<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>8502</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>1</issue>
    <volume>3315</volume>
    <type>conferenceobject</type>
    <publisherName>AIP Publishing</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">BPConvNet: a deep learning based ρ-Filtered layergram reconstruction method for computed tomography</title>
    <abstract language="eng">In this article, we address the reconstruction problem in computed tomography (CT) when dealing with sparse view&#13;
data. Traditional approaches like filtered backprojection (FBP) often fail under these conditions, leading to streaking artifacts.&#13;
We propose BPConvNet, a deep learning based version of the ρ-filtered layergram or backprojection filtration (BPF) technique&#13;
(cf. [1]). Unlike FBP, the BPF method applies filtering (F) after backprojection (BP), hence the name. The proposed BPConvNet&#13;
adapts the BPF workflow by substituting the filtering step with a residual convolutional neural network. Our numerical experiments&#13;
demonstrate that BPConvNet is competitive to similar deep learning methods. Moreover, we explain that BPConvNet can be easily&#13;
adapted to to different CT acquisition geometries, such as fan beam and 3D configurations</abstract>
    <parentTitle language="eng">AIP Conference Proceedings</parentTitle>
    <identifier type="issn">0094-243X</identifier>
    <identifier type="doi">10.1063/5.0286063</identifier>
    <enrichment key="conference_title">International Conference of Numerical Analysis and Applied Mathematics (ICNAAM); 16-22 September 2025, Heraklion</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Patrick Bauer</author>
    <author>Jürgen Frikel</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Convolutional neural network</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Deep learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Learning and learning models</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Computed tomography</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="DFGFachsystematik" number="4">Naturwissenschaften</collection>
    <collection role="othforschungsschwerpunkt" number="">Digitale Transformation</collection>
  </doc>
</export-example>
