Explainable AI for CNN-based prostate tumor segmentation in multi-parametric MRI correlated to whole mount histopathology View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2022-04-02

AUTHORS

Deepa Darshini Gunashekar, Lars Bielak, Leonard Hägele, Benedict Oerther, Matthias Benndorf, Anca-L. Grosu, Thomas Brox, Constantinos Zamboglou, Michael Bock

ABSTRACT

Automatic prostate tumor segmentation is often unable to identify the lesion even if multi-parametric MRI data is used as input, and the segmentation output is difficult to verify due to the lack of clinically established ground truth images. In this work we use an explainable deep learning model to interpret the predictions of a convolutional neural network (CNN) for prostate tumor segmentation. The CNN uses a U-Net architecture which was trained on multi-parametric MRI data from 122 patients to automatically segment the prostate gland and prostate tumor lesions. In addition, co-registered ground truth data from whole mount histopathology images were available in 15 patients that were used as a test set during CNN testing. To be able to interpret the segmentation results of the CNN, heat maps were generated using the Gradient Weighted Class Activation Map (Grad-CAM) method. The CNN achieved a mean Dice Sorensen Coefficient 0.62 and 0.31 for the prostate gland and the tumor lesions -with the radiologist drawn ground truth and 0.32 with whole-mount histology ground truth for tumor lesions. Dice Sorensen Coefficient between CNN predictions and manual segmentations from MRI and histology data were not significantly different. In the prostate the Grad-CAM heat maps could differentiate between tumor and healthy prostate tissue, which indicates that the image information in the tumor was essential for the CNN segmentation. More... »

PAGES

65

References to SciGraph publications

  • 2018-05-15. Prostate segmentation in MRI using a convolutional neural network architecture and training strategy based on statistical shape models in INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
  • 2020-06-27. Clinically significant prostate cancer detection and segmentation in low-risk patients using a convolutional neural network on multi-parametric MRI in EUROPEAN RADIOLOGY
  • 2019-10-24. Towards Interpretability of Segmentation Networks by Analyzing DeepDreams in INTERPRETABILITY OF MACHINE INTELLIGENCE IN MEDICAL IMAGE COMPUTING AND MULTIMODAL LEARNING FOR CLINICAL DECISION SUPPORT
  • 2019-03-11. Unmasking Clever Hans predictors and assessing what machines really learn in NATURE COMMUNICATIONS
  • 2022-02-22. Deep learning for fully automatic detection, segmentation, and Gleason grade estimation of prostate cancer in multiparametric magnetic resonance images in SCIENTIFIC REPORTS
  • 2012-02-10. ESUR prostate MR guidelines 2012 in EUROPEAN RADIOLOGY
  • 2021-03-12. The impact of the co-registration technique and analysis methodology in comparison studies between advanced imaging modalities and whole-mount-histology reference in primary prostate cancer in SCIENTIFIC REPORTS
  • 2019-09-19. CNN-Based Prostate Zonal Segmentation on T2-Weighted MR Images: A Cross-Dataset Study in NEURAL APPROACHES TO DYNAMICS OF SIGNAL EXCHANGES
  • 2020-04-19. Manual prostate cancer segmentation in MRI: interreader agreement and volumetric correlation with transperineal template core needle biopsy in EUROPEAN RADIOLOGY
  • 2015-11-18. U-Net: Convolutional Networks for Biomedical Image Segmentation in MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION – MICCAI 2015
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1186/s13014-022-02035-0

    DOI

    http://dx.doi.org/10.1186/s13014-022-02035-0

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1146838111

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/35366918


    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/2008/1112", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Oncology and Carcinogenesis", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Humans", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Magnetic Resonance Imaging", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Male", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Multiparametric Magnetic Resonance Imaging", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Neural Networks, Computer", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Prostatic Neoplasms", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.7708.8", 
              "name": [
                "Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Gunashekar", 
            "givenName": "Deepa Darshini", 
            "id": "sg:person.016207773533.92", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016207773533.92"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.7497.d", 
              "name": [
                "Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany", 
                "German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Bielak", 
            "givenName": "Lars", 
            "id": "sg:person.010262523724.75", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010262523724.75"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.7708.8", 
              "name": [
                "Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "H\u00e4gele", 
            "givenName": "Leonard", 
            "id": "sg:person.07504722333.02", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07504722333.02"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.7708.8", 
              "name": [
                "Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Oerther", 
            "givenName": "Benedict", 
            "id": "sg:person.016464630337.60", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016464630337.60"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.7708.8", 
              "name": [
                "Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Benndorf", 
            "givenName": "Matthias", 
            "id": "sg:person.01343171550.79", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01343171550.79"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.7708.8", 
              "name": [
                "German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany", 
                "Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Grosu", 
            "givenName": "Anca-L.", 
            "id": "sg:person.0671176260.11", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0671176260.11"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Computer Science, University of Freiburg, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.5963.9", 
              "name": [
                "Department of Computer Science, University of Freiburg, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Brox", 
            "givenName": "Thomas", 
            "id": "sg:person.012443225372.65", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.7708.8", 
              "name": [
                "German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany", 
                "Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zamboglou", 
            "givenName": "Constantinos", 
            "id": "sg:person.0635422511.04", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0635422511.04"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.7497.d", 
              "name": [
                "Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany", 
                "German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Bock", 
            "givenName": "Michael", 
            "id": "sg:person.01357166316.22", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01357166316.22"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s11548-018-1785-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1103995269", 
              "https://doi.org/10.1007/s11548-018-1785-8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00330-011-2377-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041692485", 
              "https://doi.org/10.1007/s00330-011-2377-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41598-022-06730-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1145744227", 
              "https://doi.org/10.1038/s41598-022-06730-6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00330-020-07008-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1128815987", 
              "https://doi.org/10.1007/s00330-020-07008-z"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-981-13-8950-4_25", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1121091045", 
              "https://doi.org/10.1007/978-981-13-8950-4_25"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41598-021-85028-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1136333333", 
              "https://doi.org/10.1038/s41598-021-85028-5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-24574-4_28", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017774818", 
              "https://doi.org/10.1007/978-3-319-24574-4_28"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41467-019-08987-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1112676463", 
              "https://doi.org/10.1038/s41467-019-08987-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-33850-3_7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1122084520", 
              "https://doi.org/10.1007/978-3-030-33850-3_7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00330-020-06786-w", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1126787871", 
              "https://doi.org/10.1007/s00330-020-06786-w"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2022-04-02", 
        "datePublishedReg": "2022-04-02", 
        "description": "Automatic prostate tumor segmentation is often unable to identify the lesion even if multi-parametric MRI data is used as input, and the segmentation output is difficult to verify due to the lack of clinically established ground truth images. In this work we use an explainable deep learning model to interpret the predictions of a convolutional neural network (CNN) for prostate tumor segmentation. The CNN uses a U-Net architecture which was trained on multi-parametric MRI data from 122 patients to automatically segment the prostate gland and prostate tumor lesions. In addition, co-registered ground truth data from whole mount histopathology images were available in 15 patients that were used as a test set during CNN testing. To be able to interpret the segmentation results of the CNN, heat maps were generated using the Gradient Weighted Class Activation Map (Grad-CAM) method. The CNN achieved a mean Dice Sorensen Coefficient 0.62 and 0.31 for the prostate gland and the tumor lesions -with the radiologist drawn ground truth and 0.32 with whole-mount histology ground truth for tumor lesions. Dice Sorensen Coefficient between CNN predictions and manual segmentations from MRI and histology data were not significantly different. In the prostate the Grad-CAM heat maps could differentiate between tumor and healthy prostate tissue, which indicates that the image information in the tumor was essential for the CNN segmentation.", 
        "genre": "article", 
        "id": "sg:pub.10.1186/s13014-022-02035-0", 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1036451", 
            "issn": [
              "1748-717X"
            ], 
            "name": "Radiation Oncology", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "17"
          }
        ], 
        "keywords": [
          "convolutional neural network", 
          "tumor segmentation", 
          "multi-parametric MRI data", 
          "explainable deep learning model", 
          "class activation maps method", 
          "deep learning models", 
          "ground truth images", 
          "ground truth data", 
          "heat map", 
          "Dice-Sorensen coefficient", 
          "Explainable AI", 
          "Net architecture", 
          "histopathology images", 
          "segmentation output", 
          "image information", 
          "CNN predictions", 
          "neural network", 
          "segmentation results", 
          "MRI data", 
          "CNN segmentation", 
          "truth images", 
          "learning model", 
          "ground truth", 
          "manual segmentation", 
          "segmentation", 
          "truth data", 
          "map method", 
          "images", 
          "Sorensen coefficient", 
          "multi-parametric MRI", 
          "architecture", 
          "AI", 
          "network", 
          "maps", 
          "data", 
          "truth", 
          "information", 
          "prediction", 
          "input", 
          "histology data", 
          "mount histology", 
          "output", 
          "work", 
          "model", 
          "radiologists", 
          "method", 
          "testing", 
          "results", 
          "healthy prostate tissue", 
          "lack", 
          "MRI", 
          "addition", 
          "coefficient", 
          "tumor lesions", 
          "test", 
          "prostate gland", 
          "prostate tissue", 
          "prostate", 
          "patients", 
          "lesions", 
          "tumors", 
          "histopathology", 
          "tissue", 
          "histology", 
          "gland", 
          "mount histopathology", 
          "whole-mount histopathology"
        ], 
        "name": "Explainable AI for CNN-based prostate tumor segmentation in multi-parametric MRI correlated to whole mount histopathology", 
        "pagination": "65", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1146838111"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1186/s13014-022-02035-0"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "35366918"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1186/s13014-022-02035-0", 
          "https://app.dimensions.ai/details/publication/pub.1146838111"
        ], 
        "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_941.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1186/s13014-022-02035-0"
      }
    ]
     

    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/s13014-022-02035-0'

    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/s13014-022-02035-0'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s13014-022-02035-0'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s13014-022-02035-0'


     

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

    257 TRIPLES      21 PREDICATES      108 URIs      90 LITERALS      13 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1186/s13014-022-02035-0 schema:about N1944e2dc1aa6415e9318ded87619f21b
    2 N3dbe42183eb24b61a47768f5b8d0bc33
    3 N5df5d515ac4847f993ffc6908ddb29c3
    4 Naf521fcb6548470b95bf8393ee2eabb8
    5 Nb661110662ed4acdafd8e488769c3151
    6 Ne59865d35fcd41aca552963a89fec144
    7 anzsrc-for:11
    8 anzsrc-for:1112
    9 schema:author Nf93c522aa54b45b888e7d6f847aab90f
    10 schema:citation sg:pub.10.1007/978-3-030-33850-3_7
    11 sg:pub.10.1007/978-3-319-24574-4_28
    12 sg:pub.10.1007/978-981-13-8950-4_25
    13 sg:pub.10.1007/s00330-011-2377-y
    14 sg:pub.10.1007/s00330-020-06786-w
    15 sg:pub.10.1007/s00330-020-07008-z
    16 sg:pub.10.1007/s11548-018-1785-8
    17 sg:pub.10.1038/s41467-019-08987-4
    18 sg:pub.10.1038/s41598-021-85028-5
    19 sg:pub.10.1038/s41598-022-06730-6
    20 schema:datePublished 2022-04-02
    21 schema:datePublishedReg 2022-04-02
    22 schema:description Automatic prostate tumor segmentation is often unable to identify the lesion even if multi-parametric MRI data is used as input, and the segmentation output is difficult to verify due to the lack of clinically established ground truth images. In this work we use an explainable deep learning model to interpret the predictions of a convolutional neural network (CNN) for prostate tumor segmentation. The CNN uses a U-Net architecture which was trained on multi-parametric MRI data from 122 patients to automatically segment the prostate gland and prostate tumor lesions. In addition, co-registered ground truth data from whole mount histopathology images were available in 15 patients that were used as a test set during CNN testing. To be able to interpret the segmentation results of the CNN, heat maps were generated using the Gradient Weighted Class Activation Map (Grad-CAM) method. The CNN achieved a mean Dice Sorensen Coefficient 0.62 and 0.31 for the prostate gland and the tumor lesions -with the radiologist drawn ground truth and 0.32 with whole-mount histology ground truth for tumor lesions. Dice Sorensen Coefficient between CNN predictions and manual segmentations from MRI and histology data were not significantly different. In the prostate the Grad-CAM heat maps could differentiate between tumor and healthy prostate tissue, which indicates that the image information in the tumor was essential for the CNN segmentation.
    23 schema:genre article
    24 schema:isAccessibleForFree true
    25 schema:isPartOf N12e1790ecc264de0a02184a7f08de1a1
    26 N87c73a0ed9d24c139eef0accba96f4d1
    27 sg:journal.1036451
    28 schema:keywords AI
    29 CNN predictions
    30 CNN segmentation
    31 Dice-Sorensen coefficient
    32 Explainable AI
    33 MRI
    34 MRI data
    35 Net architecture
    36 Sorensen coefficient
    37 addition
    38 architecture
    39 class activation maps method
    40 coefficient
    41 convolutional neural network
    42 data
    43 deep learning models
    44 explainable deep learning model
    45 gland
    46 ground truth
    47 ground truth data
    48 ground truth images
    49 healthy prostate tissue
    50 heat map
    51 histology
    52 histology data
    53 histopathology
    54 histopathology images
    55 image information
    56 images
    57 information
    58 input
    59 lack
    60 learning model
    61 lesions
    62 manual segmentation
    63 map method
    64 maps
    65 method
    66 model
    67 mount histology
    68 mount histopathology
    69 multi-parametric MRI
    70 multi-parametric MRI data
    71 network
    72 neural network
    73 output
    74 patients
    75 prediction
    76 prostate
    77 prostate gland
    78 prostate tissue
    79 radiologists
    80 results
    81 segmentation
    82 segmentation output
    83 segmentation results
    84 test
    85 testing
    86 tissue
    87 truth
    88 truth data
    89 truth images
    90 tumor lesions
    91 tumor segmentation
    92 tumors
    93 whole-mount histopathology
    94 work
    95 schema:name Explainable AI for CNN-based prostate tumor segmentation in multi-parametric MRI correlated to whole mount histopathology
    96 schema:pagination 65
    97 schema:productId N1790b3dc52044f30bb40fe496b10fb28
    98 N30639b8b59794b95ab54379d1233e2cd
    99 N68ab43816c264845a2dc0b6e23488988
    100 schema:sameAs https://app.dimensions.ai/details/publication/pub.1146838111
    101 https://doi.org/10.1186/s13014-022-02035-0
    102 schema:sdDatePublished 2022-09-02T16:07
    103 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    104 schema:sdPublisher N80f7001c426240528b64e1fdc65c48cb
    105 schema:url https://doi.org/10.1186/s13014-022-02035-0
    106 sgo:license sg:explorer/license/
    107 sgo:sdDataset articles
    108 rdf:type schema:ScholarlyArticle
    109 N12e1790ecc264de0a02184a7f08de1a1 schema:volumeNumber 17
    110 rdf:type schema:PublicationVolume
    111 N153ec75d8b934522950b0205cd4cfd1e rdf:first sg:person.0671176260.11
    112 rdf:rest N78a2ab4f96d741aca0522c1f6ebdbbb0
    113 N1790b3dc52044f30bb40fe496b10fb28 schema:name dimensions_id
    114 schema:value pub.1146838111
    115 rdf:type schema:PropertyValue
    116 N1944e2dc1aa6415e9318ded87619f21b schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    117 schema:name Humans
    118 rdf:type schema:DefinedTerm
    119 N30639b8b59794b95ab54379d1233e2cd schema:name doi
    120 schema:value 10.1186/s13014-022-02035-0
    121 rdf:type schema:PropertyValue
    122 N3dbe42183eb24b61a47768f5b8d0bc33 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    123 schema:name Multiparametric Magnetic Resonance Imaging
    124 rdf:type schema:DefinedTerm
    125 N5c5f9e6225cc40ab82533fda32772af2 rdf:first sg:person.0635422511.04
    126 rdf:rest Nc1459cf6225e4fbdb2227d66adb53a3c
    127 N5df5d515ac4847f993ffc6908ddb29c3 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    128 schema:name Prostatic Neoplasms
    129 rdf:type schema:DefinedTerm
    130 N68ab43816c264845a2dc0b6e23488988 schema:name pubmed_id
    131 schema:value 35366918
    132 rdf:type schema:PropertyValue
    133 N78a2ab4f96d741aca0522c1f6ebdbbb0 rdf:first sg:person.012443225372.65
    134 rdf:rest N5c5f9e6225cc40ab82533fda32772af2
    135 N7c8f5955c135457795321287f5f17f0c rdf:first sg:person.010262523724.75
    136 rdf:rest Na80d57d90e8a4bbf82831c90754314de
    137 N80f7001c426240528b64e1fdc65c48cb schema:name Springer Nature - SN SciGraph project
    138 rdf:type schema:Organization
    139 N87c73a0ed9d24c139eef0accba96f4d1 schema:issueNumber 1
    140 rdf:type schema:PublicationIssue
    141 Na80d57d90e8a4bbf82831c90754314de rdf:first sg:person.07504722333.02
    142 rdf:rest Ndeafbe68be9d46458a1939a1a341a1c7
    143 Naf521fcb6548470b95bf8393ee2eabb8 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    144 schema:name Magnetic Resonance Imaging
    145 rdf:type schema:DefinedTerm
    146 Nb661110662ed4acdafd8e488769c3151 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    147 schema:name Male
    148 rdf:type schema:DefinedTerm
    149 Nc1459cf6225e4fbdb2227d66adb53a3c rdf:first sg:person.01357166316.22
    150 rdf:rest rdf:nil
    151 Nc32a8149fe8e4a2eb6517312186decad rdf:first sg:person.01343171550.79
    152 rdf:rest N153ec75d8b934522950b0205cd4cfd1e
    153 Ndeafbe68be9d46458a1939a1a341a1c7 rdf:first sg:person.016464630337.60
    154 rdf:rest Nc32a8149fe8e4a2eb6517312186decad
    155 Ne59865d35fcd41aca552963a89fec144 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    156 schema:name Neural Networks, Computer
    157 rdf:type schema:DefinedTerm
    158 Nf93c522aa54b45b888e7d6f847aab90f rdf:first sg:person.016207773533.92
    159 rdf:rest N7c8f5955c135457795321287f5f17f0c
    160 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
    161 schema:name Medical and Health Sciences
    162 rdf:type schema:DefinedTerm
    163 anzsrc-for:1112 schema:inDefinedTermSet anzsrc-for:
    164 schema:name Oncology and Carcinogenesis
    165 rdf:type schema:DefinedTerm
    166 sg:journal.1036451 schema:issn 1748-717X
    167 schema:name Radiation Oncology
    168 schema:publisher Springer Nature
    169 rdf:type schema:Periodical
    170 sg:person.010262523724.75 schema:affiliation grid-institutes:grid.7497.d
    171 schema:familyName Bielak
    172 schema:givenName Lars
    173 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010262523724.75
    174 rdf:type schema:Person
    175 sg:person.012443225372.65 schema:affiliation grid-institutes:grid.5963.9
    176 schema:familyName Brox
    177 schema:givenName Thomas
    178 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65
    179 rdf:type schema:Person
    180 sg:person.01343171550.79 schema:affiliation grid-institutes:grid.7708.8
    181 schema:familyName Benndorf
    182 schema:givenName Matthias
    183 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01343171550.79
    184 rdf:type schema:Person
    185 sg:person.01357166316.22 schema:affiliation grid-institutes:grid.7497.d
    186 schema:familyName Bock
    187 schema:givenName Michael
    188 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01357166316.22
    189 rdf:type schema:Person
    190 sg:person.016207773533.92 schema:affiliation grid-institutes:grid.7708.8
    191 schema:familyName Gunashekar
    192 schema:givenName Deepa Darshini
    193 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016207773533.92
    194 rdf:type schema:Person
    195 sg:person.016464630337.60 schema:affiliation grid-institutes:grid.7708.8
    196 schema:familyName Oerther
    197 schema:givenName Benedict
    198 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016464630337.60
    199 rdf:type schema:Person
    200 sg:person.0635422511.04 schema:affiliation grid-institutes:grid.7708.8
    201 schema:familyName Zamboglou
    202 schema:givenName Constantinos
    203 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0635422511.04
    204 rdf:type schema:Person
    205 sg:person.0671176260.11 schema:affiliation grid-institutes:grid.7708.8
    206 schema:familyName Grosu
    207 schema:givenName Anca-L.
    208 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0671176260.11
    209 rdf:type schema:Person
    210 sg:person.07504722333.02 schema:affiliation grid-institutes:grid.7708.8
    211 schema:familyName Hägele
    212 schema:givenName Leonard
    213 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07504722333.02
    214 rdf:type schema:Person
    215 sg:pub.10.1007/978-3-030-33850-3_7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1122084520
    216 https://doi.org/10.1007/978-3-030-33850-3_7
    217 rdf:type schema:CreativeWork
    218 sg:pub.10.1007/978-3-319-24574-4_28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017774818
    219 https://doi.org/10.1007/978-3-319-24574-4_28
    220 rdf:type schema:CreativeWork
    221 sg:pub.10.1007/978-981-13-8950-4_25 schema:sameAs https://app.dimensions.ai/details/publication/pub.1121091045
    222 https://doi.org/10.1007/978-981-13-8950-4_25
    223 rdf:type schema:CreativeWork
    224 sg:pub.10.1007/s00330-011-2377-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1041692485
    225 https://doi.org/10.1007/s00330-011-2377-y
    226 rdf:type schema:CreativeWork
    227 sg:pub.10.1007/s00330-020-06786-w schema:sameAs https://app.dimensions.ai/details/publication/pub.1126787871
    228 https://doi.org/10.1007/s00330-020-06786-w
    229 rdf:type schema:CreativeWork
    230 sg:pub.10.1007/s00330-020-07008-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1128815987
    231 https://doi.org/10.1007/s00330-020-07008-z
    232 rdf:type schema:CreativeWork
    233 sg:pub.10.1007/s11548-018-1785-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103995269
    234 https://doi.org/10.1007/s11548-018-1785-8
    235 rdf:type schema:CreativeWork
    236 sg:pub.10.1038/s41467-019-08987-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112676463
    237 https://doi.org/10.1038/s41467-019-08987-4
    238 rdf:type schema:CreativeWork
    239 sg:pub.10.1038/s41598-021-85028-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1136333333
    240 https://doi.org/10.1038/s41598-021-85028-5
    241 rdf:type schema:CreativeWork
    242 sg:pub.10.1038/s41598-022-06730-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1145744227
    243 https://doi.org/10.1038/s41598-022-06730-6
    244 rdf:type schema:CreativeWork
    245 grid-institutes:grid.5963.9 schema:alternateName Department of Computer Science, University of Freiburg, Freiburg, Germany
    246 schema:name Department of Computer Science, University of Freiburg, Freiburg, Germany
    247 rdf:type schema:Organization
    248 grid-institutes:grid.7497.d schema:alternateName German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
    249 schema:name Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
    250 German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
    251 rdf:type schema:Organization
    252 grid-institutes:grid.7708.8 schema:alternateName Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
    253 Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
    254 schema:name Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
    255 Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
    256 German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
    257 rdf:type schema:Organization
     




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


    ...