Content-based image retrieval for the diagnosis of myocardial perfusion imaging using a deep convolutional autoencoder View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2022-07-08

AUTHORS

Akinori Higaki, Naoto Kawaguchi, Tsukasa Kurokawa, Hikaru Okabe, Takuro Kazatani, Shinsuke Kido, Tetsuya Aono, Kensho Matsuda, Yuta Tanaka, Saki Hosokawa, Tetsuya Kosaki, Go Kawamura, Tatsuya Shigematsu, Yoshitaka Kawada, Go Hiasa, Tadakatsu Yamada, Hideki Okayama

ABSTRACT

BackgroundSingle-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) plays a crucial role in the optimal treatment strategy for patients with coronary heart disease. We tested the feasibility of feature extraction from MPI using a deep convolutional autoencoder (CAE) model.MethodsEight hundred and forty-three pairs of stress and rest myocardial perfusion images were collected from consecutive patients who underwent cardiac scintigraphy in our hospital between December 2019 and February 2022. We trained a CAE model to reproduce the input paired image data, so as the encoder to output a 256-dimensional feature vector. The extracted feature vectors were further dimensionally reduced via principal component analysis (PCA) for data visualization. Content-based image retrieval (CBIR) was performed based on the cosine similarity of the feature vectors between the query and reference images. The agreement of the radiologist’s finding between the query and retrieved MPI was evaluated using binary accuracy, precision, recall, and F1-score.ResultsA three-dimensional scatter plot with PCA revealed that feature vectors retained clinical information such as percent summed difference score, presence of ischemia, and the location of scar reported by radiologists. When CBIR was used as a similarity-based diagnostic tool, the binary accuracy was 81.0%.ConclusionThe results indicated the utility of unsupervised feature learning for CBIR in MPI.Graphical abstract More... »

PAGES

1-10

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s12350-022-03030-4

DOI

http://dx.doi.org/10.1007/s12350-022-03030-4

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1149335055

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/35802346


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/2008/1102", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Cardiorespiratory Medicine and Haematology", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Pulmonology, Hypertension & Nephrology, Ehime University Graduate School of Medicine, Toon, Japan", 
          "id": "http://www.grid.ac/institutes/grid.255464.4", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
            "Department of Cardiology, Pulmonology, Hypertension & Nephrology, Ehime University Graduate School of Medicine, Toon, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Higaki", 
        "givenName": "Akinori", 
        "id": "sg:person.01042600153.05", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01042600153.05"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Radiology, Ehime University Graduate School of Medicine, Toon, Japan", 
          "id": "http://www.grid.ac/institutes/grid.255464.4", 
          "name": [
            "Department of Radiology, Ehime University Graduate School of Medicine, Toon, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kawaguchi", 
        "givenName": "Naoto", 
        "id": "sg:person.0610437474.42", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0610437474.42"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kurokawa", 
        "givenName": "Tsukasa", 
        "id": "sg:person.015204465003.34", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015204465003.34"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Okabe", 
        "givenName": "Hikaru", 
        "id": "sg:person.015161037101.52", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015161037101.52"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kazatani", 
        "givenName": "Takuro", 
        "id": "sg:person.010641135067.56", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010641135067.56"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kido", 
        "givenName": "Shinsuke", 
        "id": "sg:person.014177061074.15", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014177061074.15"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Aono", 
        "givenName": "Tetsuya", 
        "id": "sg:person.015725534474.19", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015725534474.19"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Matsuda", 
        "givenName": "Kensho", 
        "id": "sg:person.011051170771.94", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011051170771.94"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tanaka", 
        "givenName": "Yuta", 
        "id": "sg:person.010615424274.82", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010615424274.82"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hosokawa", 
        "givenName": "Saki", 
        "id": "sg:person.012444131771.76", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012444131771.76"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kosaki", 
        "givenName": "Tetsuya", 
        "id": "sg:person.013241512371.10", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013241512371.10"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kawamura", 
        "givenName": "Go", 
        "id": "sg:person.01311226437.84", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01311226437.84"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shigematsu", 
        "givenName": "Tatsuya", 
        "id": "sg:person.01357341637.24", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01357341637.24"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kawada", 
        "givenName": "Yoshitaka", 
        "id": "sg:person.016227414371.26", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016227414371.26"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hiasa", 
        "givenName": "Go", 
        "id": "sg:person.0736676361.71", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0736676361.71"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Yamada", 
        "givenName": "Tadakatsu", 
        "id": "sg:person.01200641137.43", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01200641137.43"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan", 
          "id": "http://www.grid.ac/institutes/grid.414413.7", 
          "name": [
            "Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Okayama", 
        "givenName": "Hideki", 
        "id": "sg:person.0633340041.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0633340041.46"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1038/nmeth.4346", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090282229", 
          "https://doi.org/10.1038/nmeth.4346"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s12350-010-9207-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041533672", 
          "https://doi.org/10.1007/s12350-010-9207-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10278-016-9904-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023116033", 
          "https://doi.org/10.1007/s10278-016-9904-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s12149-007-0059-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017307682", 
          "https://doi.org/10.1007/s12149-007-0059-2"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2022-07-08", 
    "datePublishedReg": "2022-07-08", 
    "description": "BackgroundSingle-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) plays a crucial role in the optimal treatment strategy for patients with coronary heart disease. We tested the feasibility of feature extraction from MPI using a deep convolutional autoencoder (CAE) model.MethodsEight hundred and forty-three pairs of stress and rest myocardial perfusion images were collected from consecutive patients who underwent cardiac scintigraphy in our hospital between December 2019 and February 2022. We trained a CAE model to reproduce the input paired image data, so as the encoder to output a 256-dimensional feature vector. The extracted feature vectors were further dimensionally reduced via principal component analysis (PCA) for data visualization. Content-based image retrieval (CBIR) was performed based on the cosine similarity of the feature vectors between the query and reference images. The agreement of the radiologist\u2019s finding between the query and retrieved MPI was evaluated using binary accuracy, precision, recall, and F1-score.ResultsA three-dimensional scatter plot with PCA revealed that feature vectors retained clinical information such as percent summed difference score, presence of ischemia, and the location of scar reported by radiologists. When CBIR was used as a similarity-based diagnostic tool, the binary accuracy was 81.0%.ConclusionThe results indicated the utility of unsupervised feature learning for CBIR in MPI.Graphical abstract", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s12350-022-03030-4", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1106202", 
        "issn": [
          "1071-3581", 
          "1532-6551"
        ], 
        "name": "Journal of Nuclear Cardiology", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }
    ], 
    "keywords": [
      "content-based image retrieval", 
      "feature vectors", 
      "image retrieval", 
      "binary accuracy", 
      "deep convolutional autoencoder", 
      "convolutional autoencoder model", 
      "unsupervised feature", 
      "convolutional autoencoder", 
      "feature extraction", 
      "data visualization", 
      "autoencoder model", 
      "image data", 
      "cosine similarity", 
      "reference image", 
      "three-dimensional scatter plot", 
      "queries", 
      "myocardial perfusion imaging", 
      "CAE model", 
      "principal component analysis", 
      "retrieval", 
      "abstract content", 
      "images", 
      "autoencoder", 
      "accuracy", 
      "tomography myocardial perfusion imaging", 
      "encoder", 
      "BackgroundSingle photon emission", 
      "optimal treatment strategy", 
      "coronary heart disease", 
      "presence of ischemia", 
      "component analysis", 
      "vector", 
      "visualization", 
      "MethodsEight hundred", 
      "consecutive patients", 
      "heart disease", 
      "cardiac scintigraphy", 
      "treatment strategies", 
      "myocardial perfusion images", 
      "clinical information", 
      "myocardial perfusion", 
      "perfusion imaging", 
      "radiologists' findings", 
      "scatter plots", 
      "information", 
      "recall", 
      "perfusion images", 
      "model", 
      "tool", 
      "patients", 
      "extraction", 
      "input", 
      "location of scar", 
      "diagnostic tool", 
      "precision", 
      "pairs of stress", 
      "features", 
      "difference scores", 
      "feasibility", 
      "hundreds", 
      "scintigraphy", 
      "ischemia", 
      "data", 
      "similarity", 
      "radiologists", 
      "hospital", 
      "perfusion", 
      "disease", 
      "findings", 
      "diagnosis", 
      "location", 
      "utility", 
      "scar", 
      "crucial role", 
      "scores", 
      "strategies", 
      "imaging", 
      "percent", 
      "results", 
      "pairs", 
      "role", 
      "content", 
      "analysis", 
      "presence", 
      "stress", 
      "agreement", 
      "plots", 
      "emission"
    ], 
    "name": "Content-based image retrieval for the diagnosis of myocardial perfusion imaging using a deep convolutional autoencoder", 
    "pagination": "1-10", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1149335055"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s12350-022-03030-4"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "35802346"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s12350-022-03030-4", 
      "https://app.dimensions.ai/details/publication/pub.1149335055"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-09-02T16:07", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220902/entities/gbq_results/article/article_938.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s12350-022-03030-4"
  }
]
 

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/s12350-022-03030-4'

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/s12350-022-03030-4'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s12350-022-03030-4'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s12350-022-03030-4'


 

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

277 TRIPLES      21 PREDICATES      115 URIs      103 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s12350-022-03030-4 schema:about anzsrc-for:11
2 anzsrc-for:1102
3 schema:author Nd52f53c5971b4b6aa5cc8b93cd80b956
4 schema:citation sg:pub.10.1007/s10278-016-9904-y
5 sg:pub.10.1007/s12149-007-0059-2
6 sg:pub.10.1007/s12350-010-9207-5
7 sg:pub.10.1038/nmeth.4346
8 schema:datePublished 2022-07-08
9 schema:datePublishedReg 2022-07-08
10 schema:description BackgroundSingle-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) plays a crucial role in the optimal treatment strategy for patients with coronary heart disease. We tested the feasibility of feature extraction from MPI using a deep convolutional autoencoder (CAE) model.MethodsEight hundred and forty-three pairs of stress and rest myocardial perfusion images were collected from consecutive patients who underwent cardiac scintigraphy in our hospital between December 2019 and February 2022. We trained a CAE model to reproduce the input paired image data, so as the encoder to output a 256-dimensional feature vector. The extracted feature vectors were further dimensionally reduced via principal component analysis (PCA) for data visualization. Content-based image retrieval (CBIR) was performed based on the cosine similarity of the feature vectors between the query and reference images. The agreement of the radiologist’s finding between the query and retrieved MPI was evaluated using binary accuracy, precision, recall, and F1-score.ResultsA three-dimensional scatter plot with PCA revealed that feature vectors retained clinical information such as percent summed difference score, presence of ischemia, and the location of scar reported by radiologists. When CBIR was used as a similarity-based diagnostic tool, the binary accuracy was 81.0%.ConclusionThe results indicated the utility of unsupervised feature learning for CBIR in MPI.Graphical abstract
11 schema:genre article
12 schema:isAccessibleForFree false
13 schema:isPartOf sg:journal.1106202
14 schema:keywords BackgroundSingle photon emission
15 CAE model
16 MethodsEight hundred
17 abstract content
18 accuracy
19 agreement
20 analysis
21 autoencoder
22 autoencoder model
23 binary accuracy
24 cardiac scintigraphy
25 clinical information
26 component analysis
27 consecutive patients
28 content
29 content-based image retrieval
30 convolutional autoencoder
31 convolutional autoencoder model
32 coronary heart disease
33 cosine similarity
34 crucial role
35 data
36 data visualization
37 deep convolutional autoencoder
38 diagnosis
39 diagnostic tool
40 difference scores
41 disease
42 emission
43 encoder
44 extraction
45 feasibility
46 feature extraction
47 feature vectors
48 features
49 findings
50 heart disease
51 hospital
52 hundreds
53 image data
54 image retrieval
55 images
56 imaging
57 information
58 input
59 ischemia
60 location
61 location of scar
62 model
63 myocardial perfusion
64 myocardial perfusion images
65 myocardial perfusion imaging
66 optimal treatment strategy
67 pairs
68 pairs of stress
69 patients
70 percent
71 perfusion
72 perfusion images
73 perfusion imaging
74 plots
75 precision
76 presence
77 presence of ischemia
78 principal component analysis
79 queries
80 radiologists
81 radiologists' findings
82 recall
83 reference image
84 results
85 retrieval
86 role
87 scar
88 scatter plots
89 scintigraphy
90 scores
91 similarity
92 strategies
93 stress
94 three-dimensional scatter plot
95 tomography myocardial perfusion imaging
96 tool
97 treatment strategies
98 unsupervised feature
99 utility
100 vector
101 visualization
102 schema:name Content-based image retrieval for the diagnosis of myocardial perfusion imaging using a deep convolutional autoencoder
103 schema:pagination 1-10
104 schema:productId N990f5d28f8d54f5d8284bf3bf11a05db
105 Nc3958ec2607c4b3fa8813449350e5f6d
106 Ne65baa74b55242d783a267214c6babbc
107 schema:sameAs https://app.dimensions.ai/details/publication/pub.1149335055
108 https://doi.org/10.1007/s12350-022-03030-4
109 schema:sdDatePublished 2022-09-02T16:07
110 schema:sdLicense https://scigraph.springernature.com/explorer/license/
111 schema:sdPublisher N769722d36cee4f7cb39d0f4d2315bf0a
112 schema:url https://doi.org/10.1007/s12350-022-03030-4
113 sgo:license sg:explorer/license/
114 sgo:sdDataset articles
115 rdf:type schema:ScholarlyArticle
116 N0903f8108dab4474b82c982bdcb877c0 rdf:first sg:person.010641135067.56
117 rdf:rest N9935fa0ed0e040719f9360903f7abdde
118 N185cdbb5914847c78d87c001dfc081c4 rdf:first sg:person.012444131771.76
119 rdf:rest N23eff60b926f47189f52ee4b11a31163
120 N1862d87b3e9149c8817ed8ccba1917ea rdf:first sg:person.01311226437.84
121 rdf:rest N1af38a77fe67418096d4e229c7c1066e
122 N1af38a77fe67418096d4e229c7c1066e rdf:first sg:person.01357341637.24
123 rdf:rest Nb6717aae06bb40a787ca60ba7fb0e691
124 N23eff60b926f47189f52ee4b11a31163 rdf:first sg:person.013241512371.10
125 rdf:rest N1862d87b3e9149c8817ed8ccba1917ea
126 N734512df74ea4490b37eea277119d27c rdf:first sg:person.015725534474.19
127 rdf:rest Ne8dcb04f0e9646b5ac85e9ab77b72480
128 N769722d36cee4f7cb39d0f4d2315bf0a schema:name Springer Nature - SN SciGraph project
129 rdf:type schema:Organization
130 N7751702883374d79ad3dc698a7bdf4c7 rdf:first sg:person.015161037101.52
131 rdf:rest N0903f8108dab4474b82c982bdcb877c0
132 N837197e1fb8f4a3e8ee02f20f84742d4 rdf:first sg:person.0736676361.71
133 rdf:rest N94e70f4805c4405d8a40ae1c057d377e
134 N94e70f4805c4405d8a40ae1c057d377e rdf:first sg:person.01200641137.43
135 rdf:rest Nb5a1562270f94e8f959e2fbdabeb6635
136 N990f5d28f8d54f5d8284bf3bf11a05db schema:name dimensions_id
137 schema:value pub.1149335055
138 rdf:type schema:PropertyValue
139 N9935fa0ed0e040719f9360903f7abdde rdf:first sg:person.014177061074.15
140 rdf:rest N734512df74ea4490b37eea277119d27c
141 Naeb0095a09ca4f8792b38f69a5015e74 rdf:first sg:person.015204465003.34
142 rdf:rest N7751702883374d79ad3dc698a7bdf4c7
143 Nb5a1562270f94e8f959e2fbdabeb6635 rdf:first sg:person.0633340041.46
144 rdf:rest rdf:nil
145 Nb6717aae06bb40a787ca60ba7fb0e691 rdf:first sg:person.016227414371.26
146 rdf:rest N837197e1fb8f4a3e8ee02f20f84742d4
147 Nc0ef5e76562f49339de6da594a78cf93 rdf:first sg:person.0610437474.42
148 rdf:rest Naeb0095a09ca4f8792b38f69a5015e74
149 Nc3958ec2607c4b3fa8813449350e5f6d schema:name pubmed_id
150 schema:value 35802346
151 rdf:type schema:PropertyValue
152 Ncbc42156b4104c558df55483235664d7 rdf:first sg:person.010615424274.82
153 rdf:rest N185cdbb5914847c78d87c001dfc081c4
154 Nd52f53c5971b4b6aa5cc8b93cd80b956 rdf:first sg:person.01042600153.05
155 rdf:rest Nc0ef5e76562f49339de6da594a78cf93
156 Ne65baa74b55242d783a267214c6babbc schema:name doi
157 schema:value 10.1007/s12350-022-03030-4
158 rdf:type schema:PropertyValue
159 Ne8dcb04f0e9646b5ac85e9ab77b72480 rdf:first sg:person.011051170771.94
160 rdf:rest Ncbc42156b4104c558df55483235664d7
161 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
162 schema:name Medical and Health Sciences
163 rdf:type schema:DefinedTerm
164 anzsrc-for:1102 schema:inDefinedTermSet anzsrc-for:
165 schema:name Cardiorespiratory Medicine and Haematology
166 rdf:type schema:DefinedTerm
167 sg:journal.1106202 schema:issn 1071-3581
168 1532-6551
169 schema:name Journal of Nuclear Cardiology
170 schema:publisher Springer Nature
171 rdf:type schema:Periodical
172 sg:person.01042600153.05 schema:affiliation grid-institutes:grid.255464.4
173 schema:familyName Higaki
174 schema:givenName Akinori
175 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01042600153.05
176 rdf:type schema:Person
177 sg:person.010615424274.82 schema:affiliation grid-institutes:grid.414413.7
178 schema:familyName Tanaka
179 schema:givenName Yuta
180 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010615424274.82
181 rdf:type schema:Person
182 sg:person.010641135067.56 schema:affiliation grid-institutes:grid.414413.7
183 schema:familyName Kazatani
184 schema:givenName Takuro
185 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010641135067.56
186 rdf:type schema:Person
187 sg:person.011051170771.94 schema:affiliation grid-institutes:grid.414413.7
188 schema:familyName Matsuda
189 schema:givenName Kensho
190 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011051170771.94
191 rdf:type schema:Person
192 sg:person.01200641137.43 schema:affiliation grid-institutes:grid.414413.7
193 schema:familyName Yamada
194 schema:givenName Tadakatsu
195 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01200641137.43
196 rdf:type schema:Person
197 sg:person.012444131771.76 schema:affiliation grid-institutes:grid.414413.7
198 schema:familyName Hosokawa
199 schema:givenName Saki
200 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012444131771.76
201 rdf:type schema:Person
202 sg:person.01311226437.84 schema:affiliation grid-institutes:grid.414413.7
203 schema:familyName Kawamura
204 schema:givenName Go
205 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01311226437.84
206 rdf:type schema:Person
207 sg:person.013241512371.10 schema:affiliation grid-institutes:grid.414413.7
208 schema:familyName Kosaki
209 schema:givenName Tetsuya
210 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013241512371.10
211 rdf:type schema:Person
212 sg:person.01357341637.24 schema:affiliation grid-institutes:grid.414413.7
213 schema:familyName Shigematsu
214 schema:givenName Tatsuya
215 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01357341637.24
216 rdf:type schema:Person
217 sg:person.014177061074.15 schema:affiliation grid-institutes:grid.414413.7
218 schema:familyName Kido
219 schema:givenName Shinsuke
220 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014177061074.15
221 rdf:type schema:Person
222 sg:person.015161037101.52 schema:affiliation grid-institutes:grid.414413.7
223 schema:familyName Okabe
224 schema:givenName Hikaru
225 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015161037101.52
226 rdf:type schema:Person
227 sg:person.015204465003.34 schema:affiliation grid-institutes:grid.414413.7
228 schema:familyName Kurokawa
229 schema:givenName Tsukasa
230 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015204465003.34
231 rdf:type schema:Person
232 sg:person.015725534474.19 schema:affiliation grid-institutes:grid.414413.7
233 schema:familyName Aono
234 schema:givenName Tetsuya
235 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015725534474.19
236 rdf:type schema:Person
237 sg:person.016227414371.26 schema:affiliation grid-institutes:grid.414413.7
238 schema:familyName Kawada
239 schema:givenName Yoshitaka
240 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016227414371.26
241 rdf:type schema:Person
242 sg:person.0610437474.42 schema:affiliation grid-institutes:grid.255464.4
243 schema:familyName Kawaguchi
244 schema:givenName Naoto
245 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0610437474.42
246 rdf:type schema:Person
247 sg:person.0633340041.46 schema:affiliation grid-institutes:grid.414413.7
248 schema:familyName Okayama
249 schema:givenName Hideki
250 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0633340041.46
251 rdf:type schema:Person
252 sg:person.0736676361.71 schema:affiliation grid-institutes:grid.414413.7
253 schema:familyName Hiasa
254 schema:givenName Go
255 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0736676361.71
256 rdf:type schema:Person
257 sg:pub.10.1007/s10278-016-9904-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1023116033
258 https://doi.org/10.1007/s10278-016-9904-y
259 rdf:type schema:CreativeWork
260 sg:pub.10.1007/s12149-007-0059-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017307682
261 https://doi.org/10.1007/s12149-007-0059-2
262 rdf:type schema:CreativeWork
263 sg:pub.10.1007/s12350-010-9207-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041533672
264 https://doi.org/10.1007/s12350-010-9207-5
265 rdf:type schema:CreativeWork
266 sg:pub.10.1038/nmeth.4346 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090282229
267 https://doi.org/10.1038/nmeth.4346
268 rdf:type schema:CreativeWork
269 grid-institutes:grid.255464.4 schema:alternateName Department of Cardiology, Pulmonology, Hypertension & Nephrology, Ehime University Graduate School of Medicine, Toon, Japan
270 Department of Radiology, Ehime University Graduate School of Medicine, Toon, Japan
271 schema:name Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan
272 Department of Cardiology, Pulmonology, Hypertension & Nephrology, Ehime University Graduate School of Medicine, Toon, Japan
273 Department of Radiology, Ehime University Graduate School of Medicine, Toon, Japan
274 rdf:type schema:Organization
275 grid-institutes:grid.414413.7 schema:alternateName Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan
276 schema:name Department of Cardiology, Ehime Prefectural Central Hospital, 83, Kasuga-machi, 790-0024, Matsuyama, Japan
277 rdf:type schema:Organization
 




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


...