Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2021-06-03

AUTHORS

Kazutoshi Ukai, Rashedur Rahman, Naomi Yagi, Keigo Hayashi, Akihiro Maruo, Hirotsugu Muratsu, Syoji Kobashi

ABSTRACT

Pelvic fracture is one of the leading causes of death in the elderly, carrying a high risk of death within 1 year of fracture. This study proposes an automated method to detect pelvic fractures on 3-dimensional computed tomography (3D-CT). Deep convolutional neural networks (DCNNs) have been used for lesion detection on 2D and 3D medical images. However, training a DCNN directly using 3D images is complicated, computationally costly, and requires large amounts of training data. We propose a method that evaluates multiple, 2D, real-time object detection systems (YOLOv3 models) in parallel, in which each YOLOv3 model is trained using differently orientated 2D slab images reconstructed from 3D-CT. We assume that an appropriate reconstruction orientation would exist to optimally characterize image features of bone fractures on 3D-CT. Multiple YOLOv3 models in parallel detect 2D fracture candidates in different orientations simultaneously. The 3D fracture region is then obtained by integrating the 2D fracture candidates. The proposed method was validated in 93 subjects with bone fractures. Area under the curve (AUC) was 0.824, with 0.805 recall and 0.907 precision. The AUC with a single orientation was 0.652. This method was then applied to 112 subjects without bone fractures to evaluate over-detection. The proposed method successfully detected no bone fractures in all except 4 non-fracture subjects (96.4%). More... »

PAGES

11716

Identifiers

URI

http://scigraph.springernature.com/pub.10.1038/s41598-021-91144-z

DOI

http://dx.doi.org/10.1038/s41598-021-91144-z

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1138571668

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/34083655


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/2008/11", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Medical and Health 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"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1103", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Clinical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Adult", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Aged", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Aged, 80 and over", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Deep Learning", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Female", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Fractures, Bone", 
        "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": "Imaging, Three-Dimensional", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Male", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Middle Aged", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Models, Theoretical", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Neural Networks, Computer", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Pelvic Bones", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Reproducibility of Results", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Sensitivity and Specificity", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Tomography, X-Ray Computed", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Young Adult", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Graduate School of Engineering, University of Hyogo, Himeji, Japan", 
          "id": "http://www.grid.ac/institutes/grid.266453.0", 
          "name": [
            "Research and Development Center, GLORY Ltd, Himeji, Japan", 
            "Graduate School of Engineering, University of Hyogo, Himeji, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ukai", 
        "givenName": "Kazutoshi", 
        "id": "sg:person.012272444207.36", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012272444207.36"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Graduate School of Engineering, University of Hyogo, Himeji, Japan", 
          "id": "http://www.grid.ac/institutes/grid.266453.0", 
          "name": [
            "Graduate School of Engineering, University of Hyogo, Himeji, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Rahman", 
        "givenName": "Rashedur", 
        "id": "sg:person.012251600317.34", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012251600317.34"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Himeji Dokkyo University, Himeji, Japan", 
          "id": "http://www.grid.ac/institutes/grid.412142.0", 
          "name": [
            "Graduate School of Engineering, University of Hyogo, Himeji, Japan", 
            "Himeji Dokkyo University, Himeji, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Yagi", 
        "givenName": "Naomi", 
        "id": "sg:person.010561511003.90", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010561511003.90"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Steel Memorial Hirohata Hospital, Himeji, Japan", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Steel Memorial Hirohata Hospital, Himeji, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hayashi", 
        "givenName": "Keigo", 
        "id": "sg:person.016141620635.30", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016141620635.30"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Steel Memorial Hirohata Hospital, Himeji, Japan", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Steel Memorial Hirohata Hospital, Himeji, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Maruo", 
        "givenName": "Akihiro", 
        "id": "sg:person.0626471661.86", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0626471661.86"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Steel Memorial Hirohata Hospital, Himeji, Japan", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Steel Memorial Hirohata Hospital, Himeji, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Muratsu", 
        "givenName": "Hirotsugu", 
        "id": "sg:person.01221412732.92", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01221412732.92"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Graduate School of Engineering, University of Hyogo, Himeji, Japan", 
          "id": "http://www.grid.ac/institutes/grid.266453.0", 
          "name": [
            "Graduate School of Engineering, University of Hyogo, Himeji, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kobashi", 
        "givenName": "Syoji", 
        "id": "sg:person.010347056277.56", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010347056277.56"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s00198-017-4345-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100078737", 
          "https://doi.org/10.1007/s00198-017-4345-0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s12891-021-04260-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1137716884", 
          "https://doi.org/10.1186/s12891-021-04260-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11263-009-0275-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014796149", 
          "https://doi.org/10.1007/s11263-009-0275-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s13018-019-1226-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1117770386", 
          "https://doi.org/10.1186/s13018-019-1226-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf03016088", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043292452", 
          "https://doi.org/10.1007/bf03016088"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.4103/ortho.ijortho_631_17", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1111965009", 
          "https://doi.org/10.4103/ortho.ijortho_631_17"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00223-015-0056-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010333526", 
          "https://doi.org/10.1007/s00223-015-0056-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00256-018-3016-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1105198115", 
          "https://doi.org/10.1007/s00256-018-3016-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-10404-1_65", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024028888", 
          "https://doi.org/10.1007/978-3-319-10404-1_65"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2021-06-03", 
    "datePublishedReg": "2021-06-03", 
    "description": "Pelvic fracture is one of the leading causes of death in the elderly, carrying a high risk of death within 1\u00a0year of fracture. This study proposes an automated method to detect pelvic fractures on 3-dimensional computed tomography (3D-CT). Deep convolutional neural networks (DCNNs) have been used for lesion detection on 2D and 3D medical images. However, training a DCNN directly using 3D images is complicated, computationally costly, and requires large amounts of training data. We propose a method that evaluates multiple, 2D, real-time object detection systems (YOLOv3 models) in parallel, in which each YOLOv3 model is trained using differently orientated 2D slab images reconstructed from 3D-CT. We assume that an appropriate reconstruction orientation would exist to optimally characterize image features of bone fractures on 3D-CT. Multiple YOLOv3 models in parallel detect 2D fracture candidates in different orientations simultaneously. The 3D fracture region is then obtained by integrating the 2D fracture candidates. The proposed method was validated in 93 subjects with bone fractures. Area under the curve (AUC) was 0.824, with 0.805 recall and 0.907 precision. The AUC with a single orientation was 0.652. This method was then applied to 112 subjects without bone fractures to evaluate over-detection. The proposed method successfully detected no bone fractures in all except 4 non-fracture subjects (96.4%).", 
    "genre": "article", 
    "id": "sg:pub.10.1038/s41598-021-91144-z", 
    "inLanguage": "en", 
    "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 convolutional neural network", 
      "convolutional neural network", 
      "YOLOv3 model", 
      "neural network", 
      "real-time object detection system", 
      "object detection system", 
      "fracture candidates", 
      "medical images", 
      "image features", 
      "training data", 
      "detection system", 
      "slab images", 
      "pelvic fractures", 
      "bone fractures", 
      "images", 
      "network", 
      "lesion detection", 
      "large amount", 
      "year of fracture", 
      "non-fracture subjects", 
      "cause of death", 
      "detection", 
      "high risk", 
      "computed tomography", 
      "method", 
      "recall", 
      "parallel", 
      "model", 
      "death", 
      "fractures", 
      "subjects", 
      "precision", 
      "features", 
      "system", 
      "data", 
      "AUC", 
      "tomography", 
      "risk", 
      "cause", 
      "years", 
      "amount", 
      "candidates", 
      "orientation", 
      "different orientations", 
      "study", 
      "area", 
      "fracture region", 
      "curves", 
      "region", 
      "single orientation"
    ], 
    "name": "Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images", 
    "pagination": "11716", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1138571668"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1038/s41598-021-91144-z"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "34083655"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1038/s41598-021-91144-z", 
      "https://app.dimensions.ai/details/publication/pub.1138571668"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-05-20T07:37", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220519/entities/gbq_results/article/article_878.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1038/s41598-021-91144-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.10.1038/s41598-021-91144-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.10.1038/s41598-021-91144-z'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1038/s41598-021-91144-z'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1038/s41598-021-91144-z'


 

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

277 TRIPLES      22 PREDICATES      105 URIs      86 LITERALS      25 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1038/s41598-021-91144-z schema:about N105e066d43d842b8a58b0a4b024ddfdf
2 N1635e0bae0464feba1d24afa5fc6e45e
3 N26b8d95a6c2144dfaf741c1f5620de78
4 N279ab21eef3444b299d99f35f0133a10
5 N30fcc3ec8193430490b2d23b19fb86d0
6 N47d77c61b3964a5bb033203859a9a93e
7 N4f867589b06643888105eaa22e6defec
8 N6bed6e0996b644d8b694adc75a502ff9
9 N7128d2d04c6a4fd08535130869785641
10 N7ea6c56773d14d85a294606352d6ecaf
11 N8cd4043d81aa41b3bf0089dfa167b02a
12 Nae40253cc81b4cd49b5064baaf0a1ab4
13 Nbeb32cfe268c47058ed2d429d67a254d
14 Nda8e769340604eeab312700a321e3298
15 Ne312a296b9b040b98dcb93b18e09565c
16 Ne5e883c779894b3fa90fd41bd670da5b
17 Nf37c19272c3d4ec283366aea95d1016c
18 Nff436aa0fafd4d409b1e98b6a5ad0748
19 anzsrc-for:08
20 anzsrc-for:0801
21 anzsrc-for:11
22 anzsrc-for:1103
23 schema:author N4fd3a9f367ac420eb94bdd1e245c1030
24 schema:citation sg:pub.10.1007/978-3-319-10404-1_65
25 sg:pub.10.1007/bf03016088
26 sg:pub.10.1007/s00198-017-4345-0
27 sg:pub.10.1007/s00223-015-0056-8
28 sg:pub.10.1007/s00256-018-3016-3
29 sg:pub.10.1007/s11263-009-0275-4
30 sg:pub.10.1186/s12891-021-04260-2
31 sg:pub.10.1186/s13018-019-1226-6
32 sg:pub.10.4103/ortho.ijortho_631_17
33 schema:datePublished 2021-06-03
34 schema:datePublishedReg 2021-06-03
35 schema:description Pelvic fracture is one of the leading causes of death in the elderly, carrying a high risk of death within 1 year of fracture. This study proposes an automated method to detect pelvic fractures on 3-dimensional computed tomography (3D-CT). Deep convolutional neural networks (DCNNs) have been used for lesion detection on 2D and 3D medical images. However, training a DCNN directly using 3D images is complicated, computationally costly, and requires large amounts of training data. We propose a method that evaluates multiple, 2D, real-time object detection systems (YOLOv3 models) in parallel, in which each YOLOv3 model is trained using differently orientated 2D slab images reconstructed from 3D-CT. We assume that an appropriate reconstruction orientation would exist to optimally characterize image features of bone fractures on 3D-CT. Multiple YOLOv3 models in parallel detect 2D fracture candidates in different orientations simultaneously. The 3D fracture region is then obtained by integrating the 2D fracture candidates. The proposed method was validated in 93 subjects with bone fractures. Area under the curve (AUC) was 0.824, with 0.805 recall and 0.907 precision. The AUC with a single orientation was 0.652. This method was then applied to 112 subjects without bone fractures to evaluate over-detection. The proposed method successfully detected no bone fractures in all except 4 non-fracture subjects (96.4%).
36 schema:genre article
37 schema:inLanguage en
38 schema:isAccessibleForFree true
39 schema:isPartOf N47fc0e4277be4fcba6c7fab4b3b9eea7
40 Nc88f7f1d730b4387ac579fa4cb89416e
41 sg:journal.1045337
42 schema:keywords AUC
43 YOLOv3 model
44 amount
45 area
46 bone fractures
47 candidates
48 cause
49 cause of death
50 computed tomography
51 convolutional neural network
52 curves
53 data
54 death
55 deep convolutional neural network
56 detection
57 detection system
58 different orientations
59 features
60 fracture candidates
61 fracture region
62 fractures
63 high risk
64 image features
65 images
66 large amount
67 lesion detection
68 medical images
69 method
70 model
71 network
72 neural network
73 non-fracture subjects
74 object detection system
75 orientation
76 parallel
77 pelvic fractures
78 precision
79 real-time object detection system
80 recall
81 region
82 risk
83 single orientation
84 slab images
85 study
86 subjects
87 system
88 tomography
89 training data
90 year of fracture
91 years
92 schema:name Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images
93 schema:pagination 11716
94 schema:productId N16f2d92ee39f401e8a112151dbd3ca5b
95 N229b33425990449bacd34f73e5695ffc
96 Nf6f060833ecc48c891fe42aec6d2bbf2
97 schema:sameAs https://app.dimensions.ai/details/publication/pub.1138571668
98 https://doi.org/10.1038/s41598-021-91144-z
99 schema:sdDatePublished 2022-05-20T07:37
100 schema:sdLicense https://scigraph.springernature.com/explorer/license/
101 schema:sdPublisher N17d90ec58a7e4077ad19c17eea809628
102 schema:url https://doi.org/10.1038/s41598-021-91144-z
103 sgo:license sg:explorer/license/
104 sgo:sdDataset articles
105 rdf:type schema:ScholarlyArticle
106 N1024f04d9c79482688ade29f1f95c48b rdf:first sg:person.012251600317.34
107 rdf:rest N40035ab279f2477fa0374eb0e6a796a1
108 N105e066d43d842b8a58b0a4b024ddfdf schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
109 schema:name Deep Learning
110 rdf:type schema:DefinedTerm
111 N1635e0bae0464feba1d24afa5fc6e45e schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
112 schema:name Tomography, X-Ray Computed
113 rdf:type schema:DefinedTerm
114 N16f2d92ee39f401e8a112151dbd3ca5b schema:name pubmed_id
115 schema:value 34083655
116 rdf:type schema:PropertyValue
117 N17d90ec58a7e4077ad19c17eea809628 schema:name Springer Nature - SN SciGraph project
118 rdf:type schema:Organization
119 N229b33425990449bacd34f73e5695ffc schema:name dimensions_id
120 schema:value pub.1138571668
121 rdf:type schema:PropertyValue
122 N26b8d95a6c2144dfaf741c1f5620de78 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
123 schema:name Young Adult
124 rdf:type schema:DefinedTerm
125 N279ab21eef3444b299d99f35f0133a10 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
126 schema:name Middle Aged
127 rdf:type schema:DefinedTerm
128 N30fcc3ec8193430490b2d23b19fb86d0 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
129 schema:name Fractures, Bone
130 rdf:type schema:DefinedTerm
131 N40035ab279f2477fa0374eb0e6a796a1 rdf:first sg:person.010561511003.90
132 rdf:rest Nf5d6f00077044440b22aed537aeddfbd
133 N47d77c61b3964a5bb033203859a9a93e schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
134 schema:name Female
135 rdf:type schema:DefinedTerm
136 N47fc0e4277be4fcba6c7fab4b3b9eea7 schema:issueNumber 1
137 rdf:type schema:PublicationIssue
138 N4f867589b06643888105eaa22e6defec schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
139 schema:name Models, Theoretical
140 rdf:type schema:DefinedTerm
141 N4fd3a9f367ac420eb94bdd1e245c1030 rdf:first sg:person.012272444207.36
142 rdf:rest N1024f04d9c79482688ade29f1f95c48b
143 N6a8e011b71aa4db4959720c0f0eb98fc rdf:first sg:person.01221412732.92
144 rdf:rest N7504d646dbfc41a4ac01a9025216fa40
145 N6bed6e0996b644d8b694adc75a502ff9 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
146 schema:name Aged, 80 and over
147 rdf:type schema:DefinedTerm
148 N7128d2d04c6a4fd08535130869785641 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
149 schema:name Pelvic Bones
150 rdf:type schema:DefinedTerm
151 N7504d646dbfc41a4ac01a9025216fa40 rdf:first sg:person.010347056277.56
152 rdf:rest rdf:nil
153 N7ea6c56773d14d85a294606352d6ecaf schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
154 schema:name Sensitivity and Specificity
155 rdf:type schema:DefinedTerm
156 N8cd4043d81aa41b3bf0089dfa167b02a schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
157 schema:name Imaging, Three-Dimensional
158 rdf:type schema:DefinedTerm
159 N9631ed33a1ec47e487564d9b8d16dc46 rdf:first sg:person.0626471661.86
160 rdf:rest N6a8e011b71aa4db4959720c0f0eb98fc
161 Nae40253cc81b4cd49b5064baaf0a1ab4 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
162 schema:name Adult
163 rdf:type schema:DefinedTerm
164 Nbeb32cfe268c47058ed2d429d67a254d schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
165 schema:name Image Processing, Computer-Assisted
166 rdf:type schema:DefinedTerm
167 Nc88f7f1d730b4387ac579fa4cb89416e schema:volumeNumber 11
168 rdf:type schema:PublicationVolume
169 Nda8e769340604eeab312700a321e3298 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
170 schema:name Male
171 rdf:type schema:DefinedTerm
172 Ne312a296b9b040b98dcb93b18e09565c schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
173 schema:name Neural Networks, Computer
174 rdf:type schema:DefinedTerm
175 Ne5e883c779894b3fa90fd41bd670da5b schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
176 schema:name Reproducibility of Results
177 rdf:type schema:DefinedTerm
178 Nf37c19272c3d4ec283366aea95d1016c schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
179 schema:name Humans
180 rdf:type schema:DefinedTerm
181 Nf5d6f00077044440b22aed537aeddfbd rdf:first sg:person.016141620635.30
182 rdf:rest N9631ed33a1ec47e487564d9b8d16dc46
183 Nf6f060833ecc48c891fe42aec6d2bbf2 schema:name doi
184 schema:value 10.1038/s41598-021-91144-z
185 rdf:type schema:PropertyValue
186 Nff436aa0fafd4d409b1e98b6a5ad0748 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
187 schema:name Aged
188 rdf:type schema:DefinedTerm
189 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
190 schema:name Information and Computing Sciences
191 rdf:type schema:DefinedTerm
192 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
193 schema:name Artificial Intelligence and Image Processing
194 rdf:type schema:DefinedTerm
195 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
196 schema:name Medical and Health Sciences
197 rdf:type schema:DefinedTerm
198 anzsrc-for:1103 schema:inDefinedTermSet anzsrc-for:
199 schema:name Clinical Sciences
200 rdf:type schema:DefinedTerm
201 sg:journal.1045337 schema:issn 2045-2322
202 schema:name Scientific Reports
203 schema:publisher Springer Nature
204 rdf:type schema:Periodical
205 sg:person.010347056277.56 schema:affiliation grid-institutes:grid.266453.0
206 schema:familyName Kobashi
207 schema:givenName Syoji
208 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010347056277.56
209 rdf:type schema:Person
210 sg:person.010561511003.90 schema:affiliation grid-institutes:grid.412142.0
211 schema:familyName Yagi
212 schema:givenName Naomi
213 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010561511003.90
214 rdf:type schema:Person
215 sg:person.01221412732.92 schema:affiliation grid-institutes:None
216 schema:familyName Muratsu
217 schema:givenName Hirotsugu
218 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01221412732.92
219 rdf:type schema:Person
220 sg:person.012251600317.34 schema:affiliation grid-institutes:grid.266453.0
221 schema:familyName Rahman
222 schema:givenName Rashedur
223 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012251600317.34
224 rdf:type schema:Person
225 sg:person.012272444207.36 schema:affiliation grid-institutes:grid.266453.0
226 schema:familyName Ukai
227 schema:givenName Kazutoshi
228 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012272444207.36
229 rdf:type schema:Person
230 sg:person.016141620635.30 schema:affiliation grid-institutes:None
231 schema:familyName Hayashi
232 schema:givenName Keigo
233 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016141620635.30
234 rdf:type schema:Person
235 sg:person.0626471661.86 schema:affiliation grid-institutes:None
236 schema:familyName Maruo
237 schema:givenName Akihiro
238 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0626471661.86
239 rdf:type schema:Person
240 sg:pub.10.1007/978-3-319-10404-1_65 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024028888
241 https://doi.org/10.1007/978-3-319-10404-1_65
242 rdf:type schema:CreativeWork
243 sg:pub.10.1007/bf03016088 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043292452
244 https://doi.org/10.1007/bf03016088
245 rdf:type schema:CreativeWork
246 sg:pub.10.1007/s00198-017-4345-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100078737
247 https://doi.org/10.1007/s00198-017-4345-0
248 rdf:type schema:CreativeWork
249 sg:pub.10.1007/s00223-015-0056-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010333526
250 https://doi.org/10.1007/s00223-015-0056-8
251 rdf:type schema:CreativeWork
252 sg:pub.10.1007/s00256-018-3016-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105198115
253 https://doi.org/10.1007/s00256-018-3016-3
254 rdf:type schema:CreativeWork
255 sg:pub.10.1007/s11263-009-0275-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014796149
256 https://doi.org/10.1007/s11263-009-0275-4
257 rdf:type schema:CreativeWork
258 sg:pub.10.1186/s12891-021-04260-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1137716884
259 https://doi.org/10.1186/s12891-021-04260-2
260 rdf:type schema:CreativeWork
261 sg:pub.10.1186/s13018-019-1226-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1117770386
262 https://doi.org/10.1186/s13018-019-1226-6
263 rdf:type schema:CreativeWork
264 sg:pub.10.4103/ortho.ijortho_631_17 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111965009
265 https://doi.org/10.4103/ortho.ijortho_631_17
266 rdf:type schema:CreativeWork
267 grid-institutes:None schema:alternateName Steel Memorial Hirohata Hospital, Himeji, Japan
268 schema:name Steel Memorial Hirohata Hospital, Himeji, Japan
269 rdf:type schema:Organization
270 grid-institutes:grid.266453.0 schema:alternateName Graduate School of Engineering, University of Hyogo, Himeji, Japan
271 schema:name Graduate School of Engineering, University of Hyogo, Himeji, Japan
272 Research and Development Center, GLORY Ltd, Himeji, Japan
273 rdf:type schema:Organization
274 grid-institutes:grid.412142.0 schema:alternateName Himeji Dokkyo University, Himeji, Japan
275 schema:name Graduate School of Engineering, University of Hyogo, Himeji, Japan
276 Himeji Dokkyo University, Himeji, Japan
277 rdf:type schema:Organization
 




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


...