View in EDS

Brain MRI-based Wilson disease tissue classification: an optimised deep transfer learning approach.

Saved in:
Bibliographic Details
Title: Brain MRI-based Wilson disease tissue classification: an optimised deep transfer learning approach.
Authors: Saba, L.1, Agarwal, M.2, Sanagala, S. S.3, Gupta, S. K.2, Sinha, G. R.4, Johri, A. M.5, Khanna, N. N.6, Mavrogeni, S.7, Laird, J. R.8, Pareek, G.9, Miner, M.10, Sfikakis, P. P.11, Protogerou, A.12, Viswanathan, V.13, Kitas, G. D.14, Suri, J. S.15 Jasjit.Suri@AtheroPoint.com
Source: Electronics Letters (Wiley-Blackwell). 12/10/2020, Vol. 56 Issue 25, p1395-1398. 3p.
Subjects: Deep learning, Nosology, Hepatolenticular degeneration, White matter (Nerve tissue), Random forest algorithms
Abstract: Wilson's disease (WD) is caused by the excessive accumulation of copper in the brain and liver, leading to death if not diagnosed early. WD shows its prevalence as white matter hyperintensity (WMH) in MRI scans. It is challenging and tedious to classify WD against controls when comparing visually, primarily due to subtle differences in WMH. This Letter presents a computer-aided design-based automated classification strategy that uses optimised transfer learning (TL) utilising two novel paradigms known as (i) MobileNet and (ii) the Visual Geometric Group-19 (VGG-19). Further, the authors benchmark TL systems against a machine learning (ML) paradigm. Using four-fold augmentation, VGG-19 is superior to MobileNet demonstrating accuracy and area under the curve (AUC) pairs as 95.46 ± 7.70%, 0.932 (p < 0.0001) and 86.87 ± 2.23%, 0.871 (p < 0.0001), respectively. Further, MobileNet and VGG-19 showed an improvement of 3.4 and 13.5%, respectively, when benchmarked against the ML-based soft classifier – Random Forest. [ABSTRACT FROM AUTHOR]
Copyright of Electronics Letters (Wiley-Blackwell) is the property of Wiley-Blackwell 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: 147955251
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Brain MRI-based Wilson disease tissue classification: an optimised deep transfer learning approach.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Saba%2C+L%2E%22&quot;&gt;Saba, L.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Agarwal%2C+M%2E%22&quot;&gt;Agarwal, M.&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Sanagala%2C+S%2E+S%2E%22&quot;&gt;Sanagala, S. S.&lt;/searchLink&gt;&lt;relatesTo&gt;3&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Gupta%2C+S%2E+K%2E%22&quot;&gt;Gupta, S. K.&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Sinha%2C+G%2E+R%2E%22&quot;&gt;Sinha, G. R.&lt;/searchLink&gt;&lt;relatesTo&gt;4&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Johri%2C+A%2E+M%2E%22&quot;&gt;Johri, A. M.&lt;/searchLink&gt;&lt;relatesTo&gt;5&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Khanna%2C+N%2E+N%2E%22&quot;&gt;Khanna, N. N.&lt;/searchLink&gt;&lt;relatesTo&gt;6&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Mavrogeni%2C+S%2E%22&quot;&gt;Mavrogeni, S.&lt;/searchLink&gt;&lt;relatesTo&gt;7&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Laird%2C+J%2E+R%2E%22&quot;&gt;Laird, J. R.&lt;/searchLink&gt;&lt;relatesTo&gt;8&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Pareek%2C+G%2E%22&quot;&gt;Pareek, G.&lt;/searchLink&gt;&lt;relatesTo&gt;9&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Miner%2C+M%2E%22&quot;&gt;Miner, M.&lt;/searchLink&gt;&lt;relatesTo&gt;10&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Sfikakis%2C+P%2E+P%2E%22&quot;&gt;Sfikakis, P. P.&lt;/searchLink&gt;&lt;relatesTo&gt;11&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Protogerou%2C+A%2E%22&quot;&gt;Protogerou, A.&lt;/searchLink&gt;&lt;relatesTo&gt;12&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Viswanathan%2C+V%2E%22&quot;&gt;Viswanathan, V.&lt;/searchLink&gt;&lt;relatesTo&gt;13&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Kitas%2C+G%2E+D%2E%22&quot;&gt;Kitas, G. D.&lt;/searchLink&gt;&lt;relatesTo&gt;14&lt;/relatesTo&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Suri%2C+J%2E+S%2E%22&quot;&gt;Suri, J. S.&lt;/searchLink&gt;&lt;relatesTo&gt;15&lt;/relatesTo&gt;&lt;i&gt; Jasjit.Suri@AtheroPoint.com&lt;/i&gt;
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22Electronics+Letters+%28Wiley-Blackwell%29%22&quot;&gt;Electronics Letters (Wiley-Blackwell)&lt;/searchLink&gt;. 12/10/2020, Vol. 56 Issue 25, p1395-1398. 3p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Deep+learning%22&quot;&gt;Deep learning&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Nosology%22&quot;&gt;Nosology&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Hepatolenticular+degeneration%22&quot;&gt;Hepatolenticular degeneration&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22White+matter+%28Nerve+tissue%29%22&quot;&gt;White matter (Nerve tissue)&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Random+forest+algorithms%22&quot;&gt;Random forest algorithms&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Wilson&#39;s disease (WD) is caused by the excessive accumulation of copper in the brain and liver, leading to death if not diagnosed early. WD shows its prevalence as white matter hyperintensity (WMH) in MRI scans. It is challenging and tedious to classify WD against controls when comparing visually, primarily due to subtle differences in WMH. This Letter presents a computer-aided design-based automated classification strategy that uses optimised transfer learning (TL) utilising two novel paradigms known as (i) MobileNet and (ii) the Visual Geometric Group-19 (VGG-19). Further, the authors benchmark TL systems against a machine learning (ML) paradigm. Using four-fold augmentation, VGG-19 is superior to MobileNet demonstrating accuracy and area under the curve (AUC) pairs as 95.46 &#177; 7.70%, 0.932 (p &lt; 0.0001) and 86.87 &#177; 2.23%, 0.871 (p &lt; 0.0001), respectively. Further, MobileNet and VGG-19 showed an improvement of 3.4 and 13.5%, respectively, when benchmarked against the ML-based soft classifier – Random Forest. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;Copyright of Electronics Letters (Wiley-Blackwell) is the property of Wiley-Blackwell 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=147955251
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1049/el.2020.2102
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 3
        StartPage: 1395
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Nosology
        Type: general
      – SubjectFull: Hepatolenticular degeneration
        Type: general
      – SubjectFull: White matter (Nerve tissue)
        Type: general
      – SubjectFull: Random forest algorithms
        Type: general
    Titles:
      – TitleFull: Brain MRI-based Wilson disease tissue classification: an optimised deep transfer learning approach.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Saba, L.
      – PersonEntity:
          Name:
            NameFull: Agarwal, M.
      – PersonEntity:
          Name:
            NameFull: Sanagala, S. S.
      – PersonEntity:
          Name:
            NameFull: Gupta, S. K.
      – PersonEntity:
          Name:
            NameFull: Sinha, G. R.
      – PersonEntity:
          Name:
            NameFull: Johri, A. M.
      – PersonEntity:
          Name:
            NameFull: Khanna, N. N.
      – PersonEntity:
          Name:
            NameFull: Mavrogeni, S.
      – PersonEntity:
          Name:
            NameFull: Laird, J. R.
      – PersonEntity:
          Name:
            NameFull: Pareek, G.
      – PersonEntity:
          Name:
            NameFull: Miner, M.
      – PersonEntity:
          Name:
            NameFull: Sfikakis, P. P.
      – PersonEntity:
          Name:
            NameFull: Protogerou, A.
      – PersonEntity:
          Name:
            NameFull: Viswanathan, V.
      – PersonEntity:
          Name:
            NameFull: Kitas, G. D.
      – PersonEntity:
          Name:
            NameFull: Suri, J. S.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 10
              M: 12
              Text: 12/10/2020
              Type: published
              Y: 2020
          Identifiers:
            – Type: issn-print
              Value: 00135194
          Numbering:
            – Type: volume
              Value: 56
            – Type: issue
              Value: 25
          Titles:
            – TitleFull: Electronics Letters (Wiley-Blackwell)
              Type: main
ResultId 1