Integration of 2D iteration and a 3D CNN-based model for multi-type artifact suppression in C-arm cone-beam CT View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2021-09-16

AUTHORS

Dahim Choi, Wonjin Kim, Jiyeon Lee, Mina Han, Jongduk Baek, Jang-Hwan Choi

ABSTRACT

Limiting the potential risks associated with radiation exposure is critically important when obtaining a diagnostic image. However, lowering the level of radiation may cause excessive noise and artifacts in computed tomography (CT) scans. In this study, we implemented and tested the performance of patch-based and block-based REDCNN models and revealed that a 3D kernel is efficient in removing 3D noise and artifacts. Additionally, we applied a 3D bilateral filter and a 2D-based Landweber iteration method to remove any remaining noise and to prevent the edges from blurring, which are limitations of a deep learning-based noise reduction system. For the 2D-based Landweber iteration, we examined the requisite step size and the number of iterations. The representative CT noise and artifacts, which were Gaussian noise and view aliasing artifacts, respectively, were simulated on XCAT and reproduced in vivo to verify that the proposed method could be used in an analogous clinical setting. Lastly, the performance of the proposed algorithm was evaluated on in vivo data with real low-dose noise. Our proposed method effectively suppressed complex noise without losing diagnostic features in both the simulation study and experimental evaluation. Furthermore, for the simulation study, we adopted a numerical observer model to evaluate the structural fidelity of the image quality more appropriately than existing image quality assessment methods. More... »

PAGES

116

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00138-021-01240-3

DOI

http://dx.doi.org/10.1007/s00138-021-01240-3

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1141165174


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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, 30332, Atlanta, USA", 
          "id": "http://www.grid.ac/institutes/grid.470935.c", 
          "name": [
            "Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, 30332, Atlanta, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Choi", 
        "givenName": "Dahim", 
        "id": "sg:person.010704047027.11", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010704047027.11"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Division of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans University, 03760, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.255649.9", 
          "name": [
            "Division of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans University, 03760, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kim", 
        "givenName": "Wonjin", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Division of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans University, 03760, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.255649.9", 
          "name": [
            "Division of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans University, 03760, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lee", 
        "givenName": "Jiyeon", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Integrated Technology, Yonsei University, 406840, Incheon, Korea", 
          "id": "http://www.grid.ac/institutes/grid.15444.30", 
          "name": [
            "School of Integrated Technology, Yonsei University, 406840, Incheon, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Han", 
        "givenName": "Mina", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Integrated Technology, Yonsei University, 406840, Incheon, Korea", 
          "id": "http://www.grid.ac/institutes/grid.15444.30", 
          "name": [
            "School of Integrated Technology, Yonsei University, 406840, Incheon, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Baek", 
        "givenName": "Jongduk", 
        "id": "sg:person.0766770345.58", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0766770345.58"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Division of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans University, 03760, Seoul, Korea", 
          "id": "http://www.grid.ac/institutes/grid.255649.9", 
          "name": [
            "Division of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans University, 03760, Seoul, Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Choi", 
        "givenName": "Jang-Hwan", 
        "id": "sg:person.01347002431.75", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01347002431.75"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s10278-018-0056-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101127404", 
          "https://doi.org/10.1007/s10278-018-0056-0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-46475-6_43", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018034649", 
          "https://doi.org/10.1007/978-3-319-46475-6_43"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2021-09-16", 
    "datePublishedReg": "2021-09-16", 
    "description": "Limiting the potential risks associated with radiation exposure is critically important when obtaining a diagnostic image. However, lowering the level of radiation may cause excessive noise and artifacts in computed tomography (CT) scans. In this study, we implemented and tested the performance of patch-based and block-based REDCNN models and revealed that a 3D kernel is efficient in removing 3D noise and artifacts. Additionally, we applied a 3D bilateral filter and a 2D-based Landweber iteration method to remove any remaining noise and to prevent the edges from blurring, which are limitations of a deep learning-based noise reduction system. For the 2D-based Landweber iteration, we examined the requisite step size and the number of iterations. The representative CT noise and artifacts, which were Gaussian noise and view aliasing artifacts, respectively, were simulated on XCAT and reproduced in vivo to verify that the proposed method could be used in an analogous clinical setting. Lastly, the performance of the proposed algorithm was evaluated on in vivo data with real low-dose noise. Our proposed method effectively suppressed complex noise without losing diagnostic features in both the simulation study and experimental evaluation. Furthermore, for the simulation study, we adopted a numerical observer model to evaluate the structural fidelity of the image quality more appropriately than existing image quality assessment methods.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s00138-021-01240-3", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1045266", 
        "issn": [
          "0932-8092", 
          "1432-1769"
        ], 
        "name": "Machine Vision and Applications", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "6", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "32"
      }
    ], 
    "keywords": [
      "arm cone-beam CT", 
      "tomography scan", 
      "clinical setting", 
      "radiation exposure", 
      "cone-beam CT", 
      "vivo data", 
      "potential risk", 
      "diagnostic features", 
      "diagnostic images", 
      "study", 
      "CT", 
      "noise reduction system", 
      "scans", 
      "risk", 
      "vivo", 
      "exposure", 
      "level of radiation", 
      "Landweber iteration method", 
      "excessive noise", 
      "assessment methods", 
      "suppression", 
      "setting", 
      "simulation study", 
      "reduction system", 
      "levels", 
      "image quality", 
      "evaluation", 
      "bilateral filter", 
      "noise", 
      "artifact suppression", 
      "Gaussian noise", 
      "step size", 
      "complex noise", 
      "structural fidelity", 
      "observer model", 
      "experimental evaluation", 
      "iteration method", 
      "method", 
      "performance", 
      "data", 
      "Landweber iteration", 
      "quality", 
      "CT noise", 
      "number of iterations", 
      "number", 
      "model", 
      "image quality assessment method", 
      "filter", 
      "features", 
      "limitations", 
      "iteration", 
      "radiation", 
      "quality assessment method", 
      "artifacts", 
      "size", 
      "XCAT", 
      "edge", 
      "system", 
      "view", 
      "algorithm", 
      "integration", 
      "images", 
      "fidelity", 
      "CNN", 
      "kernel", 
      "block-based REDCNN models", 
      "REDCNN models", 
      "deep learning-based noise reduction system", 
      "learning-based noise reduction system", 
      "requisite step size", 
      "representative CT noise", 
      "analogous clinical setting", 
      "real low-dose noise", 
      "low-dose noise", 
      "numerical observer model", 
      "multi-type artifact suppression"
    ], 
    "name": "Integration of 2D iteration and a 3D CNN-based model for multi-type artifact suppression in C-arm cone-beam CT", 
    "pagination": "116", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1141165174"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00138-021-01240-3"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00138-021-01240-3", 
      "https://app.dimensions.ai/details/publication/pub.1141165174"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-01-01T19:00", 
    "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_904.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s00138-021-01240-3"
  }
]
 

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/s00138-021-01240-3'

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/s00138-021-01240-3'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00138-021-01240-3'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00138-021-01240-3'


 

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

180 TRIPLES      22 PREDICATES      103 URIs      93 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00138-021-01240-3 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N8d966394e1e644229715b9ebed6c7818
4 schema:citation sg:pub.10.1007/978-3-319-46475-6_43
5 sg:pub.10.1007/s10278-018-0056-0
6 schema:datePublished 2021-09-16
7 schema:datePublishedReg 2021-09-16
8 schema:description Limiting the potential risks associated with radiation exposure is critically important when obtaining a diagnostic image. However, lowering the level of radiation may cause excessive noise and artifacts in computed tomography (CT) scans. In this study, we implemented and tested the performance of patch-based and block-based REDCNN models and revealed that a 3D kernel is efficient in removing 3D noise and artifacts. Additionally, we applied a 3D bilateral filter and a 2D-based Landweber iteration method to remove any remaining noise and to prevent the edges from blurring, which are limitations of a deep learning-based noise reduction system. For the 2D-based Landweber iteration, we examined the requisite step size and the number of iterations. The representative CT noise and artifacts, which were Gaussian noise and view aliasing artifacts, respectively, were simulated on XCAT and reproduced in vivo to verify that the proposed method could be used in an analogous clinical setting. Lastly, the performance of the proposed algorithm was evaluated on in vivo data with real low-dose noise. Our proposed method effectively suppressed complex noise without losing diagnostic features in both the simulation study and experimental evaluation. Furthermore, for the simulation study, we adopted a numerical observer model to evaluate the structural fidelity of the image quality more appropriately than existing image quality assessment methods.
9 schema:genre article
10 schema:inLanguage en
11 schema:isAccessibleForFree false
12 schema:isPartOf N742a09990cb649399c0211cf226969a7
13 Nc3f978a6e81e4b099c8b0fe54314894a
14 sg:journal.1045266
15 schema:keywords CNN
16 CT
17 CT noise
18 Gaussian noise
19 Landweber iteration
20 Landweber iteration method
21 REDCNN models
22 XCAT
23 algorithm
24 analogous clinical setting
25 arm cone-beam CT
26 artifact suppression
27 artifacts
28 assessment methods
29 bilateral filter
30 block-based REDCNN models
31 clinical setting
32 complex noise
33 cone-beam CT
34 data
35 deep learning-based noise reduction system
36 diagnostic features
37 diagnostic images
38 edge
39 evaluation
40 excessive noise
41 experimental evaluation
42 exposure
43 features
44 fidelity
45 filter
46 image quality
47 image quality assessment method
48 images
49 integration
50 iteration
51 iteration method
52 kernel
53 learning-based noise reduction system
54 level of radiation
55 levels
56 limitations
57 low-dose noise
58 method
59 model
60 multi-type artifact suppression
61 noise
62 noise reduction system
63 number
64 number of iterations
65 numerical observer model
66 observer model
67 performance
68 potential risk
69 quality
70 quality assessment method
71 radiation
72 radiation exposure
73 real low-dose noise
74 reduction system
75 representative CT noise
76 requisite step size
77 risk
78 scans
79 setting
80 simulation study
81 size
82 step size
83 structural fidelity
84 study
85 suppression
86 system
87 tomography scan
88 view
89 vivo
90 vivo data
91 schema:name Integration of 2D iteration and a 3D CNN-based model for multi-type artifact suppression in C-arm cone-beam CT
92 schema:pagination 116
93 schema:productId Nc2d5ad9b5bf64d1e9db6b7e2e5edd16c
94 Nc6fabbe5c01d4eeea9c4735670e66e61
95 schema:sameAs https://app.dimensions.ai/details/publication/pub.1141165174
96 https://doi.org/10.1007/s00138-021-01240-3
97 schema:sdDatePublished 2022-01-01T19:00
98 schema:sdLicense https://scigraph.springernature.com/explorer/license/
99 schema:sdPublisher N049bc8c7951f4f348c0e643d70c8c8c0
100 schema:url https://doi.org/10.1007/s00138-021-01240-3
101 sgo:license sg:explorer/license/
102 sgo:sdDataset articles
103 rdf:type schema:ScholarlyArticle
104 N049bc8c7951f4f348c0e643d70c8c8c0 schema:name Springer Nature - SN SciGraph project
105 rdf:type schema:Organization
106 N10aa7e0be37b4c85b23018a391d3262a schema:affiliation grid-institutes:grid.255649.9
107 schema:familyName Kim
108 schema:givenName Wonjin
109 rdf:type schema:Person
110 N2bda854986394c0d8ce9432fe2d32c57 schema:affiliation grid-institutes:grid.15444.30
111 schema:familyName Han
112 schema:givenName Mina
113 rdf:type schema:Person
114 N3ff675f45ddc4b48ae125c94d585c76d rdf:first sg:person.0766770345.58
115 rdf:rest Nd52c4c85bc1e42dc9243b93f05b4ecd4
116 N742a09990cb649399c0211cf226969a7 schema:volumeNumber 32
117 rdf:type schema:PublicationVolume
118 N8d966394e1e644229715b9ebed6c7818 rdf:first sg:person.010704047027.11
119 rdf:rest Nfd9f6ee2515844dca603e82e78fc6210
120 Na106ad45bd8943b9a14f574a83c07be9 rdf:first Nd161b2b930ad4c10961317a56a4cba58
121 rdf:rest Nbe431c7824ac4a49bee14463b9a8c3b8
122 Nbe431c7824ac4a49bee14463b9a8c3b8 rdf:first N2bda854986394c0d8ce9432fe2d32c57
123 rdf:rest N3ff675f45ddc4b48ae125c94d585c76d
124 Nc2d5ad9b5bf64d1e9db6b7e2e5edd16c schema:name dimensions_id
125 schema:value pub.1141165174
126 rdf:type schema:PropertyValue
127 Nc3f978a6e81e4b099c8b0fe54314894a schema:issueNumber 6
128 rdf:type schema:PublicationIssue
129 Nc6fabbe5c01d4eeea9c4735670e66e61 schema:name doi
130 schema:value 10.1007/s00138-021-01240-3
131 rdf:type schema:PropertyValue
132 Nd161b2b930ad4c10961317a56a4cba58 schema:affiliation grid-institutes:grid.255649.9
133 schema:familyName Lee
134 schema:givenName Jiyeon
135 rdf:type schema:Person
136 Nd52c4c85bc1e42dc9243b93f05b4ecd4 rdf:first sg:person.01347002431.75
137 rdf:rest rdf:nil
138 Nfd9f6ee2515844dca603e82e78fc6210 rdf:first N10aa7e0be37b4c85b23018a391d3262a
139 rdf:rest Na106ad45bd8943b9a14f574a83c07be9
140 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
141 schema:name Information and Computing Sciences
142 rdf:type schema:DefinedTerm
143 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
144 schema:name Artificial Intelligence and Image Processing
145 rdf:type schema:DefinedTerm
146 sg:journal.1045266 schema:issn 0932-8092
147 1432-1769
148 schema:name Machine Vision and Applications
149 schema:publisher Springer Nature
150 rdf:type schema:Periodical
151 sg:person.010704047027.11 schema:affiliation grid-institutes:grid.470935.c
152 schema:familyName Choi
153 schema:givenName Dahim
154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010704047027.11
155 rdf:type schema:Person
156 sg:person.01347002431.75 schema:affiliation grid-institutes:grid.255649.9
157 schema:familyName Choi
158 schema:givenName Jang-Hwan
159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01347002431.75
160 rdf:type schema:Person
161 sg:person.0766770345.58 schema:affiliation grid-institutes:grid.15444.30
162 schema:familyName Baek
163 schema:givenName Jongduk
164 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0766770345.58
165 rdf:type schema:Person
166 sg:pub.10.1007/978-3-319-46475-6_43 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018034649
167 https://doi.org/10.1007/978-3-319-46475-6_43
168 rdf:type schema:CreativeWork
169 sg:pub.10.1007/s10278-018-0056-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101127404
170 https://doi.org/10.1007/s10278-018-0056-0
171 rdf:type schema:CreativeWork
172 grid-institutes:grid.15444.30 schema:alternateName School of Integrated Technology, Yonsei University, 406840, Incheon, Korea
173 schema:name School of Integrated Technology, Yonsei University, 406840, Incheon, Korea
174 rdf:type schema:Organization
175 grid-institutes:grid.255649.9 schema:alternateName Division of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans University, 03760, Seoul, Korea
176 schema:name Division of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans University, 03760, Seoul, Korea
177 rdf:type schema:Organization
178 grid-institutes:grid.470935.c schema:alternateName Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, 30332, Atlanta, USA
179 schema:name Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, 30332, Atlanta, USA
180 rdf:type schema:Organization
 




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


...