Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2019-12

AUTHORS

Jason W. Wei, Laura J. Tafe, Yevgeniy A. Linnik, Louis J. Vaickus, Naofumi Tomita, Saeed Hassanpour

ABSTRACT

Classification of histologic patterns in lung adenocarcinoma is critical for determining tumor grade and treatment for patients. However, this task is often challenging due to the heterogeneous nature of lung adenocarcinoma and the subjective criteria for evaluation. In this study, we propose a deep learning model that automatically classifies the histologic patterns of lung adenocarcinoma on surgical resection slides. Our model uses a convolutional neural network to identify regions of neoplastic cells, then aggregates those classifications to infer predominant and minor histologic patterns for any given whole-slide image. We evaluated our model on an independent set of 143 whole-slide images. It achieved a kappa score of 0.525 and an agreement of 66.6% with three pathologists for classifying the predominant patterns, slightly higher than the inter-pathologist kappa score of 0.485 and agreement of 62.7% on this test set. All evaluation metrics for our model and the three pathologists were within 95% confidence intervals of agreement. If confirmed in clinical practice, our model can assist pathologists in improving classification of lung adenocarcinoma patterns by automatically pre-screening and highlighting cancerous regions prior to review. Our approach can be generalized to any whole-slide image classification task, and code is made publicly available at https://github.com/BMIRDS/deepslide . More... »

PAGES

3358

Identifiers

URI

http://scigraph.springernature.com/pub.10.1038/s41598-019-40041-7

DOI

http://dx.doi.org/10.1038/s41598-019-40041-7

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1112512281

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/30833650


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/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Dartmouth College", 
          "id": "https://www.grid.ac/institutes/grid.254880.3", 
          "name": [
            "Department of Biomedical Data Science, Dartmouth College, Hanover, NH, USA", 
            "Department of Computer Science, Dartmouth College, Hanover, NH, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wei", 
        "givenName": "Jason W.", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dartmouth\u2013Hitchcock Medical Center", 
          "id": "https://www.grid.ac/institutes/grid.413480.a", 
          "name": [
            "Department of Pathology and Laboratory Medicine, Dartmouth-Hitchcock Medical Center, Lebanon, NH, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tafe", 
        "givenName": "Laura J.", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dartmouth\u2013Hitchcock Medical Center", 
          "id": "https://www.grid.ac/institutes/grid.413480.a", 
          "name": [
            "Department of Pathology and Laboratory Medicine, Dartmouth-Hitchcock Medical Center, Lebanon, NH, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Linnik", 
        "givenName": "Yevgeniy A.", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dartmouth\u2013Hitchcock Medical Center", 
          "id": "https://www.grid.ac/institutes/grid.413480.a", 
          "name": [
            "Department of Pathology and Laboratory Medicine, Dartmouth-Hitchcock Medical Center, Lebanon, NH, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Vaickus", 
        "givenName": "Louis J.", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dartmouth College", 
          "id": "https://www.grid.ac/institutes/grid.254880.3", 
          "name": [
            "Department of Biomedical Data Science, Dartmouth College, Hanover, NH, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tomita", 
        "givenName": "Naofumi", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dartmouth College", 
          "id": "https://www.grid.ac/institutes/grid.254880.3", 
          "name": [
            "Department of Biomedical Data Science, Dartmouth College, Hanover, NH, USA", 
            "Department of Computer Science, Dartmouth College, Hanover, NH, USA", 
            "Department of Epidemiology, Dartmouth College, Lebanon, NH, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hassanpour", 
        "givenName": "Saeed", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.5858/arpa.2010-0493-oa", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000242468"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5858/arpa.2010-0493-oa", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000242468"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/ncomms12474", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000998210", 
          "https://doi.org/10.1038/ncomms12474"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/jnci/djt166", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006296938"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/jnci/djt166", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006296938"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/pas.0000000000000134", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006699754"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/pas.0000000000000134", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006699754"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/pas.0000000000000134", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006699754"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/jto.0b013e318221f701", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007371930"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11263-015-0816-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009767488", 
          "https://doi.org/10.1007/s11263-015-0816-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1183/09031936.00219211", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010411029"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00428-012-1263-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010621353", 
          "https://doi.org/10.1007/s00428-012-1263-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00428-012-1263-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010621353", 
          "https://doi.org/10.1007/s00428-012-1263-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-24223-1_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1013659543", 
          "https://doi.org/10.1007/978-3-319-24223-1_1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.jtho.2016.10.017", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015044716"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/modpathol.2010.232", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016062506", 
          "https://doi.org/10.1038/modpathol.2010.232"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/jto.0b013e318206a221", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020132671"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1200/jco.2011.37.2185", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022128964"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1200/jco.2011.37.2185", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022128964"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pone.0121323", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025866605"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pone.0121323", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025866605"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/pas.0b013e3181b8cf03", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030628930"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/pas.0b013e3181b8cf03", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030628930"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/pas.0b013e3181b8cf03", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030628930"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.jtcvs.2013.09.045", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036617948"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.jtcvs.2013.09.045", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036617948"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/pin.12016", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036686282"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1200/jco.2014.58.8335", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042319271"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1200/jco.2014.58.8335", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042319271"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/pas.0000000000000246", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044077620"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/pas.0000000000000246", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044077620"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/pas.0000000000000246", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044077620"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.jtcvs.2013.08.058", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044855097"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.jtcvs.2013.08.058", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044855097"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-10602-1_48", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045321436", 
          "https://doi.org/10.1007/978-3-319-10602-1_48"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/jto.0000000000000630", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1046335884"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/00000478-200301000-00011", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047643654"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1097/00000478-200301000-00011", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047643654"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/modpathol.2012.106", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051056011", 
          "https://doi.org/10.1038/modpathol.2012.106"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.ejso.2013.08.026", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051713035"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.11613/bm.2012.031", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1063347969"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.4103/jpi.jpi_34_17", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090898992"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.media.2017.07.005", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090904008"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2016.90", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093359587"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2015.123", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093828312"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3390/medsci5040034", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099651777"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2017.322", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100060307"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3414/me17-01-0039", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1103283982"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.compbiomed.2018.05.011", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1103851305"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/s41598-018-27707-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1105359794", 
          "https://doi.org/10.1038/s41598-018-27707-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/s41591-018-0177-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1106837359", 
          "https://doi.org/10.1038/s41591-018-0177-5"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-12", 
    "datePublishedReg": "2019-12-01", 
    "description": "Classification of histologic patterns in lung adenocarcinoma is critical for determining tumor grade and treatment for patients. However, this task is often challenging due to the heterogeneous nature of lung adenocarcinoma and the subjective criteria for evaluation. In this study, we propose a deep learning model that automatically classifies the histologic patterns of lung adenocarcinoma on surgical resection slides. Our model uses a convolutional neural network to identify regions of neoplastic cells, then aggregates those classifications to infer predominant and minor histologic patterns for any given whole-slide image. We evaluated our model on an independent set of 143 whole-slide images. It achieved a kappa score of 0.525 and an agreement of 66.6% with three pathologists for classifying the predominant patterns, slightly higher than the inter-pathologist kappa score of 0.485 and agreement of 62.7% on this test set. All evaluation metrics for our model and the three pathologists were within 95% confidence intervals of agreement. If confirmed in clinical practice, our model can assist pathologists in improving classification of lung adenocarcinoma patterns by automatically pre-screening and highlighting cancerous regions prior to review. Our approach can be generalized to any whole-slide image classification task, and code is made publicly available at https://github.com/BMIRDS/deepslide .", 
    "genre": "research_article", 
    "id": "sg:pub.10.1038/s41598-019-40041-7", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1045337", 
        "issn": [
          "2045-2322"
        ], 
        "name": "Scientific Reports", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "9"
      }
    ], 
    "name": "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks", 
    "pagination": "3358", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "ecd198e7402ab05a4e0b7d3269bbe21d3a85e7cf92c32de959c3268e2db1e19f"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "30833650"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "101563288"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1038/s41598-019-40041-7"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1112512281"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1038/s41598-019-40041-7", 
      "https://app.dimensions.ai/details/publication/pub.1112512281"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T11:21", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000354_0000000354/records_11728_00000002.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://www.nature.com/articles/s41598-019-40041-7"
  }
]
 

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.10.1038/s41598-019-40041-7'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1038/s41598-019-40041-7'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1038/s41598-019-40041-7'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1038/s41598-019-40041-7'


 

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

219 TRIPLES      21 PREDICATES      65 URIs      21 LITERALS      9 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1038/s41598-019-40041-7 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N0cfc6699f37c4c5197d228db1caa9f11
4 schema:citation sg:pub.10.1007/978-3-319-10602-1_48
5 sg:pub.10.1007/978-3-319-24223-1_1
6 sg:pub.10.1007/s00428-012-1263-6
7 sg:pub.10.1007/s11263-015-0816-y
8 sg:pub.10.1038/modpathol.2010.232
9 sg:pub.10.1038/modpathol.2012.106
10 sg:pub.10.1038/ncomms12474
11 sg:pub.10.1038/s41591-018-0177-5
12 sg:pub.10.1038/s41598-018-27707-4
13 https://doi.org/10.1016/j.compbiomed.2018.05.011
14 https://doi.org/10.1016/j.ejso.2013.08.026
15 https://doi.org/10.1016/j.jtcvs.2013.08.058
16 https://doi.org/10.1016/j.jtcvs.2013.09.045
17 https://doi.org/10.1016/j.jtho.2016.10.017
18 https://doi.org/10.1016/j.media.2017.07.005
19 https://doi.org/10.1093/jnci/djt166
20 https://doi.org/10.1097/00000478-200301000-00011
21 https://doi.org/10.1097/jto.0000000000000630
22 https://doi.org/10.1097/jto.0b013e318206a221
23 https://doi.org/10.1097/jto.0b013e318221f701
24 https://doi.org/10.1097/pas.0000000000000134
25 https://doi.org/10.1097/pas.0000000000000246
26 https://doi.org/10.1097/pas.0b013e3181b8cf03
27 https://doi.org/10.1109/cvpr.2016.90
28 https://doi.org/10.1109/iccv.2015.123
29 https://doi.org/10.1109/iccv.2017.322
30 https://doi.org/10.1111/pin.12016
31 https://doi.org/10.11613/bm.2012.031
32 https://doi.org/10.1183/09031936.00219211
33 https://doi.org/10.1200/jco.2011.37.2185
34 https://doi.org/10.1200/jco.2014.58.8335
35 https://doi.org/10.1371/journal.pone.0121323
36 https://doi.org/10.3390/medsci5040034
37 https://doi.org/10.3414/me17-01-0039
38 https://doi.org/10.4103/jpi.jpi_34_17
39 https://doi.org/10.5858/arpa.2010-0493-oa
40 schema:datePublished 2019-12
41 schema:datePublishedReg 2019-12-01
42 schema:description Classification of histologic patterns in lung adenocarcinoma is critical for determining tumor grade and treatment for patients. However, this task is often challenging due to the heterogeneous nature of lung adenocarcinoma and the subjective criteria for evaluation. In this study, we propose a deep learning model that automatically classifies the histologic patterns of lung adenocarcinoma on surgical resection slides. Our model uses a convolutional neural network to identify regions of neoplastic cells, then aggregates those classifications to infer predominant and minor histologic patterns for any given whole-slide image. We evaluated our model on an independent set of 143 whole-slide images. It achieved a kappa score of 0.525 and an agreement of 66.6% with three pathologists for classifying the predominant patterns, slightly higher than the inter-pathologist kappa score of 0.485 and agreement of 62.7% on this test set. All evaluation metrics for our model and the three pathologists were within 95% confidence intervals of agreement. If confirmed in clinical practice, our model can assist pathologists in improving classification of lung adenocarcinoma patterns by automatically pre-screening and highlighting cancerous regions prior to review. Our approach can be generalized to any whole-slide image classification task, and code is made publicly available at https://github.com/BMIRDS/deepslide .
43 schema:genre research_article
44 schema:inLanguage en
45 schema:isAccessibleForFree true
46 schema:isPartOf N6c5b2b1a52a5436da421feb55b6145db
47 N9133962698204476905db9afb6d0e3c3
48 sg:journal.1045337
49 schema:name Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks
50 schema:pagination 3358
51 schema:productId N24b18ae6891e43ecafb4c562f623cd4b
52 N902fb0a64da0483eadd10be7e86c6fa1
53 Na8cb3c5481aa4af2904c13550377e145
54 Nb56eb34d5b9e4d5cb39c417d0bf1a258
55 Nd40b913048a84f4f9507dec372485bd3
56 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112512281
57 https://doi.org/10.1038/s41598-019-40041-7
58 schema:sdDatePublished 2019-04-11T11:21
59 schema:sdLicense https://scigraph.springernature.com/explorer/license/
60 schema:sdPublisher N384f681c41504865895047e54e4e529f
61 schema:url https://www.nature.com/articles/s41598-019-40041-7
62 sgo:license sg:explorer/license/
63 sgo:sdDataset articles
64 rdf:type schema:ScholarlyArticle
65 N0cfc6699f37c4c5197d228db1caa9f11 rdf:first Nfcaab3be1ba2430691907aa7aa6d5aff
66 rdf:rest Nb6ae8d2b4e604c39b45b039c92e3cc21
67 N24b18ae6891e43ecafb4c562f623cd4b schema:name dimensions_id
68 schema:value pub.1112512281
69 rdf:type schema:PropertyValue
70 N384f681c41504865895047e54e4e529f schema:name Springer Nature - SN SciGraph project
71 rdf:type schema:Organization
72 N42e2c21c5f5644ecab2c8d8235968415 schema:affiliation https://www.grid.ac/institutes/grid.413480.a
73 schema:familyName Vaickus
74 schema:givenName Louis J.
75 rdf:type schema:Person
76 N43caa003b44a4750816c267fdd829806 schema:affiliation https://www.grid.ac/institutes/grid.254880.3
77 schema:familyName Hassanpour
78 schema:givenName Saeed
79 rdf:type schema:Person
80 N6c5b2b1a52a5436da421feb55b6145db schema:volumeNumber 9
81 rdf:type schema:PublicationVolume
82 N774d3b377d184a2d8f438798e2851910 rdf:first N776e37909abc4459abd91502fb2c2300
83 rdf:rest Nba10e3a22a5547ae873e388276dfe95b
84 N776e37909abc4459abd91502fb2c2300 schema:affiliation https://www.grid.ac/institutes/grid.254880.3
85 schema:familyName Tomita
86 schema:givenName Naofumi
87 rdf:type schema:Person
88 N898bbe7f62584f71b4ad85bbf2a8d643 rdf:first N42e2c21c5f5644ecab2c8d8235968415
89 rdf:rest N774d3b377d184a2d8f438798e2851910
90 N902fb0a64da0483eadd10be7e86c6fa1 schema:name doi
91 schema:value 10.1038/s41598-019-40041-7
92 rdf:type schema:PropertyValue
93 N9133962698204476905db9afb6d0e3c3 schema:issueNumber 1
94 rdf:type schema:PublicationIssue
95 Na8cb3c5481aa4af2904c13550377e145 schema:name pubmed_id
96 schema:value 30833650
97 rdf:type schema:PropertyValue
98 Nb56eb34d5b9e4d5cb39c417d0bf1a258 schema:name readcube_id
99 schema:value ecd198e7402ab05a4e0b7d3269bbe21d3a85e7cf92c32de959c3268e2db1e19f
100 rdf:type schema:PropertyValue
101 Nb6ae8d2b4e604c39b45b039c92e3cc21 rdf:first Ncd046a631aa446e69550b0fcb53ed5f4
102 rdf:rest Nf95473edfb4d474aa20a0d29e185915a
103 Nba10e3a22a5547ae873e388276dfe95b rdf:first N43caa003b44a4750816c267fdd829806
104 rdf:rest rdf:nil
105 Nbb35f59ccd7447998ed07a26789075f8 schema:affiliation https://www.grid.ac/institutes/grid.413480.a
106 schema:familyName Linnik
107 schema:givenName Yevgeniy A.
108 rdf:type schema:Person
109 Ncd046a631aa446e69550b0fcb53ed5f4 schema:affiliation https://www.grid.ac/institutes/grid.413480.a
110 schema:familyName Tafe
111 schema:givenName Laura J.
112 rdf:type schema:Person
113 Nd40b913048a84f4f9507dec372485bd3 schema:name nlm_unique_id
114 schema:value 101563288
115 rdf:type schema:PropertyValue
116 Nf95473edfb4d474aa20a0d29e185915a rdf:first Nbb35f59ccd7447998ed07a26789075f8
117 rdf:rest N898bbe7f62584f71b4ad85bbf2a8d643
118 Nfcaab3be1ba2430691907aa7aa6d5aff schema:affiliation https://www.grid.ac/institutes/grid.254880.3
119 schema:familyName Wei
120 schema:givenName Jason W.
121 rdf:type schema:Person
122 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
123 schema:name Information and Computing Sciences
124 rdf:type schema:DefinedTerm
125 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
126 schema:name Artificial Intelligence and Image Processing
127 rdf:type schema:DefinedTerm
128 sg:journal.1045337 schema:issn 2045-2322
129 schema:name Scientific Reports
130 rdf:type schema:Periodical
131 sg:pub.10.1007/978-3-319-10602-1_48 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045321436
132 https://doi.org/10.1007/978-3-319-10602-1_48
133 rdf:type schema:CreativeWork
134 sg:pub.10.1007/978-3-319-24223-1_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013659543
135 https://doi.org/10.1007/978-3-319-24223-1_1
136 rdf:type schema:CreativeWork
137 sg:pub.10.1007/s00428-012-1263-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010621353
138 https://doi.org/10.1007/s00428-012-1263-6
139 rdf:type schema:CreativeWork
140 sg:pub.10.1007/s11263-015-0816-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1009767488
141 https://doi.org/10.1007/s11263-015-0816-y
142 rdf:type schema:CreativeWork
143 sg:pub.10.1038/modpathol.2010.232 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016062506
144 https://doi.org/10.1038/modpathol.2010.232
145 rdf:type schema:CreativeWork
146 sg:pub.10.1038/modpathol.2012.106 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051056011
147 https://doi.org/10.1038/modpathol.2012.106
148 rdf:type schema:CreativeWork
149 sg:pub.10.1038/ncomms12474 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000998210
150 https://doi.org/10.1038/ncomms12474
151 rdf:type schema:CreativeWork
152 sg:pub.10.1038/s41591-018-0177-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1106837359
153 https://doi.org/10.1038/s41591-018-0177-5
154 rdf:type schema:CreativeWork
155 sg:pub.10.1038/s41598-018-27707-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105359794
156 https://doi.org/10.1038/s41598-018-27707-4
157 rdf:type schema:CreativeWork
158 https://doi.org/10.1016/j.compbiomed.2018.05.011 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103851305
159 rdf:type schema:CreativeWork
160 https://doi.org/10.1016/j.ejso.2013.08.026 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051713035
161 rdf:type schema:CreativeWork
162 https://doi.org/10.1016/j.jtcvs.2013.08.058 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044855097
163 rdf:type schema:CreativeWork
164 https://doi.org/10.1016/j.jtcvs.2013.09.045 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036617948
165 rdf:type schema:CreativeWork
166 https://doi.org/10.1016/j.jtho.2016.10.017 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015044716
167 rdf:type schema:CreativeWork
168 https://doi.org/10.1016/j.media.2017.07.005 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090904008
169 rdf:type schema:CreativeWork
170 https://doi.org/10.1093/jnci/djt166 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006296938
171 rdf:type schema:CreativeWork
172 https://doi.org/10.1097/00000478-200301000-00011 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047643654
173 rdf:type schema:CreativeWork
174 https://doi.org/10.1097/jto.0000000000000630 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046335884
175 rdf:type schema:CreativeWork
176 https://doi.org/10.1097/jto.0b013e318206a221 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020132671
177 rdf:type schema:CreativeWork
178 https://doi.org/10.1097/jto.0b013e318221f701 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007371930
179 rdf:type schema:CreativeWork
180 https://doi.org/10.1097/pas.0000000000000134 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006699754
181 rdf:type schema:CreativeWork
182 https://doi.org/10.1097/pas.0000000000000246 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044077620
183 rdf:type schema:CreativeWork
184 https://doi.org/10.1097/pas.0b013e3181b8cf03 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030628930
185 rdf:type schema:CreativeWork
186 https://doi.org/10.1109/cvpr.2016.90 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093359587
187 rdf:type schema:CreativeWork
188 https://doi.org/10.1109/iccv.2015.123 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093828312
189 rdf:type schema:CreativeWork
190 https://doi.org/10.1109/iccv.2017.322 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060307
191 rdf:type schema:CreativeWork
192 https://doi.org/10.1111/pin.12016 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036686282
193 rdf:type schema:CreativeWork
194 https://doi.org/10.11613/bm.2012.031 schema:sameAs https://app.dimensions.ai/details/publication/pub.1063347969
195 rdf:type schema:CreativeWork
196 https://doi.org/10.1183/09031936.00219211 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010411029
197 rdf:type schema:CreativeWork
198 https://doi.org/10.1200/jco.2011.37.2185 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022128964
199 rdf:type schema:CreativeWork
200 https://doi.org/10.1200/jco.2014.58.8335 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042319271
201 rdf:type schema:CreativeWork
202 https://doi.org/10.1371/journal.pone.0121323 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025866605
203 rdf:type schema:CreativeWork
204 https://doi.org/10.3390/medsci5040034 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099651777
205 rdf:type schema:CreativeWork
206 https://doi.org/10.3414/me17-01-0039 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103283982
207 rdf:type schema:CreativeWork
208 https://doi.org/10.4103/jpi.jpi_34_17 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090898992
209 rdf:type schema:CreativeWork
210 https://doi.org/10.5858/arpa.2010-0493-oa schema:sameAs https://app.dimensions.ai/details/publication/pub.1000242468
211 rdf:type schema:CreativeWork
212 https://www.grid.ac/institutes/grid.254880.3 schema:alternateName Dartmouth College
213 schema:name Department of Biomedical Data Science, Dartmouth College, Hanover, NH, USA
214 Department of Computer Science, Dartmouth College, Hanover, NH, USA
215 Department of Epidemiology, Dartmouth College, Lebanon, NH, USA
216 rdf:type schema:Organization
217 https://www.grid.ac/institutes/grid.413480.a schema:alternateName Dartmouth–Hitchcock Medical Center
218 schema:name Department of Pathology and Laboratory Medicine, Dartmouth-Hitchcock Medical Center, Lebanon, NH, USA
219 rdf:type schema:Organization
 




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


...