View in EDS HTML Full Text PDF Full Text

Can incorporating image resolution into neural networks improve kidney tumor classification performance in ultrasound images?

Saved in:
Bibliographic Details
Title: Can incorporating image resolution into neural networks improve kidney tumor classification performance in ultrasound images?
Authors: He, Haihao1,2 (AUTHOR), Liu, Yuhan3 (AUTHOR), Zhou, Xin1,2 (AUTHOR), Zhan, Jia3 (AUTHOR), Wang, Changyan1,2 (AUTHOR), Shen, Yiwen1,2 (AUTHOR), Chen, Haobo1,2 (AUTHOR), Chen, Lin3 (AUTHOR) linchen11@fudan.edu.cn, Zhang, Qi1,2 (AUTHOR) zhangq@t.shu.edu.cn
Source: Medical & Biological Engineering & Computing. Aug2026, Vol. 64 Issue 8, p2889-2901. 13p.
Subjects: Convolutional neural networks, Spatial resolution, Deep learning, Kidney tumors, Image segmentation, Benign tumors, Receiver operating characteristic curves
Abstract: Deep learning has been widely used in ultrasound image analysis, and it also benefits kidney ultrasound interpretation and diagnosis. However, the importance of ultrasound image resolution often goes overlooked within deep learning methodologies. In this study, we integrate the ultrasound image resolution into a convolutional neural network and explore the effect of the resolution on diagnosis of kidney tumors. In the process of integrating the image resolution information, we propose two different approaches to narrow the semantic gap between the features extracted by the neural network and the resolution features. In the first approach, the resolution is directly concatenated with the features extracted by the neural network. In the second approach, the features extracted by the neural network are first dimensionally reduced and then combined with the resolution features to form new composite features. We compare these two approaches incorporating the resolution with the method without incorporating the resolution on a kidney tumor dataset of 926 images consisting of 211 images of benign kidney tumors and 715 images of malignant kidney tumors. The area under the receiver operating characteristic curve (AUC) of the method without incorporating the resolution is 0.8665, and the AUCs of the two approaches incorporating the resolution are 0.8926 (P < 0.0001) and 0.9135 (P < 0.0001) respectively. This study has established end-to-end kidney tumor classification systems and has demonstrated the benefits of integrating image resolution, showing that incorporating image resolution into neural networks can more accurately distinguish between malignant and benign kidney tumors in ultrasound images. [ABSTRACT FROM AUTHOR]
Copyright of Medical & Biological Engineering & Computing 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: 197537773
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Can incorporating image resolution into neural networks improve kidney tumor classification performance in ultrasound images?
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22He%2C+Haihao%22&quot;&gt;He, Haihao&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Liu%2C+Yuhan%22&quot;&gt;Liu, Yuhan&lt;/searchLink&gt;&lt;relatesTo&gt;3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Zhou%2C+Xin%22&quot;&gt;Zhou, Xin&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Zhan%2C+Jia%22&quot;&gt;Zhan, Jia&lt;/searchLink&gt;&lt;relatesTo&gt;3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Wang%2C+Changyan%22&quot;&gt;Wang, Changyan&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Shen%2C+Yiwen%22&quot;&gt;Shen, Yiwen&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Chen%2C+Haobo%22&quot;&gt;Chen, Haobo&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Chen%2C+Lin%22&quot;&gt;Chen, Lin&lt;/searchLink&gt;&lt;relatesTo&gt;3&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; linchen11@fudan.edu.cn&lt;/i&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Zhang%2C+Qi%22&quot;&gt;Zhang, Qi&lt;/searchLink&gt;&lt;relatesTo&gt;1,2&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; zhangq@t.shu.edu.cn&lt;/i&gt;
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22Medical+%26+Biological+Engineering+%26+Computing%22&quot;&gt;Medical &amp; Biological Engineering &amp; Computing&lt;/searchLink&gt;. Aug2026, Vol. 64 Issue 8, p2889-2901. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Convolutional+neural+networks%22&quot;&gt;Convolutional neural networks&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Spatial+resolution%22&quot;&gt;Spatial resolution&lt;/searchLink&gt;&lt;br /&gt;&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;%22Kidney+tumors%22&quot;&gt;Kidney tumors&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Image+segmentation%22&quot;&gt;Image segmentation&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Benign+tumors%22&quot;&gt;Benign tumors&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Receiver+operating+characteristic+curves%22&quot;&gt;Receiver operating characteristic curves&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Deep learning has been widely used in ultrasound image analysis, and it also benefits kidney ultrasound interpretation and diagnosis. However, the importance of ultrasound image resolution often goes overlooked within deep learning methodologies. In this study, we integrate the ultrasound image resolution into a convolutional neural network and explore the effect of the resolution on diagnosis of kidney tumors. In the process of integrating the image resolution information, we propose two different approaches to narrow the semantic gap between the features extracted by the neural network and the resolution features. In the first approach, the resolution is directly concatenated with the features extracted by the neural network. In the second approach, the features extracted by the neural network are first dimensionally reduced and then combined with the resolution features to form new composite features. We compare these two approaches incorporating the resolution with the method without incorporating the resolution on a kidney tumor dataset of 926 images consisting of 211 images of benign kidney tumors and 715 images of malignant kidney tumors. The area under the receiver operating characteristic curve (AUC) of the method without incorporating the resolution is 0.8665, and the AUCs of the two approaches incorporating the resolution are 0.8926 (P &lt; 0.0001) and 0.9135 (P &lt; 0.0001) respectively. This study has established end-to-end kidney tumor classification systems and has demonstrated the benefits of integrating image resolution, showing that incorporating image resolution into neural networks can more accurately distinguish between malignant and benign kidney tumors in ultrasound images. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;Copyright of Medical &amp; Biological Engineering &amp; Computing 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=197537773
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11517-024-03188-8
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 2889
    Subjects:
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Spatial resolution
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Kidney tumors
        Type: general
      – SubjectFull: Image segmentation
        Type: general
      – SubjectFull: Benign tumors
        Type: general
      – SubjectFull: Receiver operating characteristic curves
        Type: general
    Titles:
      – TitleFull: Can incorporating image resolution into neural networks improve kidney tumor classification performance in ultrasound images?
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: He, Haihao
      – PersonEntity:
          Name:
            NameFull: Liu, Yuhan
      – PersonEntity:
          Name:
            NameFull: Zhou, Xin
      – PersonEntity:
          Name:
            NameFull: Zhan, Jia
      – PersonEntity:
          Name:
            NameFull: Wang, Changyan
      – PersonEntity:
          Name:
            NameFull: Shen, Yiwen
      – PersonEntity:
          Name:
            NameFull: Chen, Haobo
      – PersonEntity:
          Name:
            NameFull: Chen, Lin
      – PersonEntity:
          Name:
            NameFull: Zhang, Qi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 01400118
          Numbering:
            – Type: volume
              Value: 64
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: Medical & Biological Engineering & Computing
              Type: main
ResultId 1