View in EDS

Improving polyp detection algorithms for CT colonography: Pareto front approach

Saved in:
Bibliographic Details
Title: Improving polyp detection algorithms for CT colonography: Pareto front approach
Authors: Huang, Adam1,2, Li, Jiang1,3, Summers, Ronald M.1, Petrick, Nicholas4, Hara, Amy K.5
Source: Pattern Recognition Letters. Aug2010, Vol. 31 Issue 11, p1461-1469. 9p.
Subjects: POLYP (Computer system), Algorithms, Virtual colonoscopy, Performance evaluation, Pareto optimum, Evolutionary computation, Sensitivity analysis
Abstract: Abstract: We investigated a Pareto front approach to improve polyp detection algorithms for CT colonography (CTC). A dataset of 56 CTC colon surfaces with 87 proven positive detections of 53 polyps sized 4–60mm was used to evaluate the performance of a one-step and a two-step curvature-based region growing algorithm. The algorithmic performance was statistically evaluated and compared based on the Pareto optimal solutions from 20 experiments by evolutionary algorithms. The false positive rate was lower (p <0.05) by the two-step algorithm than by the one-step for 63% of all possible operating points. While operating at a suitable sensitivity level such as 90.8% (79/87) or 88.5% (77/87), the false positive rate was reduced by 24.4% (95% confidence intervals 17.9–31.0%) or 45.8% (95% confidence intervals 40.1–51.0%), respectively. We demonstrated that, with a proper experimental design, the Pareto optimization process can effectively help in fine-tuning and redesigning polyp detection algorithms. [Copyright &y& Elsevier]
Copyright of Pattern Recognition Letters is the property of Elsevier B.V. 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
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 51401516
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Improving polyp detection algorithms for CT colonography: Pareto front approach
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Huang%2C+Adam%22&quot;&gt;Huang, Adam&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Li%2C+Jiang%22&quot;&gt;Li, Jiang&lt;/searchLink&gt;&lt;relatesTo&gt;1,3&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Summers%2C+Ronald+M%2E%22&quot;&gt;Summers, Ronald M.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Petrick%2C+Nicholas%22&quot;&gt;Petrick, Nicholas&lt;/searchLink&gt;&lt;relatesTo&gt;4&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Hara%2C+Amy+K%2E%22&quot;&gt;Hara, Amy K.&lt;/searchLink&gt;&lt;relatesTo&gt;5&lt;/relatesTo&gt;
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22Pattern+Recognition+Letters%22&quot;&gt;Pattern Recognition Letters&lt;/searchLink&gt;. Aug2010, Vol. 31 Issue 11, p1461-1469. 9p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22POLYP+%28Computer+system%29%22&quot;&gt;POLYP (Computer system)&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Algorithms%22&quot;&gt;Algorithms&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Virtual+colonoscopy%22&quot;&gt;Virtual colonoscopy&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Performance+evaluation%22&quot;&gt;Performance evaluation&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Pareto+optimum%22&quot;&gt;Pareto optimum&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Evolutionary+computation%22&quot;&gt;Evolutionary computation&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Sensitivity+analysis%22&quot;&gt;Sensitivity analysis&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Abstract: We investigated a Pareto front approach to improve polyp detection algorithms for CT colonography (CTC). A dataset of 56 CTC colon surfaces with 87 proven positive detections of 53 polyps sized 4–60mm was used to evaluate the performance of a one-step and a two-step curvature-based region growing algorithm. The algorithmic performance was statistically evaluated and compared based on the Pareto optimal solutions from 20 experiments by evolutionary algorithms. The false positive rate was lower (p &lt;0.05) by the two-step algorithm than by the one-step for 63% of all possible operating points. While operating at a suitable sensitivity level such as 90.8% (79/87) or 88.5% (77/87), the false positive rate was reduced by 24.4% (95% confidence intervals 17.9–31.0%) or 45.8% (95% confidence intervals 40.1–51.0%), respectively. We demonstrated that, with a proper experimental design, the Pareto optimization process can effectively help in fine-tuning and redesigning polyp detection algorithms. [Copyright &amp;y&amp; Elsevier]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;Copyright of Pattern Recognition Letters is the property of Elsevier B.V. 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=51401516
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.patrec.2010.03.013
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 9
        StartPage: 1461
    Subjects:
      – SubjectFull: POLYP (Computer system)
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Virtual colonoscopy
        Type: general
      – SubjectFull: Performance evaluation
        Type: general
      – SubjectFull: Pareto optimum
        Type: general
      – SubjectFull: Evolutionary computation
        Type: general
      – SubjectFull: Sensitivity analysis
        Type: general
    Titles:
      – TitleFull: Improving polyp detection algorithms for CT colonography: Pareto front approach
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Huang, Adam
      – PersonEntity:
          Name:
            NameFull: Li, Jiang
      – PersonEntity:
          Name:
            NameFull: Summers, Ronald M.
      – PersonEntity:
          Name:
            NameFull: Petrick, Nicholas
      – PersonEntity:
          Name:
            NameFull: Hara, Amy K.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2010
              Type: published
              Y: 2010
          Identifiers:
            – Type: issn-print
              Value: 01678655
          Numbering:
            – Type: volume
              Value: 31
            – Type: issue
              Value: 11
          Titles:
            – TitleFull: Pattern Recognition Letters
              Type: main
ResultId 1