View in EDS HTML Full Text PDF Full Text

Hepatocellular carcinoma 18F‐FDG PET/CT kinetic parameter estimation based on the advantage actor‐critic algorithm.

Saved in:
Bibliographic Details
Title: Hepatocellular carcinoma 18F‐FDG PET/CT kinetic parameter estimation based on the advantage actor‐critic algorithm.
Authors: He, Jianfeng1 (AUTHOR), Li, Siming1 (AUTHOR), Xiong, Yiwei1 (AUTHOR), Yao, Yu1 (AUTHOR), Wang, Siyu2 (AUTHOR), Wang, Sidan2 (AUTHOR), Wang, Shaobo2 (AUTHOR) wshbo_98@126.com
Source: Medical Physics. Jul2025, Vol. 52 Issue 7, p1-12. 12p.
Subjects: Hepatocellular carcinoma, Reinforcement learning, Macroscopic kinetics, Computer-assisted image analysis (Medicine), Least squares
Abstract: Background: Kinetic parameters estimated with dynamic 18F‐fluorodeoxyglucose (18F‐FDG) positron emission tomography (PET)/computed tomography (CT) help characterize hepatocellular carcinoma (HCC), and deep reinforcement learning (DRL) can improve kinetic parameter estimation. Purpose: The advantage actor‐critic (A2C) algorithm is a DRL algorithm with neural networks that seek the optimal parameters. The aim of this study was to preliminarily assess the role of the A2C algorithm in estimating the kinetic parameters of 18F‐FDG PET/CT in patients with HCC. Materials and Methods: 18F‐FDG PET data from 14 liver tissues and 17 HCC tumors obtained via a previously developed, abbreviated acquisition protocol (5‐min dynamic PET/CT imaging supplemented with 1‐min static imaging at 60 min) were prospectively collected. The A2C algorithm was used to estimate kinetic parameters with a reversible double‐input, three‐compartment model, and the results were compared with those of the conventional nonlinear least squares (NLLS) algorithm. Fitting errors were compared via the root‐mean‐square errors (RMSEs) of the time activity curves (TACs). Results: Significant differences in K1, k2, k3, k4, fa, and vb according to the A2C algorithm and k3, fa, and vb according to the NLLS algorithm were detected between HCC and normal liver tissues (all p < 0.05). Furthermore, A2C demonstrated superior diagnostic performance over NLLS in terms of k3 and vb (both p < 0.05 in the Delong test). Notably, A2C yielded a smaller fitting error for normal liver tissue (0.62 ± 0.24 vs. 1.04 ± 1.00) and HCC tissue (1.40 ± 0.42 vs. 1.51 ± 0.97) than did NLLS. Conclusions: Compared with the conventional postreconstruction NLLS method, the A2C algorithm can more precisely estimate 18F‐FDG kinetic parameters with a reversible double‐input, three‐compartment model for HCC tumors, attaining better TAC fitting with a lower RMSE. [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: 186809883
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Hepatocellular carcinoma &lt;superscript&gt;18&lt;/superscript&gt;F‐FDG PET/CT kinetic parameter estimation based on the advantage actor‐critic algorithm.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22He%2C+Jianfeng%22&quot;&gt;He, Jianfeng&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Li%2C+Siming%22&quot;&gt;Li, Siming&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Xiong%2C+Yiwei%22&quot;&gt;Xiong, Yiwei&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Yao%2C+Yu%22&quot;&gt;Yao, Yu&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Wang%2C+Siyu%22&quot;&gt;Wang, Siyu&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Wang%2C+Sidan%22&quot;&gt;Wang, Sidan&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Wang%2C+Shaobo%22&quot;&gt;Wang, Shaobo&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; wshbo_98@126.com&lt;/i&gt;
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22Medical+Physics%22&quot;&gt;Medical Physics&lt;/searchLink&gt;. Jul2025, Vol. 52 Issue 7, p1-12. 12p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Hepatocellular+carcinoma%22&quot;&gt;Hepatocellular carcinoma&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Reinforcement+learning%22&quot;&gt;Reinforcement learning&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Macroscopic+kinetics%22&quot;&gt;Macroscopic kinetics&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Computer-assisted+image+analysis+%28Medicine%29%22&quot;&gt;Computer-assisted image analysis (Medicine)&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Least+squares%22&quot;&gt;Least squares&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Kinetic parameters estimated with dynamic 18F‐fluorodeoxyglucose (18F‐FDG) positron emission tomography (PET)/computed tomography (CT) help characterize hepatocellular carcinoma (HCC), and deep reinforcement learning (DRL) can improve kinetic parameter estimation. Purpose: The advantage actor‐critic (A2C) algorithm is a DRL algorithm with neural networks that seek the optimal parameters. The aim of this study was to preliminarily assess the role of the A2C algorithm in estimating the kinetic parameters of 18F‐FDG PET/CT in patients with HCC. Materials and Methods: 18F‐FDG PET data from 14 liver tissues and 17 HCC tumors obtained via a previously developed, abbreviated acquisition protocol (5‐min dynamic PET/CT imaging supplemented with 1‐min static imaging at 60 min) were prospectively collected. The A2C algorithm was used to estimate kinetic parameters with a reversible double‐input, three‐compartment model, and the results were compared with those of the conventional nonlinear least squares (NLLS) algorithm. Fitting errors were compared via the root‐mean‐square errors (RMSEs) of the time activity curves (TACs). Results: Significant differences in K1, k2, k3, k4, fa, and vb according to the A2C algorithm and k3, fa, and vb according to the NLLS algorithm were detected between HCC and normal liver tissues (all p &lt; 0.05). Furthermore, A2C demonstrated superior diagnostic performance over NLLS in terms of k3 and vb (both p &lt; 0.05 in the Delong test). Notably, A2C yielded a smaller fitting error for normal liver tissue (0.62 &#177; 0.24 vs. 1.04 &#177; 1.00) and HCC tissue (1.40 &#177; 0.42 vs. 1.51 &#177; 0.97) than did NLLS. Conclusions: Compared with the conventional postreconstruction NLLS method, the A2C algorithm can more precisely estimate 18F‐FDG kinetic parameters with a reversible double‐input, three‐compartment model for HCC tumors, attaining better TAC fitting with a lower RMSE. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;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&#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=186809883
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/mp.17851
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 1
    Subjects:
      – SubjectFull: Hepatocellular carcinoma
        Type: general
      – SubjectFull: Reinforcement learning
        Type: general
      – SubjectFull: Macroscopic kinetics
        Type: general
      – SubjectFull: Computer-assisted image analysis (Medicine)
        Type: general
      – SubjectFull: Least squares
        Type: general
    Titles:
      – TitleFull: Hepatocellular carcinoma 18F‐FDG PET/CT kinetic parameter estimation based on the advantage actor‐critic algorithm.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: He, Jianfeng
      – PersonEntity:
          Name:
            NameFull: Li, Siming
      – PersonEntity:
          Name:
            NameFull: Xiong, Yiwei
      – PersonEntity:
          Name:
            NameFull: Yao, Yu
      – PersonEntity:
          Name:
            NameFull: Wang, Siyu
      – PersonEntity:
          Name:
            NameFull: Wang, Sidan
      – PersonEntity:
          Name:
            NameFull: Wang, Shaobo
    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