View in EDS HTML Full Text PDF Full Text

Improving pose accuracy and geometry in neural radiance field‐based medical image synthesis.

Saved in:
Bibliographic Details
Title: Improving pose accuracy and geometry in neural radiance field‐based medical image synthesis.
Authors: Kabika, Twaha1 (AUTHOR), Hongsen, Cai1 (AUTHOR), Hongling, Zhu2 (AUTHOR), Jingxian, Dong1 (AUTHOR), Siyuan, Zhang1 (AUTHOR), Ding, Mingyue1 (AUTHOR), Xianbo, Deng3 (AUTHOR), Wenguang, Hou1 (AUTHOR) houwenguang99@163.com, Yan, Wang2 (AUTHOR) newswangyan@th.tjmu.edu.cn
Source: Medical Physics. Jul2025, Vol. 52 Issue 7, p1-16. 16p.
Subjects: Computed tomography, Rendering (Computer graphics), Posture, Anatomical specimens
Abstract: Background: Neural radiance field (NeRF) models have garnered significant attention for their impressive ability to synthesize high‐quality novel scene views from posed 2D images. Recently, the MedNeRF algorithm was developed to render complete computed tomography (CT) projections from a single or a few x‐ray images further. Despite this advancement, MedNeRF struggles with accurate pose reconstruction, crucial for radiologists during image analysis, leading to blurry geometry in the generated outputs. Purpose: Motivated by these challenges, our research aims to address MedNeRF's limitations in pose accuracy and image clarity. Specifically, we seek to improve the pose accuracy of reconstructed images and enhance the generated output's anatomical detail and quality. Methods: We propose a novel pose‐aware discriminator that estimates pose differences between generated and real patches, ensuring accurate poses and deeper anatomical structures in generated images. We enhance volumetric rendering from single‐view x‐rays by introducing a customized distortion adaptive loss function and present the HTDataset, a new dataset pair that better mimics machine‐generated x‐rays, offering clearer anatomical depictions with reduced noise. Results: Our method successfully renders images with correct poses and high fidelity, outperforming existing state‐of‐the‐art methods. The results demonstrate superior performance in both qualitative and quantitative metrics. Conclusions: The proposed approach addresses the pose reconstruction challenge in MedNeRF, enhances the anatomical detail, and reduces noise in generated images. The use of HTDataset and the innovative discriminator structure lead to significant improvements in the accuracy and quality of the rendered images, setting a new benchmark in the field. [ABSTRACT FROM AUTHOR]
Copyright of Medical Physics 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
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 186809869
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Improving pose accuracy and geometry in neural radiance field‐based medical image synthesis.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Kabika%2C+Twaha%22">Kabika, Twaha</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hongsen%2C+Cai%22">Hongsen, Cai</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hongling%2C+Zhu%22">Hongling, Zhu</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Jingxian%2C+Dong%22">Jingxian, Dong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Siyuan%2C+Zhang%22">Siyuan, Zhang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ding%2C+Mingyue%22">Ding, Mingyue</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xianbo%2C+Deng%22">Xianbo, Deng</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wenguang%2C+Hou%22">Wenguang, Hou</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> houwenguang99@163.com</i><br /><searchLink fieldCode="AR" term="%22Yan%2C+Wang%22">Yan, Wang</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> newswangyan@th.tjmu.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Medical+Physics%22">Medical Physics</searchLink>. Jul2025, Vol. 52 Issue 7, p1-16. 16p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Computed+tomography%22">Computed tomography</searchLink><br /><searchLink fieldCode="DE" term="%22Rendering+%28Computer+graphics%29%22">Rendering (Computer graphics)</searchLink><br /><searchLink fieldCode="DE" term="%22Posture%22">Posture</searchLink><br /><searchLink fieldCode="DE" term="%22Anatomical+specimens%22">Anatomical specimens</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Neural radiance field (NeRF) models have garnered significant attention for their impressive ability to synthesize high‐quality novel scene views from posed 2D images. Recently, the MedNeRF algorithm was developed to render complete computed tomography (CT) projections from a single or a few x‐ray images further. Despite this advancement, MedNeRF struggles with accurate pose reconstruction, crucial for radiologists during image analysis, leading to blurry geometry in the generated outputs. Purpose: Motivated by these challenges, our research aims to address MedNeRF's limitations in pose accuracy and image clarity. Specifically, we seek to improve the pose accuracy of reconstructed images and enhance the generated output's anatomical detail and quality. Methods: We propose a novel pose‐aware discriminator that estimates pose differences between generated and real patches, ensuring accurate poses and deeper anatomical structures in generated images. We enhance volumetric rendering from single‐view x‐rays by introducing a customized distortion adaptive loss function and present the HTDataset, a new dataset pair that better mimics machine‐generated x‐rays, offering clearer anatomical depictions with reduced noise. Results: Our method successfully renders images with correct poses and high fidelity, outperforming existing state‐of‐the‐art methods. The results demonstrate superior performance in both qualitative and quantitative metrics. Conclusions: The proposed approach addresses the pose reconstruction challenge in MedNeRF, enhances the anatomical detail, and reduces noise in generated images. The use of HTDataset and the innovative discriminator structure lead to significant improvements in the accuracy and quality of the rendered images, setting a new benchmark in the field. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Medical Physics 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.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=186809869
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/mp.17832
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 16
        StartPage: 1
    Subjects:
      – SubjectFull: Computed tomography
        Type: general
      – SubjectFull: Rendering (Computer graphics)
        Type: general
      – SubjectFull: Posture
        Type: general
      – SubjectFull: Anatomical specimens
        Type: general
    Titles:
      – TitleFull: Improving pose accuracy and geometry in neural radiance field‐based medical image synthesis.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kabika, Twaha
      – PersonEntity:
          Name:
            NameFull: Hongsen, Cai
      – PersonEntity:
          Name:
            NameFull: Hongling, Zhu
      – PersonEntity:
          Name:
            NameFull: Jingxian, Dong
      – PersonEntity:
          Name:
            NameFull: Siyuan, Zhang
      – PersonEntity:
          Name:
            NameFull: Ding, Mingyue
      – PersonEntity:
          Name:
            NameFull: Xianbo, Deng
      – PersonEntity:
          Name:
            NameFull: Wenguang, Hou
      – PersonEntity:
          Name:
            NameFull: Yan, Wang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 00942405
          Numbering:
            – Type: volume
              Value: 52
            – Type: issue
              Value: 7
          Titles:
            – TitleFull: Medical Physics
              Type: main
ResultId 1