Automatic segmentation and classification of breast lesions through identification of informative multiparametric PET/MRI features View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2019-04-27

AUTHORS

Wolf-Dieter Vogl, Katja Pinker, Thomas H. Helbich, Hubert Bickel, Günther Grabner, Wolfgang Bogner, Stephan Gruber, Zsuzsanna Bago-Horvath, Peter Dubsky, Georg Langs

ABSTRACT

BackgroundMultiparametric positron emission tomography/magnetic resonance imaging (mpPET/MRI) shows clinical potential for detection and classification of breast lesions. Yet, the contribution of features for computer-aided segmentation and diagnosis (CAD) need to be better understood. We proposed a data-driven machine learning approach for a CAD system combining dynamic contrast-enhanced (DCE)-MRI, diffusion-weighted imaging (DWI), and 18F-fluorodeoxyglucose (18F-FDG)-PET.MethodsThe CAD incorporated a random forest (RF) classifier combined with mpPET/MRI intensity-based features for lesion segmentation and shape features, kinetic and spatio-temporal texture features, for lesion classification. The CAD pipeline detected and segmented suspicious regions and classified lesions as benign or malignant. The inherent feature selection method of RF and alternatively the minimum-redundancy-maximum-relevance feature ranking method were used.ResultsIn 34 patients, we report a detection rate of 10/12 (83.3%) and 22/22 (100%) for benign and malignant lesions, respectively, a Dice similarity coefficient of 0.665 for segmentation, and a classification performance with an area under the curve at receiver operating characteristics analysis of 0.978, a sensitivity of 0.946, and a specificity of 0.936. Segmentation but not classification performance of DCE-MRI improved with information from DWI and FDG-PET. Feature ranking revealed that kinetic and spatio-temporal texture features had the highest contribution for lesion classification. 18F-FDG-PET and morphologic features were less predictive.ConclusionOur CAD enables the assessment of the relevance of mpPET/MRI features on segmentation and classification accuracy. It may aid as a novel computational tool for exploring different modalities/features and their contributions for the detection and classification of breast lesions. More... »

PAGES

18

Journal

TITLE

European Radiology Experimental

ISSUE

1

VOLUME

3

Identifiers

URI

http://scigraph.springernature.com/pub.10.1186/s41747-019-0096-3

DOI

http://dx.doi.org/10.1186/s41747-019-0096-3

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1113789081

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/31030291


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Adult", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Aged", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Breast Diseases", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Breast Neoplasms", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Contrast Media", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Diffusion Magnetic Resonance Imaging", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Female", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Fluorodeoxyglucose F18", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Humans", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Image Interpretation, Computer-Assisted", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Machine Learning", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Middle Aged", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Multimodal Imaging", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Multiparametric Magnetic Resonance Imaging", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Positron-Emission Tomography", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Radiopharmaceuticals", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Retrospective Studies", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Young Adult", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Computational Imaging Research Laboratory, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, Waehringer Guertel 18-20, 1090, Vienna, Austria", 
          "id": "http://www.grid.ac/institutes/grid.22937.3d", 
          "name": [
            "Computational Imaging Research Laboratory, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, Waehringer Guertel 18-20, 1090, Vienna, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Vogl", 
        "givenName": "Wolf-Dieter", 
        "id": "sg:person.0715016652.61", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0715016652.61"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 10065, New York, NY, USA", 
          "id": "http://www.grid.ac/institutes/grid.51462.34", 
          "name": [
            "Division of Molecular and Gender Imaging, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria", 
            "Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 10065, New York, NY, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Pinker", 
        "givenName": "Katja", 
        "id": "sg:person.0771356426.64", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0771356426.64"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Division of Molecular and Gender Imaging, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria", 
          "id": "http://www.grid.ac/institutes/grid.22937.3d", 
          "name": [
            "Division of Molecular and Gender Imaging, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Helbich", 
        "givenName": "Thomas H.", 
        "id": "sg:person.01027401416.56", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01027401416.56"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Division of Molecular and Gender Imaging, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria", 
          "id": "http://www.grid.ac/institutes/grid.22937.3d", 
          "name": [
            "Division of Molecular and Gender Imaging, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bickel", 
        "givenName": "Hubert", 
        "id": "sg:person.0714164140.30", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0714164140.30"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Radiologic Technology, Carinthia University of Applied Sciences, Klagenfurt, Austria", 
          "id": "http://www.grid.ac/institutes/grid.452087.c", 
          "name": [
            "MR Center of Excellence, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria", 
            "Department of Radiologic Technology, Carinthia University of Applied Sciences, Klagenfurt, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Grabner", 
        "givenName": "G\u00fcnther", 
        "id": "sg:person.0722520562.29", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0722520562.29"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "MR Center of Excellence, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria", 
          "id": "http://www.grid.ac/institutes/grid.22937.3d", 
          "name": [
            "MR Center of Excellence, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bogner", 
        "givenName": "Wolfgang", 
        "id": "sg:person.01105605026.77", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01105605026.77"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "MR Center of Excellence, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria", 
          "id": "http://www.grid.ac/institutes/grid.22937.3d", 
          "name": [
            "MR Center of Excellence, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Gruber", 
        "givenName": "Stephan", 
        "id": "sg:person.015234132112.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015234132112.37"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Pathology, Medical University Vienna, 1090, Vienna, Austria", 
          "id": "http://www.grid.ac/institutes/grid.22937.3d", 
          "name": [
            "Department of Pathology, Medical University Vienna, 1090, Vienna, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bago-Horvath", 
        "givenName": "Zsuzsanna", 
        "id": "sg:person.01206226414.12", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01206226414.12"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Surgery, Medical University Vienna, 1090, Vienna, Austria", 
          "id": "http://www.grid.ac/institutes/grid.22937.3d", 
          "name": [
            "Department of Surgery, Medical University Vienna, 1090, Vienna, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Dubsky", 
        "givenName": "Peter", 
        "id": "sg:person.01223341413.62", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01223341413.62"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computational Imaging Research Laboratory, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, Waehringer Guertel 18-20, 1090, Vienna, Austria", 
          "id": "http://www.grid.ac/institutes/grid.22937.3d", 
          "name": [
            "Computational Imaging Research Laboratory, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, Waehringer Guertel 18-20, 1090, Vienna, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Langs", 
        "givenName": "Georg", 
        "id": "sg:person.01044337625.58", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01044337625.58"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s10278-010-9298-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019988831", 
          "https://doi.org/10.1007/s10278-010-9298-1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-22092-0_21", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053314260", 
          "https://doi.org/10.1007/978-3-642-22092-0_21"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1471-2105-10-213", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002419282", 
          "https://doi.org/10.1186/1471-2105-10-213"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00330-011-2256-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033280588", 
          "https://doi.org/10.1007/s00330-011-2256-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00259-015-3099-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005135283", 
          "https://doi.org/10.1007/s00259-015-3099-1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00330-004-2280-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036861287", 
          "https://doi.org/10.1007/s00330-004-2280-x"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1010933404324", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024739340", 
          "https://doi.org/10.1023/a:1010933404324"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-04-27", 
    "datePublishedReg": "2019-04-27", 
    "description": "BackgroundMultiparametric positron emission tomography/magnetic resonance imaging (mpPET/MRI) shows clinical potential for detection and classification of breast lesions. Yet, the contribution of features for computer-aided segmentation and diagnosis (CAD) need to be better understood. We proposed a data-driven machine learning approach for a CAD system combining dynamic contrast-enhanced (DCE)-MRI, diffusion-weighted imaging (DWI), and 18F-fluorodeoxyglucose (18F-FDG)-PET.MethodsThe CAD incorporated a random forest (RF) classifier combined with mpPET/MRI intensity-based features for lesion segmentation and shape features, kinetic and spatio-temporal texture features, for lesion classification. The CAD pipeline detected and segmented suspicious regions and classified lesions as benign or malignant. The inherent feature selection method of RF and alternatively the minimum-redundancy-maximum-relevance feature ranking method were used.ResultsIn 34 patients, we report a detection rate of 10/12 (83.3%) and 22/22 (100%) for benign and malignant lesions, respectively, a Dice similarity coefficient of 0.665 for segmentation, and a classification performance with an area under the curve at receiver operating characteristics analysis of 0.978, a sensitivity of 0.946, and a specificity of 0.936. Segmentation but not classification performance of DCE-MRI improved with information from DWI and FDG-PET. Feature ranking revealed that kinetic and spatio-temporal texture features had the highest contribution for lesion classification. 18F-FDG-PET and morphologic features were less predictive.ConclusionOur CAD enables the assessment of the relevance of mpPET/MRI features on segmentation and classification accuracy. It may aid as a novel computational tool for exploring different modalities/features and their contributions for the detection and classification of breast lesions.", 
    "genre": "article", 
    "id": "sg:pub.10.1186/s41747-019-0096-3", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isFundedItemOf": [
      {
        "id": "sg:grant.6206445", 
        "type": "MonetaryGrant"
      }, 
      {
        "id": "sg:grant.5050587", 
        "type": "MonetaryGrant"
      }, 
      {
        "id": "sg:grant.2438793", 
        "type": "MonetaryGrant"
      }
    ], 
    "isPartOf": [
      {
        "id": "sg:journal.1290418", 
        "issn": [
          "2509-9280"
        ], 
        "name": "European Radiology Experimental", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "3"
      }
    ], 
    "keywords": [
      "texture features", 
      "classification performance", 
      "lesion classification", 
      "data-driven machine", 
      "intensity-based features", 
      "feature selection method", 
      "contribution of features", 
      "feature ranking methods", 
      "Computer-aided segmentation", 
      "random forest classifier", 
      "Dice similarity coefficient", 
      "CAD pipeline", 
      "automatic segmentation", 
      "feature ranking", 
      "lesion segmentation", 
      "CAD system", 
      "classification accuracy", 
      "shape features", 
      "suspicious regions", 
      "forest classifier", 
      "segmentation", 
      "novel computational tool", 
      "selection method", 
      "ranking method", 
      "computational tools", 
      "similarity coefficient", 
      "classification", 
      "detection rate", 
      "multiparametric PET/MRI", 
      "classifier", 
      "CAD", 
      "features", 
      "machine", 
      "performance", 
      "detection", 
      "pipeline", 
      "accuracy", 
      "information", 
      "ranking", 
      "tool", 
      "DCE-MRI", 
      "method", 
      "system", 
      "breast lesions", 
      "PET/MRI", 
      "receiver", 
      "contribution", 
      "identification", 
      "RF", 
      "imaging", 
      "area", 
      "MRI", 
      "characteristic analysis", 
      "magnetic resonance imaging", 
      "relevance", 
      "analysis", 
      "resonance imaging", 
      "diffusion-weighted imaging", 
      "assessment", 
      "PET", 
      "potential", 
      "coefficient", 
      "tomography/magnetic resonance imaging", 
      "positron emission tomography/magnetic resonance imaging", 
      "curves", 
      "rate", 
      "diagnosis", 
      "FDG-PET", 
      "malignant lesions", 
      "lesions", 
      "morphologic features", 
      "region", 
      "clinical potential", 
      "specificity", 
      "sensitivity", 
      "patients", 
      "highest contribution", 
      "approach"
    ], 
    "name": "Automatic segmentation and classification of breast lesions through identification of informative multiparametric PET/MRI features", 
    "pagination": "18", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1113789081"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1186/s41747-019-0096-3"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "31030291"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1186/s41747-019-0096-3", 
      "https://app.dimensions.ai/details/publication/pub.1113789081"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-05-20T07:36", 
    "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_817.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1186/s41747-019-0096-3"
  }
]
 

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.10.1186/s41747-019-0096-3'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s41747-019-0096-3'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s41747-019-0096-3'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s41747-019-0096-3'


 

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

324 TRIPLES      22 PREDICATES      129 URIs      114 LITERALS      25 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1186/s41747-019-0096-3 schema:about N03ea6e2a1b90406a8628571fd293bb1c
2 N08a0a9b921cc44fea49ea470080435db
3 N1762f3e9586e4bb6b3aa7f839edad0eb
4 N27fb3b20e3544e34984a929dccc8ac21
5 N39bea2b6f341485c869fbb9264280d3a
6 N4aed605a25eb4d1d9d6124bad8e6ab57
7 N60b8a718d5314f6093db03515ee04dad
8 N80960b9c56ff4d708b819aacd626e025
9 N85a164c58c434ceaa447b9f753590f92
10 N8e5bbdc0215141d18725cdc2d4031ab2
11 N92964009ad66470da14231bb75e1a0cf
12 Nb1103265eda745fcbfbbbc56cb6c96df
13 Nbd67c1ed3fab45f5a9dace0eb756f01a
14 Nc86e51d49a7746fcac10511b9a19eea7
15 Ndbc54901bc5447e4aac214f15e5a0074
16 Ne3cd0548e6964b249b19d828cf59075d
17 Nfb4ca35257ba4fd484de836636769240
18 Nffdabd969c934f3ea23da642950a2c83
19 anzsrc-for:08
20 anzsrc-for:0801
21 schema:author Nf0adc6e1f3354ac3be0c6632b939f344
22 schema:citation sg:pub.10.1007/978-3-642-22092-0_21
23 sg:pub.10.1007/s00259-015-3099-1
24 sg:pub.10.1007/s00330-004-2280-x
25 sg:pub.10.1007/s00330-011-2256-6
26 sg:pub.10.1007/s10278-010-9298-1
27 sg:pub.10.1023/a:1010933404324
28 sg:pub.10.1186/1471-2105-10-213
29 schema:datePublished 2019-04-27
30 schema:datePublishedReg 2019-04-27
31 schema:description BackgroundMultiparametric positron emission tomography/magnetic resonance imaging (mpPET/MRI) shows clinical potential for detection and classification of breast lesions. Yet, the contribution of features for computer-aided segmentation and diagnosis (CAD) need to be better understood. We proposed a data-driven machine learning approach for a CAD system combining dynamic contrast-enhanced (DCE)-MRI, diffusion-weighted imaging (DWI), and 18F-fluorodeoxyglucose (18F-FDG)-PET.MethodsThe CAD incorporated a random forest (RF) classifier combined with mpPET/MRI intensity-based features for lesion segmentation and shape features, kinetic and spatio-temporal texture features, for lesion classification. The CAD pipeline detected and segmented suspicious regions and classified lesions as benign or malignant. The inherent feature selection method of RF and alternatively the minimum-redundancy-maximum-relevance feature ranking method were used.ResultsIn 34 patients, we report a detection rate of 10/12 (83.3%) and 22/22 (100%) for benign and malignant lesions, respectively, a Dice similarity coefficient of 0.665 for segmentation, and a classification performance with an area under the curve at receiver operating characteristics analysis of 0.978, a sensitivity of 0.946, and a specificity of 0.936. Segmentation but not classification performance of DCE-MRI improved with information from DWI and FDG-PET. Feature ranking revealed that kinetic and spatio-temporal texture features had the highest contribution for lesion classification. 18F-FDG-PET and morphologic features were less predictive.ConclusionOur CAD enables the assessment of the relevance of mpPET/MRI features on segmentation and classification accuracy. It may aid as a novel computational tool for exploring different modalities/features and their contributions for the detection and classification of breast lesions.
32 schema:genre article
33 schema:inLanguage en
34 schema:isAccessibleForFree true
35 schema:isPartOf N04e9d2eaec464aaebae1e31a92c2178f
36 N884b32efc3c34373b7100094577ecbed
37 sg:journal.1290418
38 schema:keywords CAD
39 CAD pipeline
40 CAD system
41 Computer-aided segmentation
42 DCE-MRI
43 Dice similarity coefficient
44 FDG-PET
45 MRI
46 PET
47 PET/MRI
48 RF
49 accuracy
50 analysis
51 approach
52 area
53 assessment
54 automatic segmentation
55 breast lesions
56 characteristic analysis
57 classification
58 classification accuracy
59 classification performance
60 classifier
61 clinical potential
62 coefficient
63 computational tools
64 contribution
65 contribution of features
66 curves
67 data-driven machine
68 detection
69 detection rate
70 diagnosis
71 diffusion-weighted imaging
72 feature ranking
73 feature ranking methods
74 feature selection method
75 features
76 forest classifier
77 highest contribution
78 identification
79 imaging
80 information
81 intensity-based features
82 lesion classification
83 lesion segmentation
84 lesions
85 machine
86 magnetic resonance imaging
87 malignant lesions
88 method
89 morphologic features
90 multiparametric PET/MRI
91 novel computational tool
92 patients
93 performance
94 pipeline
95 positron emission tomography/magnetic resonance imaging
96 potential
97 random forest classifier
98 ranking
99 ranking method
100 rate
101 receiver
102 region
103 relevance
104 resonance imaging
105 segmentation
106 selection method
107 sensitivity
108 shape features
109 similarity coefficient
110 specificity
111 suspicious regions
112 system
113 texture features
114 tomography/magnetic resonance imaging
115 tool
116 schema:name Automatic segmentation and classification of breast lesions through identification of informative multiparametric PET/MRI features
117 schema:pagination 18
118 schema:productId N5a24e631f5f54f5bb9f4cb86edd05286
119 N5f44740cd1824c38b8dfde1b0c0eab71
120 Nd635ceb60690486daefd7db04c4fc900
121 schema:sameAs https://app.dimensions.ai/details/publication/pub.1113789081
122 https://doi.org/10.1186/s41747-019-0096-3
123 schema:sdDatePublished 2022-05-20T07:36
124 schema:sdLicense https://scigraph.springernature.com/explorer/license/
125 schema:sdPublisher Ncfbf358ef58e4980a88d9ed3e4a709d0
126 schema:url https://doi.org/10.1186/s41747-019-0096-3
127 sgo:license sg:explorer/license/
128 sgo:sdDataset articles
129 rdf:type schema:ScholarlyArticle
130 N03208c20a28f467fa68b05052900fa0f rdf:first sg:person.01223341413.62
131 rdf:rest Nfd8467d02fd24bd788a945f508eeecb2
132 N03ea6e2a1b90406a8628571fd293bb1c schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
133 schema:name Image Interpretation, Computer-Assisted
134 rdf:type schema:DefinedTerm
135 N04e9d2eaec464aaebae1e31a92c2178f schema:issueNumber 1
136 rdf:type schema:PublicationIssue
137 N05383fafca394820aa1e2e8a8e502170 rdf:first sg:person.015234132112.37
138 rdf:rest N514f5d1418324b13a6e90828ca9fa7d3
139 N08a0a9b921cc44fea49ea470080435db schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
140 schema:name Machine Learning
141 rdf:type schema:DefinedTerm
142 N0d869cbc71924988845c3fa6d4085967 rdf:first sg:person.01105605026.77
143 rdf:rest N05383fafca394820aa1e2e8a8e502170
144 N1762f3e9586e4bb6b3aa7f839edad0eb schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
145 schema:name Contrast Media
146 rdf:type schema:DefinedTerm
147 N27fb3b20e3544e34984a929dccc8ac21 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
148 schema:name Young Adult
149 rdf:type schema:DefinedTerm
150 N39bea2b6f341485c869fbb9264280d3a schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
151 schema:name Breast Neoplasms
152 rdf:type schema:DefinedTerm
153 N4aed605a25eb4d1d9d6124bad8e6ab57 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
154 schema:name Multimodal Imaging
155 rdf:type schema:DefinedTerm
156 N514f5d1418324b13a6e90828ca9fa7d3 rdf:first sg:person.01206226414.12
157 rdf:rest N03208c20a28f467fa68b05052900fa0f
158 N5a24e631f5f54f5bb9f4cb86edd05286 schema:name doi
159 schema:value 10.1186/s41747-019-0096-3
160 rdf:type schema:PropertyValue
161 N5f44740cd1824c38b8dfde1b0c0eab71 schema:name pubmed_id
162 schema:value 31030291
163 rdf:type schema:PropertyValue
164 N60b8a718d5314f6093db03515ee04dad schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
165 schema:name Adult
166 rdf:type schema:DefinedTerm
167 N698da07e38cc412c9f3c5eceaae39693 rdf:first sg:person.0722520562.29
168 rdf:rest N0d869cbc71924988845c3fa6d4085967
169 N7fa449c602234f5ca0c956fe3c8419d4 rdf:first sg:person.0714164140.30
170 rdf:rest N698da07e38cc412c9f3c5eceaae39693
171 N80960b9c56ff4d708b819aacd626e025 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
172 schema:name Female
173 rdf:type schema:DefinedTerm
174 N85a164c58c434ceaa447b9f753590f92 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
175 schema:name Breast Diseases
176 rdf:type schema:DefinedTerm
177 N884b32efc3c34373b7100094577ecbed schema:volumeNumber 3
178 rdf:type schema:PublicationVolume
179 N8e5bbdc0215141d18725cdc2d4031ab2 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
180 schema:name Fluorodeoxyglucose F18
181 rdf:type schema:DefinedTerm
182 N92964009ad66470da14231bb75e1a0cf schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
183 schema:name Diffusion Magnetic Resonance Imaging
184 rdf:type schema:DefinedTerm
185 Nb1103265eda745fcbfbbbc56cb6c96df schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
186 schema:name Multiparametric Magnetic Resonance Imaging
187 rdf:type schema:DefinedTerm
188 Nb566cab306584e58a6997fcf663e8109 rdf:first sg:person.0771356426.64
189 rdf:rest Nf8c69b6d79a34d5aba8e088ce2d6af71
190 Nbd67c1ed3fab45f5a9dace0eb756f01a schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
191 schema:name Positron-Emission Tomography
192 rdf:type schema:DefinedTerm
193 Nc86e51d49a7746fcac10511b9a19eea7 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
194 schema:name Radiopharmaceuticals
195 rdf:type schema:DefinedTerm
196 Ncfbf358ef58e4980a88d9ed3e4a709d0 schema:name Springer Nature - SN SciGraph project
197 rdf:type schema:Organization
198 Nd635ceb60690486daefd7db04c4fc900 schema:name dimensions_id
199 schema:value pub.1113789081
200 rdf:type schema:PropertyValue
201 Ndbc54901bc5447e4aac214f15e5a0074 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
202 schema:name Retrospective Studies
203 rdf:type schema:DefinedTerm
204 Ne3cd0548e6964b249b19d828cf59075d schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
205 schema:name Humans
206 rdf:type schema:DefinedTerm
207 Nf0adc6e1f3354ac3be0c6632b939f344 rdf:first sg:person.0715016652.61
208 rdf:rest Nb566cab306584e58a6997fcf663e8109
209 Nf8c69b6d79a34d5aba8e088ce2d6af71 rdf:first sg:person.01027401416.56
210 rdf:rest N7fa449c602234f5ca0c956fe3c8419d4
211 Nfb4ca35257ba4fd484de836636769240 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
212 schema:name Middle Aged
213 rdf:type schema:DefinedTerm
214 Nfd8467d02fd24bd788a945f508eeecb2 rdf:first sg:person.01044337625.58
215 rdf:rest rdf:nil
216 Nffdabd969c934f3ea23da642950a2c83 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
217 schema:name Aged
218 rdf:type schema:DefinedTerm
219 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
220 schema:name Information and Computing Sciences
221 rdf:type schema:DefinedTerm
222 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
223 schema:name Artificial Intelligence and Image Processing
224 rdf:type schema:DefinedTerm
225 sg:grant.2438793 http://pending.schema.org/fundedItem sg:pub.10.1186/s41747-019-0096-3
226 rdf:type schema:MonetaryGrant
227 sg:grant.5050587 http://pending.schema.org/fundedItem sg:pub.10.1186/s41747-019-0096-3
228 rdf:type schema:MonetaryGrant
229 sg:grant.6206445 http://pending.schema.org/fundedItem sg:pub.10.1186/s41747-019-0096-3
230 rdf:type schema:MonetaryGrant
231 sg:journal.1290418 schema:issn 2509-9280
232 schema:name European Radiology Experimental
233 schema:publisher Springer Nature
234 rdf:type schema:Periodical
235 sg:person.01027401416.56 schema:affiliation grid-institutes:grid.22937.3d
236 schema:familyName Helbich
237 schema:givenName Thomas H.
238 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01027401416.56
239 rdf:type schema:Person
240 sg:person.01044337625.58 schema:affiliation grid-institutes:grid.22937.3d
241 schema:familyName Langs
242 schema:givenName Georg
243 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01044337625.58
244 rdf:type schema:Person
245 sg:person.01105605026.77 schema:affiliation grid-institutes:grid.22937.3d
246 schema:familyName Bogner
247 schema:givenName Wolfgang
248 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01105605026.77
249 rdf:type schema:Person
250 sg:person.01206226414.12 schema:affiliation grid-institutes:grid.22937.3d
251 schema:familyName Bago-Horvath
252 schema:givenName Zsuzsanna
253 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01206226414.12
254 rdf:type schema:Person
255 sg:person.01223341413.62 schema:affiliation grid-institutes:grid.22937.3d
256 schema:familyName Dubsky
257 schema:givenName Peter
258 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01223341413.62
259 rdf:type schema:Person
260 sg:person.015234132112.37 schema:affiliation grid-institutes:grid.22937.3d
261 schema:familyName Gruber
262 schema:givenName Stephan
263 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015234132112.37
264 rdf:type schema:Person
265 sg:person.0714164140.30 schema:affiliation grid-institutes:grid.22937.3d
266 schema:familyName Bickel
267 schema:givenName Hubert
268 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0714164140.30
269 rdf:type schema:Person
270 sg:person.0715016652.61 schema:affiliation grid-institutes:grid.22937.3d
271 schema:familyName Vogl
272 schema:givenName Wolf-Dieter
273 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0715016652.61
274 rdf:type schema:Person
275 sg:person.0722520562.29 schema:affiliation grid-institutes:grid.452087.c
276 schema:familyName Grabner
277 schema:givenName Günther
278 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0722520562.29
279 rdf:type schema:Person
280 sg:person.0771356426.64 schema:affiliation grid-institutes:grid.51462.34
281 schema:familyName Pinker
282 schema:givenName Katja
283 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0771356426.64
284 rdf:type schema:Person
285 sg:pub.10.1007/978-3-642-22092-0_21 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053314260
286 https://doi.org/10.1007/978-3-642-22092-0_21
287 rdf:type schema:CreativeWork
288 sg:pub.10.1007/s00259-015-3099-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005135283
289 https://doi.org/10.1007/s00259-015-3099-1
290 rdf:type schema:CreativeWork
291 sg:pub.10.1007/s00330-004-2280-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1036861287
292 https://doi.org/10.1007/s00330-004-2280-x
293 rdf:type schema:CreativeWork
294 sg:pub.10.1007/s00330-011-2256-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033280588
295 https://doi.org/10.1007/s00330-011-2256-6
296 rdf:type schema:CreativeWork
297 sg:pub.10.1007/s10278-010-9298-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019988831
298 https://doi.org/10.1007/s10278-010-9298-1
299 rdf:type schema:CreativeWork
300 sg:pub.10.1023/a:1010933404324 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024739340
301 https://doi.org/10.1023/a:1010933404324
302 rdf:type schema:CreativeWork
303 sg:pub.10.1186/1471-2105-10-213 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002419282
304 https://doi.org/10.1186/1471-2105-10-213
305 rdf:type schema:CreativeWork
306 grid-institutes:grid.22937.3d schema:alternateName Computational Imaging Research Laboratory, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, Waehringer Guertel 18-20, 1090, Vienna, Austria
307 Department of Pathology, Medical University Vienna, 1090, Vienna, Austria
308 Department of Surgery, Medical University Vienna, 1090, Vienna, Austria
309 Division of Molecular and Gender Imaging, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria
310 MR Center of Excellence, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria
311 schema:name Computational Imaging Research Laboratory, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, Waehringer Guertel 18-20, 1090, Vienna, Austria
312 Department of Pathology, Medical University Vienna, 1090, Vienna, Austria
313 Department of Surgery, Medical University Vienna, 1090, Vienna, Austria
314 Division of Molecular and Gender Imaging, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria
315 MR Center of Excellence, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria
316 rdf:type schema:Organization
317 grid-institutes:grid.452087.c schema:alternateName Department of Radiologic Technology, Carinthia University of Applied Sciences, Klagenfurt, Austria
318 schema:name Department of Radiologic Technology, Carinthia University of Applied Sciences, Klagenfurt, Austria
319 MR Center of Excellence, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria
320 rdf:type schema:Organization
321 grid-institutes:grid.51462.34 schema:alternateName Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 10065, New York, NY, USA
322 schema:name Department of Radiology, Breast Imaging Service, Memorial Sloan Kettering Cancer Center, 10065, New York, NY, USA
323 Division of Molecular and Gender Imaging, Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090, Vienna, Austria
324 rdf:type schema:Organization
 




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


...