fe54d
133 N0ea8f77075eb4f638999ddf2f652f198 schema:volumeNumber 11
134 rdf:type schema:PublicationVolume
135 N1d1c23bcbd3540079902b846d6fa1bca schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
136 schema:name Deep Learning
137 rdf:type schema:DefinedTerm
138 N1d552bc2e7754ea3aca2e665da7b6198 rdf:first sg:person.07455564201.65
139 rdf:rest Nfd4d750c99d84c6eb3b736af38916b37
140 N2a7a08de358b40a38b02735d66f074d7 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
141 schema:name Abdominal Muscles
142 rdf:type schema:DefinedTerm
143 N2e18c42a362749ce89059cfdace567b4 rdf:first sg:person.0576122127.23
144 rdf:rest Ne05c1f85932649de92423909a5130ec2
145 N39800c1742834a4d9d49bdd385c706ff rdf:first sg:person.012477731120.69
146 rdf:rest Ndcd529a5a2b74fe388aa7b9751715a8c
147 N3ea0847c06f94349b4d4a8a5883cfa96 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
148 schema:name Neural Networks, Computer
149 rdf:type schema:DefinedTerm
150 N41f013b148d34b97937c827dc01fe54d rdf:first sg:person.01137623345.18
151 rdf:rest N39800c1742834a4d9d49bdd385c706ff
152 N483abcbb27dd4d5484a9a75cf5a22b21 schema:issueNumber 1
153 rdf:type schema:PublicationIssue
154 N4ac5aecab032431f8652da3ff60c621e rdf:first sg:person.014001312403.46
155 rdf:rest N1d552bc2e7754ea3aca2e665da7b6198
156 N567aded7c9354d29b8dc266a9d824457 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
157 schema:name Humans
158 rdf:type schema:DefinedTerm
159 N59460195c0464228b610bf4e4d585d20 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
160 schema:name Computational Biology
161 rdf:type schema:DefinedTerm
162 N5e7f6e1fa51647e5b9a267d6e8af275f rdf:first sg:person.010061104677.90
163 rdf:rest rdf:nil
164 N652d0a9f98d84e9f9c1ee98a0c9f86c8 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
165 schema:name Algorithms
166 rdf:type schema:DefinedTerm
167 N7918b78c9a674aa684bd8d2274835bb6 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
168 schema:name Machine Learning
169 rdf:type schema:DefinedTerm
170 N7d695fd11c474bc7b1e24a81c1753aea rdf:first sg:person.010625374353.81
171 rdf:rest Na020d993d01b4f2393306811422955f9
172 N9d1e50f841df432c836ec220029bf06a schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
173 schema:name Sarcopenia
174 rdf:type schema:DefinedTerm
175 N9e733c03317349d3895a02d38809968d schema:name Springer Nature - SN SciGraph project
176 rdf:type schema:Organization
177 Na020d993d01b4f2393306811422955f9 rdf:first sg:person.016160635401.76
178 rdf:rest Ned367d7df9f8483ca4e38cb1f1e364c2
179 Nb283d375a0c44c93a653d20bdab619eb rdf:first sg:person.015361710053.92
180 rdf:rest N2e18c42a362749ce89059cfdace567b4
181 Nc2185217d26a4079b29d77cafdc12b6c schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
182 schema:name Body Composition
183 rdf:type schema:DefinedTerm
184 Nd855dd2aa2584978ba8add633de6350f schema:name doi
185 schema:value 10.1038/s41598-021-00161-5
186 rdf:type schema:PropertyValue
187 Ndbab78360a134f23873dbdc95c40af76 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
188 schema:name Lumbar Vertebrae
189 rdf:type schema:DefinedTerm
190 Ndbb2627eaefd4d56a55fe70c8e73f9ed schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
191 schema:name Tomography, X-Ray Computed
192 rdf:type schema:DefinedTerm
193 Ndc9a5ce233d14ade85388492b6c37ca7 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
194 schema:name Databases, Factual
195 rdf:type schema:DefinedTerm
196 Ndcd529a5a2b74fe388aa7b9751715a8c rdf:first sg:person.0671111600.05
197 rdf:rest Nb283d375a0c44c93a653d20bdab619eb
198 Ne05c1f85932649de92423909a5130ec2 rdf:first sg:person.016655052074.44
199 rdf:rest N4ac5aecab032431f8652da3ff60c621e
200 Ne7f87c60fa57406aa2d9ec668949b98e schema:name dimensions_id
201 schema:value pub.1142372124
202 rdf:type schema:PropertyValue
203 Ne88a3786542541f78b991be276951ddd schema:name pubmed_id
204 schema:value 34737340
205 rdf:type schema:PropertyValue
206 Ned367d7df9f8483ca4e38cb1f1e364c2 rdf:first sg:person.0651135776.93
207 rdf:rest N0dc0c01ebd9447f0bdd1dab3484f7767
208 Nf4925e4b7c034392b36e610457ca8f41 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
209 schema:name Image Processing, Computer-Assisted
210 rdf:type schema:DefinedTerm
211 Nfd4d750c99d84c6eb3b736af38916b37 rdf:first sg:person.01011505663.09
212 rdf:rest N5e7f6e1fa51647e5b9a267d6e8af275f
213 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
214 schema:name Information and Computing Sciences
215 rdf:type schema:DefinedTerm
216 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
217 schema:name Artificial Intelligence and Image Processing
218 rdf:type schema:DefinedTerm
219 sg:journal.1045337 schema:issn 2045-2322
220 schema:name Scientific Reports
221 schema:publisher Springer Nature
222 rdf:type schema:Periodical
223 sg:person.010061104677.90 schema:affiliation grid-institutes:grid.413967.e
224 schema:familyName Kim
225 schema:givenName Kyung Won
226 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010061104677.90
227 rdf:type schema:Person
228 sg:person.01011505663.09 schema:affiliation grid-institutes:grid.263765.3
229 schema:familyName Lee
230 schema:givenName Jeongjin
231 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01011505663.09
232 rdf:type schema:Person
233 sg:person.010222413237.11 schema:affiliation grid-institutes:grid.413967.e
234 schema:familyName Shin
235 schema:givenName Youngbin
236 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010222413237.11
237 rdf:type schema:Person
238 sg:person.010625374353.81 schema:affiliation grid-institutes:grid.413967.e
239 schema:familyName Ha
240 schema:givenName Jiyeon
241 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010625374353.81
242 rdf:type schema:Person
243 sg:person.01137623345.18 schema:affiliation grid-institutes:grid.413967.e
244 schema:familyName Ko
245 schema:givenName Yousun
246 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01137623345.18
247 rdf:type schema:Person
248 sg:person.012477731120.69 schema:affiliation grid-institutes:grid.413967.e
249 schema:familyName Kim
250 schema:givenName Dong Wook
251 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012477731120.69
252 rdf:type schema:Person
253 sg:person.014001312403.46 schema:affiliation grid-institutes:grid.263765.3
254 schema:familyName Jeong
255 schema:givenName Heeryeol
256 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014001312403.46
257 rdf:type schema:Person
258 sg:person.015361710053.92 schema:affiliation grid-institutes:grid.413967.e
259 schema:familyName Lee
260 schema:givenName Jiwoo
261 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015361710053.92
262 rdf:type schema:Person
263 sg:person.016160635401.76 schema:affiliation grid-institutes:grid.267370.7
264 schema:familyName Park
265 schema:givenName Taeyong
266 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016160635401.76
267 rdf:type schema:Person
268 sg:person.016655052074.44 schema:affiliation grid-institutes:grid.263765.3
269 schema:familyName Khang
270 schema:givenName Seungwoo
271 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016655052074.44
272 rdf:type schema:Person
273 sg:person.0576122127.23 schema:affiliation grid-institutes:grid.413967.e
274 schema:familyName Ham
275 schema:givenName Su Jung
276 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0576122127.23
277 rdf:type schema:Person
278 sg:person.0651135776.93 schema:affiliation grid-institutes:grid.413967.e
279 schema:familyName Kim
280 schema:givenName Hong-Kyu
281 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0651135776.93
282 rdf:type schema:Person
283 sg:person.0671111600.05 schema:affiliation grid-institutes:grid.267370.7
284 schema:familyName Sung
285 schema:givenName Yu Sub
286 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0671111600.05
287 rdf:type schema:Person
288 sg:person.07455564201.65 schema:affiliation grid-institutes:grid.263765.3
289 schema:familyName Koo
290 schema:givenName Kyoyeong
291 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07455564201.65
292 rdf:type schema:Person
293 sg:pub.10.1007/978-3-030-01201-4_22 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107352150
294 https://doi.org/10.1007/978-3-030-01201-4_22
295 rdf:type schema:CreativeWork
296 sg:pub.10.1007/s10120-015-0546-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003903397
297 https://doi.org/10.1007/s10120-015-0546-4
298 rdf:type schema:CreativeWork
299 sg:pub.10.1007/s10278-017-9988-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1086357467
300 https://doi.org/10.1007/s10278-017-9988-z
301 rdf:type schema:CreativeWork
302 sg:pub.10.1007/s12194-011-0127-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025763617
303 https://doi.org/10.1007/s12194-011-0127-0
304 rdf:type schema:CreativeWork
305 sg:pub.10.1007/s13244-013-0286-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050737797
306 https://doi.org/10.1007/s13244-013-0286-0
307 rdf:type schema:CreativeWork
308 sg:pub.10.1038/ejcn.2014.169 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042737966
309 https://doi.org/10.1038/ejcn.2014.169
310 rdf:type schema:CreativeWork
311 sg:pub.10.1245/s10434-014-4040-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053187502
312 https://doi.org/10.1245/s10434-014-4040-8
313 rdf:type schema:CreativeWork
314 grid-institutes:grid.263765.3 schema:alternateName School of Computer Science and Engineering, Soongsil University, Seoul, Korea
315 schema:name School of Computer Science and Engineering, Soongsil University, Seoul, Korea
316 rdf:type schema:Organization
317 grid-institutes:grid.267370.7 schema:alternateName Department of Convergence Medicine, University of Ulsan College of Medicine, Seoul, Korea
318 Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Seoul, Korea
319 schema:name Clinical Research Center, Asan Medical Center, Seoul, Korea
320 Department of Convergence Medicine, University of Ulsan College of Medicine, Seoul, Korea
321 Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Seoul, Korea
322 rdf:type schema:Organization
323 grid-institutes:grid.413967.e schema:alternateName Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea
324 Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro, 43-gil, Songpa-gu, 05505, Seoul, Korea
325 Health Screening and Promotion Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
326 schema:name Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea
327 Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro, 43-gil, Songpa-gu, 05505, Seoul, Korea
328 Health Screening and Promotion Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
329 rdf:type schema:Organization
 




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


...