View in EDS HTML Full Text PDF Full Text

Population-wide evaluation of artificial intelligence and radiologist assessment of screening mammograms.

Saved in:
Bibliographic Details
Title: Population-wide evaluation of artificial intelligence and radiologist assessment of screening mammograms.
Authors: Kühl, Johanne1 (AUTHOR), Elhakim, Mohammad Talal1,2 (AUTHOR) mte@rsyd.dk, Stougaard, Sarah Wordenskjold1 (AUTHOR), Rasmussen, Benjamin Schnack Brandt1,2,3 (AUTHOR), Nielsen, Mads4 (AUTHOR), Gerke, Oke1,5 (AUTHOR), Larsen, Lisbet Brønsro2 (AUTHOR), Graumann, Ole1,6,7 (AUTHOR)
Source: European Radiology. Jun2024, Vol. 34 Issue 6, p3935-3946. 12p.
Subjects: Medical screening, Artificial intelligence, Mammograms, Radiologists, Early detection of cancer
Geographic Terms: Denmark
Abstract: Objectives: To validate an AI system for standalone breast cancer detection on an entire screening population in comparison to first-reading breast radiologists. Materials and methods: All mammography screenings performed between August 4, 2014, and August 15, 2018, in the Region of Southern Denmark with follow-up within 24 months were eligible. Screenings were assessed as normal or abnormal by breast radiologists through double reading with arbitration. For an AI decision of normal or abnormal, two AI-score cut-off points were applied by matching at mean sensitivity (AIsens) and specificity (AIspec) of first readers. Accuracy measures were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and recall rate (RR). Results: The sample included 249,402 screenings (149,495 women) and 2033 breast cancers (72.6% screen-detected cancers, 27.4% interval cancers). AIsens had lower specificity (97.5% vs 97.7%; p < 0.0001) and PPV (17.5% vs 18.7%; p = 0.01) and a higher RR (3.0% vs 2.8%; p < 0.0001) than first readers. AIspec was comparable to first readers in terms of all accuracy measures. Both AIsens and AIspec detected significantly fewer screen-detected cancers (1166 (AIsens), 1156 (AIspec) vs 1252; p < 0.0001) but found more interval cancers compared to first readers (126 (AIsens), 117 (AIspec) vs 39; p < 0.0001) with varying types of cancers detected across multiple subgroups. Conclusion: Standalone AI can detect breast cancer at an accuracy level equivalent to the standard of first readers when the AI threshold point was matched at first reader specificity. However, AI and first readers detected a different composition of cancers. Clinical relevance statement: Replacing first readers with AI with an appropriate cut-off score could be feasible. AI-detected cancers not detected by radiologists suggest a potential increase in the number of cancers detected if AI is implemented to support double reading within screening, although the clinicopathological characteristics of detected cancers would not change significantly. Key Points: • Standalone AI cancer detection was compared to first readers in a double-read mammography screening population. • Standalone AI matched at first reader specificity showed no statistically significant difference in overall accuracy but detected different cancers. • With an appropriate threshold, AI-integrated screening can increase the number of detected cancers with similar clinicopathological characteristics. [ABSTRACT FROM AUTHOR]
Copyright of European Radiology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 177797500
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Population-wide evaluation of artificial intelligence and radiologist assessment of screening mammograms.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22K&#252;hl%2C+Johanne%22&quot;&gt;K&#252;hl, Johanne&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Elhakim%2C+Mohammad+Talal%22&quot;&gt;Elhakim, Mohammad Talal&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; mte@rsyd.dk&lt;/i&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Stougaard%2C+Sarah+Wordenskjold%22&quot;&gt;Stougaard, Sarah Wordenskjold&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Rasmussen%2C+Benjamin+Schnack+Brandt%22&quot;&gt;Rasmussen, Benjamin Schnack Brandt&lt;/searchLink&gt;&lt;relatesTo&gt;1,2,3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Nielsen%2C+Mads%22&quot;&gt;Nielsen, Mads&lt;/searchLink&gt;&lt;relatesTo&gt;4&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Gerke%2C+Oke%22&quot;&gt;Gerke, Oke&lt;/searchLink&gt;&lt;relatesTo&gt;1,5&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Larsen%2C+Lisbet+Br&#248;nsro%22&quot;&gt;Larsen, Lisbet Br&#248;nsro&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Graumann%2C+Ole%22&quot;&gt;Graumann, Ole&lt;/searchLink&gt;&lt;relatesTo&gt;1,6,7&lt;/relatesTo&gt; (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22European+Radiology%22&quot;&gt;European Radiology&lt;/searchLink&gt;. Jun2024, Vol. 34 Issue 6, p3935-3946. 12p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Medical+screening%22&quot;&gt;Medical screening&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Artificial+intelligence%22&quot;&gt;Artificial intelligence&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Mammograms%22&quot;&gt;Mammograms&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Radiologists%22&quot;&gt;Radiologists&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Early+detection+of+cancer%22&quot;&gt;Early detection of cancer&lt;/searchLink&gt;
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Denmark%22&quot;&gt;Denmark&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Objectives: To validate an AI system for standalone breast cancer detection on an entire screening population in comparison to first-reading breast radiologists. Materials and methods: All mammography screenings performed between August 4, 2014, and August 15, 2018, in the Region of Southern Denmark with follow-up within 24 months were eligible. Screenings were assessed as normal or abnormal by breast radiologists through double reading with arbitration. For an AI decision of normal or abnormal, two AI-score cut-off points were applied by matching at mean sensitivity (AIsens) and specificity (AIspec) of first readers. Accuracy measures were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and recall rate (RR). Results: The sample included 249,402 screenings (149,495 women) and 2033 breast cancers (72.6% screen-detected cancers, 27.4% interval cancers). AIsens had lower specificity (97.5% vs 97.7%; p &lt; 0.0001) and PPV (17.5% vs 18.7%; p = 0.01) and a higher RR (3.0% vs 2.8%; p &lt; 0.0001) than first readers. AIspec was comparable to first readers in terms of all accuracy measures. Both AIsens and AIspec detected significantly fewer screen-detected cancers (1166 (AIsens), 1156 (AIspec) vs 1252; p &lt; 0.0001) but found more interval cancers compared to first readers (126 (AIsens), 117 (AIspec) vs 39; p &lt; 0.0001) with varying types of cancers detected across multiple subgroups. Conclusion: Standalone AI can detect breast cancer at an accuracy level equivalent to the standard of first readers when the AI threshold point was matched at first reader specificity. However, AI and first readers detected a different composition of cancers. Clinical relevance statement: Replacing first readers with AI with an appropriate cut-off score could be feasible. AI-detected cancers not detected by radiologists suggest a potential increase in the number of cancers detected if AI is implemented to support double reading within screening, although the clinicopathological characteristics of detected cancers would not change significantly. Key Points: • Standalone AI cancer detection was compared to first readers in a double-read mammography screening population. • Standalone AI matched at first reader specificity showed no statistically significant difference in overall accuracy but detected different cancers. • With an appropriate threshold, AI-integrated screening can increase the number of detected cancers with similar clinicopathological characteristics. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;Copyright of European Radiology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder&#39;s express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.&lt;/i&gt; (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=177797500
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00330-023-10423-7
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 3935
    Subjects:
      – SubjectFull: Medical screening
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Mammograms
        Type: general
      – SubjectFull: Radiologists
        Type: general
      – SubjectFull: Early detection of cancer
        Type: general
      – SubjectFull: Denmark
        Type: general
    Titles:
      – TitleFull: Population-wide evaluation of artificial intelligence and radiologist assessment of screening mammograms.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kühl, Johanne
      – PersonEntity:
          Name:
            NameFull: Elhakim, Mohammad Talal
      – PersonEntity:
          Name:
            NameFull: Stougaard, Sarah Wordenskjold
      – PersonEntity:
          Name:
            NameFull: Rasmussen, Benjamin Schnack Brandt
      – PersonEntity:
          Name:
            NameFull: Nielsen, Mads
      – PersonEntity:
          Name:
            NameFull: Gerke, Oke
      – PersonEntity:
          Name:
            NameFull: Larsen, Lisbet Brønsro
      – PersonEntity:
          Name:
            NameFull: Graumann, Ole
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 09387994
          Numbering:
            – Type: volume
              Value: 34
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: European Radiology
              Type: main
ResultId 1