Full-Dose PET Image Estimation from Low-Dose PET Image Using Deep Learning: a Pilot Study View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2018-11-06

AUTHORS

Sydney Kaplan, Yang-Ming Zhu

ABSTRACT

Positron emission tomography (PET) imaging is an effective tool used in determining disease stage and lesion malignancy; however, radiation exposure to patients and technicians during PET scans continues to draw concern. One way to minimize radiation exposure is to reduce the dose of radioactive tracer administered in order to obtain the scan. Yet, low-dose images are inherently noisy and have poor image quality making them difficult to read. This paper proposes the use of a deep learning model that takes specific image features into account in the loss function to denoise low-dose PET image slices and estimate their full-dose image quality equivalent. Testing on low-dose image slices indicates a significant improvement in image quality that is comparable to the ground truth full–dose image slices. Additionally, this approach can lower the cost of conducting a PET scan since less radioactive material is required per scan, which may promote the usage of PET scans for medical diagnosis. More... »

PAGES

773-778

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s10278-018-0150-3

DOI

http://dx.doi.org/10.1007/s10278-018-0150-3

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1108058515

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/30402670


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/2008/11", 
        "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/2008/1103", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Clinical Sciences", 
        "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": "Pilot Projects", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Positron-Emission Tomography", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Radiation Dosage", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Signal-To-Noise Ratio", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Department of Neurology, Washington University School of Medicine, 63110, St. Louis, MO, USA", 
          "id": "http://www.grid.ac/institutes/grid.4367.6", 
          "name": [
            "Philips Healthcare, 44143, Highland Heights, OH, USA", 
            "Department of Neurology, Washington University School of Medicine, 63110, St. Louis, MO, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kaplan", 
        "givenName": "Sydney", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Siemens Healthineers, 07836, Flanders, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.415886.6", 
          "name": [
            "Philips Healthcare, 44143, Highland Heights, OH, USA", 
            "Siemens Healthineers, 07836, Flanders, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhu", 
        "givenName": "Yang-Ming", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s11227-017-2080-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085733860", 
          "https://doi.org/10.1007/s11227-017-2080-0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-67389-9_39", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091521436", 
          "https://doi.org/10.1007/978-3-319-67389-9_39"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2018-11-06", 
    "datePublishedReg": "2018-11-06", 
    "description": "Positron emission tomography (PET) imaging is an effective tool used in determining disease stage and lesion malignancy; however, radiation exposure to patients and technicians during PET scans continues to draw concern. One way to minimize radiation exposure is to reduce the dose of radioactive tracer administered in order to obtain the scan. Yet, low-dose images are inherently noisy and have poor image quality making them difficult to read. This paper proposes the use of a deep learning model that takes specific image features into account in the loss function to denoise low-dose PET image slices and estimate their full-dose image quality equivalent. Testing on low-dose image slices indicates a significant improvement in image quality that is comparable to the ground truth full\u2013dose image slices. Additionally, this approach can lower the cost of conducting a PET scan since less radioactive material is required per scan, which may promote the usage of PET scans for medical diagnosis.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s10278-018-0150-3", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1100894", 
        "issn": [
          "0897-1889", 
          "1618-727X"
        ], 
        "name": "Journal of Digital Imaging", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "5", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "32"
      }
    ], 
    "keywords": [
      "PET scans", 
      "radiation exposure", 
      "positron emission tomography (PET) imaging", 
      "emission tomography (PET) imaging", 
      "low-dose PET images", 
      "disease stage", 
      "low-dose images", 
      "tomography (PET) imaging", 
      "pilot study", 
      "scans", 
      "image slices", 
      "lesion malignancy", 
      "PET images", 
      "poor image quality", 
      "significant improvement", 
      "deep learning model", 
      "specific image features", 
      "slices", 
      "exposure", 
      "image quality", 
      "patients", 
      "image features", 
      "deep learning", 
      "malignancy", 
      "image estimation", 
      "dose", 
      "diagnosis", 
      "learning model", 
      "radioactive tracers", 
      "medical diagnosis", 
      "loss function", 
      "imaging", 
      "images", 
      "quality", 
      "study", 
      "technicians", 
      "improvement", 
      "effective tool", 
      "tracer", 
      "use", 
      "stage", 
      "function", 
      "concern", 
      "learning", 
      "usage", 
      "radioactive materials", 
      "features", 
      "equivalent", 
      "tool", 
      "estimation", 
      "cost", 
      "way", 
      "order", 
      "model", 
      "materials", 
      "approach", 
      "account", 
      "paper", 
      "low-dose PET image slices", 
      "PET image slices", 
      "full-dose image quality equivalent", 
      "image quality equivalent", 
      "quality equivalent", 
      "low-dose image slices", 
      "ground truth full\u2013dose image slices", 
      "truth full\u2013dose image slices", 
      "full\u2013dose image slices", 
      "Dose PET Image Estimation", 
      "PET Image Estimation"
    ], 
    "name": "Full-Dose PET Image Estimation from Low-Dose PET Image Using Deep Learning: a Pilot Study", 
    "pagination": "773-778", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1108058515"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s10278-018-0150-3"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "30402670"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s10278-018-0150-3", 
      "https://app.dimensions.ai/details/publication/pub.1108058515"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2021-11-01T18:33", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211101/entities/gbq_results/article/article_781.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s10278-018-0150-3"
  }
]
 

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/s10278-018-0150-3'

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/s10278-018-0150-3'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s10278-018-0150-3'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s10278-018-0150-3'


 

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

177 TRIPLES      22 PREDICATES      104 URIs      94 LITERALS      14 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s10278-018-0150-3 schema:about N479a3464dde24d2ea1da0b23026a4340
2 N56884091e11c4deaa83988a7c466238f
3 N607f77d507da47fa9d3555f425040798
4 N699294bcaa404c7aa177aa5d5859ec14
5 N98c882c603c04220bc5c0e4e83643fbb
6 N9a03e57091564b5596932295e48b3cf3
7 Na1ba22f467214372b2cbd99928e14589
8 anzsrc-for:11
9 anzsrc-for:1103
10 schema:author Nff0bc9c78d6347998b778ac6337e9ab9
11 schema:citation sg:pub.10.1007/978-3-319-67389-9_39
12 sg:pub.10.1007/s11227-017-2080-0
13 schema:datePublished 2018-11-06
14 schema:datePublishedReg 2018-11-06
15 schema:description Positron emission tomography (PET) imaging is an effective tool used in determining disease stage and lesion malignancy; however, radiation exposure to patients and technicians during PET scans continues to draw concern. One way to minimize radiation exposure is to reduce the dose of radioactive tracer administered in order to obtain the scan. Yet, low-dose images are inherently noisy and have poor image quality making them difficult to read. This paper proposes the use of a deep learning model that takes specific image features into account in the loss function to denoise low-dose PET image slices and estimate their full-dose image quality equivalent. Testing on low-dose image slices indicates a significant improvement in image quality that is comparable to the ground truth full–dose image slices. Additionally, this approach can lower the cost of conducting a PET scan since less radioactive material is required per scan, which may promote the usage of PET scans for medical diagnosis.
16 schema:genre article
17 schema:inLanguage en
18 schema:isAccessibleForFree true
19 schema:isPartOf N64162827f3dc422c8d4538cf7cdccf32
20 Nc7d0353c82964bfca6da03b4ea841838
21 sg:journal.1100894
22 schema:keywords Dose PET Image Estimation
23 PET Image Estimation
24 PET image slices
25 PET images
26 PET scans
27 account
28 approach
29 concern
30 cost
31 deep learning
32 deep learning model
33 diagnosis
34 disease stage
35 dose
36 effective tool
37 emission tomography (PET) imaging
38 equivalent
39 estimation
40 exposure
41 features
42 full-dose image quality equivalent
43 full–dose image slices
44 function
45 ground truth full–dose image slices
46 image estimation
47 image features
48 image quality
49 image quality equivalent
50 image slices
51 images
52 imaging
53 improvement
54 learning
55 learning model
56 lesion malignancy
57 loss function
58 low-dose PET image slices
59 low-dose PET images
60 low-dose image slices
61 low-dose images
62 malignancy
63 materials
64 medical diagnosis
65 model
66 order
67 paper
68 patients
69 pilot study
70 poor image quality
71 positron emission tomography (PET) imaging
72 quality
73 quality equivalent
74 radiation exposure
75 radioactive materials
76 radioactive tracers
77 scans
78 significant improvement
79 slices
80 specific image features
81 stage
82 study
83 technicians
84 tomography (PET) imaging
85 tool
86 tracer
87 truth full–dose image slices
88 usage
89 use
90 way
91 schema:name Full-Dose PET Image Estimation from Low-Dose PET Image Using Deep Learning: a Pilot Study
92 schema:pagination 773-778
93 schema:productId N4135e6a029e94f4d8eca824c5296c518
94 N90fe5c5cc39643c3853ea2353200089a
95 N94a51ebfb7fd4f8f9efe80ec8ac02786
96 schema:sameAs https://app.dimensions.ai/details/publication/pub.1108058515
97 https://doi.org/10.1007/s10278-018-0150-3
98 schema:sdDatePublished 2021-11-01T18:33
99 schema:sdLicense https://scigraph.springernature.com/explorer/license/
100 schema:sdPublisher Nc177e475bd5d4958930034238e85795b
101 schema:url https://doi.org/10.1007/s10278-018-0150-3
102 sgo:license sg:explorer/license/
103 sgo:sdDataset articles
104 rdf:type schema:ScholarlyArticle
105 N4135e6a029e94f4d8eca824c5296c518 schema:name dimensions_id
106 schema:value pub.1108058515
107 rdf:type schema:PropertyValue
108 N479a3464dde24d2ea1da0b23026a4340 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
109 schema:name Pilot Projects
110 rdf:type schema:DefinedTerm
111 N56884091e11c4deaa83988a7c466238f schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
112 schema:name Positron-Emission Tomography
113 rdf:type schema:DefinedTerm
114 N607f77d507da47fa9d3555f425040798 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
115 schema:name Deep Learning
116 rdf:type schema:DefinedTerm
117 N64162827f3dc422c8d4538cf7cdccf32 schema:volumeNumber 32
118 rdf:type schema:PublicationVolume
119 N699294bcaa404c7aa177aa5d5859ec14 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
120 schema:name Signal-To-Noise Ratio
121 rdf:type schema:DefinedTerm
122 N7c2044ce248b4235bbdadb8571c19085 rdf:first Nc241ac501d0946dfb39cce98c457dbf6
123 rdf:rest rdf:nil
124 N9019f64e98f04442b625a702519f5174 schema:affiliation grid-institutes:grid.4367.6
125 schema:familyName Kaplan
126 schema:givenName Sydney
127 rdf:type schema:Person
128 N90fe5c5cc39643c3853ea2353200089a schema:name pubmed_id
129 schema:value 30402670
130 rdf:type schema:PropertyValue
131 N94a51ebfb7fd4f8f9efe80ec8ac02786 schema:name doi
132 schema:value 10.1007/s10278-018-0150-3
133 rdf:type schema:PropertyValue
134 N98c882c603c04220bc5c0e4e83643fbb schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
135 schema:name Image Processing, Computer-Assisted
136 rdf:type schema:DefinedTerm
137 N9a03e57091564b5596932295e48b3cf3 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
138 schema:name Radiation Dosage
139 rdf:type schema:DefinedTerm
140 Na1ba22f467214372b2cbd99928e14589 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
141 schema:name Humans
142 rdf:type schema:DefinedTerm
143 Nc177e475bd5d4958930034238e85795b schema:name Springer Nature - SN SciGraph project
144 rdf:type schema:Organization
145 Nc241ac501d0946dfb39cce98c457dbf6 schema:affiliation grid-institutes:grid.415886.6
146 schema:familyName Zhu
147 schema:givenName Yang-Ming
148 rdf:type schema:Person
149 Nc7d0353c82964bfca6da03b4ea841838 schema:issueNumber 5
150 rdf:type schema:PublicationIssue
151 Nff0bc9c78d6347998b778ac6337e9ab9 rdf:first N9019f64e98f04442b625a702519f5174
152 rdf:rest N7c2044ce248b4235bbdadb8571c19085
153 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
154 schema:name Medical and Health Sciences
155 rdf:type schema:DefinedTerm
156 anzsrc-for:1103 schema:inDefinedTermSet anzsrc-for:
157 schema:name Clinical Sciences
158 rdf:type schema:DefinedTerm
159 sg:journal.1100894 schema:issn 0897-1889
160 1618-727X
161 schema:name Journal of Digital Imaging
162 schema:publisher Springer Nature
163 rdf:type schema:Periodical
164 sg:pub.10.1007/978-3-319-67389-9_39 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091521436
165 https://doi.org/10.1007/978-3-319-67389-9_39
166 rdf:type schema:CreativeWork
167 sg:pub.10.1007/s11227-017-2080-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085733860
168 https://doi.org/10.1007/s11227-017-2080-0
169 rdf:type schema:CreativeWork
170 grid-institutes:grid.415886.6 schema:alternateName Siemens Healthineers, 07836, Flanders, NJ, USA
171 schema:name Philips Healthcare, 44143, Highland Heights, OH, USA
172 Siemens Healthineers, 07836, Flanders, NJ, USA
173 rdf:type schema:Organization
174 grid-institutes:grid.4367.6 schema:alternateName Department of Neurology, Washington University School of Medicine, 63110, St. Louis, MO, USA
175 schema:name Department of Neurology, Washington University School of Medicine, 63110, St. Louis, MO, USA
176 Philips Healthcare, 44143, Highland Heights, OH, USA
177 rdf:type schema:Organization
 




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


...