<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>8471</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>36</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>preprint</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge</title>
    <abstract language="eng">Reliable recognition and localization of surgical instruments in endoscopic video recordings are foundational for a wide range of applications in computer- and robot-assisted minimally invasive surgery (RAMIS), including surgical training, skill assessment, and autonomous assistance. However, robust performance under real-world conditions remains a significant challenge. Incorporating surgical context - such as the current procedural phase - has emerged as a promising strategy to improve robustness and interpretability. To address these challenges, we organized the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) sub-challenge as part of the Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We introduced a novel, multi-center dataset comprising thirteen full-length laparoscopic cholecystectomy videos collected from three distinct medical institutions, with unified annotations for three interrelated tasks: surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation. Unlike existing datasets, ours enables joint investigation of instrument localization and procedural context within the same data while supporting the integration of temporal information across entire procedures. We report results and findings in accordance with the BIAS guidelines for biomedical image analysis challenges. The PhaKIR sub-challenge advances the field by providing a unique benchmark for developing temporally aware, context-driven methods in RAMIS and offers a high-quality resource to support future research in surgical scene understanding.</abstract>
    <identifier type="arxiv">2507.16559</identifier>
    <note>Der Aufsatz wurde peer-reviewed veröffentlicht und ist ebenfalls in diesem Repositorium verzeichnet unter: https://opus4.kobv.de/opus4-oth-regensburg/frontdoor/index/index/start/0/rows/10/sortfield/score/sortorder/desc/searchtype/simple/query/10.1016%2Fj.media.2026.103945/docId/8846</note>
    <enrichment key="opus.import.date">2025-08-11T19:43:46+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <licence>Creative Commons - CC BY-NC-SA - Namensnennung - Nicht kommerziell -  Weitergabe unter gleichen Bedingungen 4.0 International</licence>
    <author>Tobias Rückert</author>
    <author>David Rauber</author>
    <author>Raphaela Maerkl</author>
    <author>Leonard Klausmann</author>
    <author>Suemeyye R. Yildiran</author>
    <author>Max Gutbrod</author>
    <author>Danilo Weber Nunes</author>
    <author>Alvaro Fernandez Moreno</author>
    <author>Imanol Luengo</author>
    <author>Danail Stoyanov</author>
    <author>Nicolas Toussaint</author>
    <author>Enki Cho</author>
    <author>Hyeon Bae Kim</author>
    <author>Oh Sung Choo</author>
    <author>Ka Young Kim</author>
    <author>Seong Tae Kim</author>
    <author>Gonçalo Arantes</author>
    <author>Kehan Song</author>
    <author>Jianjun Zhu</author>
    <author>Junchen Xiong</author>
    <author>Tingyi Lin</author>
    <author>Shunsuke Kikuchi</author>
    <author>Hiroki Matsuzaki</author>
    <author>Atsushi Kouno</author>
    <author>João Renato Ribeiro Manesco</author>
    <author>João Paulo Papa</author>
    <author>Tae-Min Choi</author>
    <author>Tae Kyeong Jeong</author>
    <author>Juyoun Park</author>
    <author>Oluwatosin Alabi</author>
    <author>Meng Wei</author>
    <author>Tom Vercauteren</author>
    <author>Runzhi Wu</author>
    <author>Mengya Xu</author>
    <author> an Wang</author>
    <author>Long Bai</author>
    <author>Hongliang Ren</author>
    <author>Amine Yamlahi</author>
    <author>Jakob Hennighausen</author>
    <author>Lena Maier-Hein</author>
    <author>Satoshi Kondo</author>
    <author>Satoshi Kasai</author>
    <author>Kousuke Hirasawa</author>
    <author>Shu Yang</author>
    <author>Yihui Wang</author>
    <author>Hao Chen</author>
    <author>Santiago Rodríguez</author>
    <author>Nicolás Aparicio</author>
    <author>Leonardo Manrique</author>
    <author>Juan Camilo Lyons</author>
    <author>Olivia Hosie</author>
    <author>Nicolás Ayobi</author>
    <author>Pablo Arbeláez</author>
    <author>Yiping Li</author>
    <author>Yasmina Al Khalil</author>
    <author>Sahar Nasirihaghighi</author>
    <author>Stefanie Speidel</author>
    <author>Daniel Rückert</author>
    <author>Hubertus Feussner</author>
    <author>Dirk Wilhelm</author>
    <author>Christoph Palm</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="institutes" number="RCBE">Regensburg Center of Biomedical Engineering - RCBE</collection>
    <collection role="institutes" number="RCHST">Regensburg Center of Health Sciences and Technology - RCHST</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
    <collection role="DFGFachsystematik" number="1">Ingenieurwissenschaften</collection>
    <collection role="othforschungsschwerpunkt" number="">Gesundheit und Soziales</collection>
  </doc>
  <doc>
    <id>8846</id>
    <completedYear/>
    <publishedYear>2026</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>31</pageNumber>
    <edition/>
    <issue/>
    <volume>109</volume>
    <type>article</type>
    <publisherName>Elsevier</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge</title>
    <abstract language="eng">Reliable recognition and localization of surgical instruments in endoscopic video recordings are foundational for a wide range of applications in computer- and robot-assisted minimally invasive surgery (RAMIS), including surgical training, skill assessment, and autonomous assistance. However, robust performance under real-world conditions remains a significant challenge. Incorporating surgical context – such as the current procedural phase – has emerged as a promising strategy to improve robustness and interpretability.&#13;
To address these challenges, we organized the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) sub-challenge as part of the Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We introduced a novel, multi-center dataset comprising thirteen full-length laparoscopic cholecystectomy videos collected from three distinct medical institutions, with unified annotations for three interrelated tasks: surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation. Unlike existing datasets, ours enables joint investigation of instrument localization and procedural context within the same data while supporting the integration of temporal information across entire procedures.&#13;
We report results and findings in accordance with the BIAS guidelines for biomedical image analysis challenges. The PhaKIR sub-challenge advances the field by providing a unique benchmark for developing temporally aware, context-driven methods in RAMIS and offers a high-quality resource to support future research in surgical scene understanding.</abstract>
    <parentTitle language="eng">Medical Image Analysis</parentTitle>
    <identifier type="issn">1361-8415</identifier>
    <identifier type="doi">10.1016/j.media.2026.103945</identifier>
    <note>Corresponding author der OTH Regensburg: Tobias Rueckert&#13;
&#13;
Die Preprint-Version ist ebenfalls in diesem Repositorium verzeichnet unter: &#13;
https://opus4.kobv.de/opus4-oth-regensburg/solrsearch/index/search/start/0/rows/10/sortfield/score/sortorder/desc/searchtype/simple/query/2507.16559</note>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="local_crossrefDocumentType">journal-article</enrichment>
    <enrichment key="local_crossrefLicence">https://www.elsevier.com/tdm/userlicense/1.0/</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="CorrespondingAuthor">Tobias Rueckert</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="Kostentraeger">2027701</enrichment>
    <licence>Creative Commons - CC BY-NC - Namensnennung - Nicht kommerziell 4.0 International</licence>
    <author>Tobias Rueckert</author>
    <author>David Rauber</author>
    <author>Raphaela Maerkl</author>
    <author>Leonard Klausmann</author>
    <author>Suemeyye R. Yildiran</author>
    <author>Max Gutbrod</author>
    <author>Danilo Weber Nunes</author>
    <author>Alvaro Fernandez Moreno</author>
    <author>Imanol Luengo</author>
    <author>Danail Stoyanov</author>
    <author>Nicolas Toussaint</author>
    <author>Enki Cho</author>
    <author>Hyeon Bae Kim</author>
    <author>Oh Sung Choo</author>
    <author>Ka Young Kim</author>
    <author>Seong Tae Kim</author>
    <author>Gonçalo Arantes</author>
    <author>Kehan Song</author>
    <author>Jianjun Zhu</author>
    <author>Junchen Xiong</author>
    <author>Tingyi Lin</author>
    <author>Shunsuke Kikuchi</author>
    <author>Hiroki Matsuzaki</author>
    <author>Atsushi Kouno</author>
    <author>João Renato Ribeiro Manesco</author>
    <author>João Paulo Papa</author>
    <author>Tae-Min Choi</author>
    <author>Tae Kyeong Jeong</author>
    <author>Juyoun Park</author>
    <author>Oluwatosin Alabi</author>
    <author>Meng Wei</author>
    <author>Tom Vercauteren</author>
    <author>Runzhi Wu</author>
    <author>Mengya Xu</author>
    <author>An Wang</author>
    <author>Long Bai</author>
    <author>Hongliang Ren</author>
    <author>Amine Yamlahi</author>
    <author>Jakob Hennighausen</author>
    <author>Lena Maier-Hein</author>
    <author>Satoshi Kondo</author>
    <author>Satoshi Kasai</author>
    <author>Kousuke Hirasawa</author>
    <author>Shu Yang</author>
    <author>Yihui Wang</author>
    <author>Hao Chen</author>
    <author>Santiago Rodríguez</author>
    <author>Nicolás Aparicio</author>
    <author>Leonardo Manrique</author>
    <author>Christoph Palm</author>
    <author>Dirk Wilhelm</author>
    <author>Hubertus Feussner</author>
    <author>Daniel Rueckert</author>
    <author>Stefanie Speidel</author>
    <author>Sahar Nasirihaghighi</author>
    <author>Yasmina Al Khalil</author>
    <author>Yiping Li</author>
    <author>Pablo Arbeláez</author>
    <author>Nicolás Ayobi</author>
    <author>Olivia Hosie</author>
    <author>Juan Camilo Lyons</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Surgical phase recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Instrument keypoint estimation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Instrument instance segmentation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Robot-assisted surgery</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="institutes" number="RCBE">Regensburg Center of Biomedical Engineering - RCBE</collection>
    <collection role="institutes" number="RCHST">Regensburg Center of Health Sciences and Technology - RCHST</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="oaweg" number="">Hybrid Open Access - OA-Veröffentlichung in einer Subskriptionszeitschrift/-medium</collection>
    <collection role="oaweg" number="">Corresponding author der OTH Regensburg</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
    <collection role="funding" number="">DEAL Elsevier</collection>
    <collection role="DFGFachsystematik" number="1">Ingenieurwissenschaften</collection>
    <collection role="othforschungsschwerpunkt" number="">Digitale Transformation</collection>
  </doc>
  <doc>
    <id>5429</id>
    <completedYear/>
    <publishedYear>2022</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2388</pageFirst>
    <pageLast>2390</pageLast>
    <pageNumber/>
    <edition/>
    <issue>12</issue>
    <volume>71</volume>
    <type>article</type>
    <publisherName>BMJ</publisherName>
    <publisherPlace>London</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-09-16</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Vessel and tissue recognition during third-space endoscopy using a deep learning algorithm</title>
    <abstract language="eng">In this study, we aimed to develop an artificial intelligence clinical decision support solution to mitigate operator-dependent limitations during complex endoscopic procedures such as endoscopic submucosal dissection and peroral endoscopic myotomy, for example, bleeding and perforation. A DeepLabv3-based model was trained to delineate vessels, tissue structures and instruments on endoscopic still images from such procedures. The mean cross-validated Intersection over Union and Dice Score were 63% and 76%, respectively. Applied to standardised video clips from third-space endoscopic procedures, the algorithm showed a mean vessel detection rate of 85% with a false-positive rate of 0.75/min. These performance statistics suggest a potential clinical benefit for procedure safety, time and also training.</abstract>
    <parentTitle language="eng">Gut</parentTitle>
    <identifier type="doi">10.1136/gutjnl-2021-326470</identifier>
    <identifier type="urn">urn:nbn:de:bvb:898-opus4-54293</identifier>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Creative Commons - CC BY-NC - Namensnennung - Nicht kommerziell 4.0 International</licence>
    <author>Alanna Ebigbo</author>
    <author>Robert Mendel</author>
    <author>Markus W. Scheppach</author>
    <author>Andreas Probst</author>
    <author>Neal Shahidi</author>
    <author>Friederike Prinz</author>
    <author>Carola Fleischmann</author>
    <author>Christoph Römmele</author>
    <author>Stefan Karl Gölder</author>
    <author>Georg Braun</author>
    <author>David Rauber</author>
    <author>Tobias Rückert</author>
    <author>Luis Antonio de Souza Jr.</author>
    <author>João Paulo Papa</author>
    <author>Michael F. Byrne</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Artificial Intelligence</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Endoscopy</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Medical Image Computing</value>
    </subject>
    <collection role="ddc" number="004">Datenverarbeitung; Informatik</collection>
    <collection role="ddc" number="617">Chirurgie und verwandte medizinische Fachrichtungen</collection>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="othforschungsschwerpunkt" number="16314">Lebenswissenschaften und Ethik</collection>
    <collection role="oaweg" number="">Hybrid Open Access - OA-Veröffentlichung in einer Subskriptionszeitschrift/-medium</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
    <thesisPublisher>Ostbayerische Technische Hochschule Regensburg</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-oth-regensburg/files/5429/gutjnl-2021-326470.full_supp.pdf</file>
  </doc>
  <doc>
    <id>680</id>
    <completedYear/>
    <publishedYear>2021</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>878</pageFirst>
    <pageLast>883</pageLast>
    <pageNumber/>
    <edition/>
    <issue>09</issue>
    <volume>53</volume>
    <type>article</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace>Stuttgart</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2020-11-28</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Endoscopic prediction of submucosal invasion in Barrett’s cancer with the use of Artificial Intelligence: A pilot Study</title>
    <abstract language="eng">Background and aims: The accurate differentiation between T1a and T1b Barrett’s cancer has both therapeutic and prognostic implications but is challenging even for experienced physicians. We trained an Artificial Intelligence (AI) system on the basis of deep artificial neural networks (deep learning) to differentiate between T1a and T1b Barrett’s cancer white-light images. &#13;
&#13;
Methods: Endoscopic images from three tertiary care centres in Germany were collected retrospectively. A deep learning system was trained and tested using the principles of cross-validation. A total of 230 white-light endoscopic images (108 T1a and 122 T1b) was evaluated with the AI-system. For comparison, the images were also classified by experts specialized in endoscopic diagnosis and treatment of Barrett’s cancer. &#13;
&#13;
Results: The sensitivity, specificity, F1 and accuracy of the AI-system in the differentiation between T1a and T1b cancer lesions was 0.77, 0.64, 0.73 and 0.71, respectively. There was no statistically significant difference between the performance of the AI-system and that of human experts with sensitivity, specificity, F1 and accuracy of 0.63, 0.78, 0.67 and 0.70 respectively. &#13;
&#13;
Conclusion: This pilot study demonstrates the first multicenter application of an AI-based system in the prediction of submucosal invasion in endoscopic images of Barrett’s cancer. AI scored equal to international experts in the field, but more work is necessary to improve the system and apply it to video sequences and in a real-life setting. Nevertheless, the correct prediction of submucosal invasion in Barret´s cancer remains challenging for both experts and AI.</abstract>
    <parentTitle language="eng">Endoscopy</parentTitle>
    <identifier type="doi">10.1055/a-1311-8570</identifier>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Alanna Ebigbo</author>
    <author>Robert Mendel</author>
    <author>Tobias Rückert</author>
    <author>Laurin Schuster</author>
    <author>Andreas Probst</author>
    <author>Johannes Manzeneder</author>
    <author>Friederike Prinz</author>
    <author>Matthias Mende</author>
    <author>Ingo Steinbrück</author>
    <author>Siegbert Faiss</author>
    <author>David Rauber</author>
    <author>Luis Antonio de Souza Jr.</author>
    <author>João Paulo Papa</author>
    <author>Pierre Deprez</author>
    <author>Tsuneo Oyama</author>
    <author>Akiko Takahashi</author>
    <author>Stefan Seewald</author>
    <author>Prateek Sharma</author>
    <author>Michael F. Byrne</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Maschinelles Lernen</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Neuronales Netz</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Speiseröhrenkrebs</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Diagnose</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Artificial Intelligence</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Machine learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Adenocarcinoma</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Barrett’s cancer</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>submucosal invasion</value>
    </subject>
    <collection role="ddc" number="0">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="ddc" number="6">Technik, Medizin, angewandte Wissenschaften</collection>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="institutes" number="RCHST">Regensburg Center of Health Sciences and Technology - RCHST</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="persons" number="palmbarrett">Palm, Christoph (Prof. Dr.) - Projekt Barrett</collection>
    <collection role="othforschungsschwerpunkt" number="16314">Lebenswissenschaften und Ethik</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
  <doc>
    <id>5779</id>
    <completedYear/>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>13</pageNumber>
    <edition/>
    <issue>March</issue>
    <volume>154</volume>
    <type>article</type>
    <publisherName>Elsevier</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2023-02-03</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Error-Correcting Mean-Teacher: Corrections instead of consistency-targets applied to semi-supervised medical image segmentation</title>
    <abstract language="eng">Semantic segmentation is an essential task in medical imaging research. Many powerful deep-learning-based approaches can be employed for this problem, but they are dependent on the availability of an expansive labeled dataset. In this work, we augment such supervised segmentation models to be suitable for learning from unlabeled data. Our semi-supervised approach, termed Error-Correcting Mean-Teacher, uses an exponential moving average model like the original Mean Teacher but introduces our new paradigm of error correction. The original segmentation network is augmented to handle this secondary correction task. Both tasks build upon the core feature extraction layers of the model. For the correction task, features detected in the input image are fused with features detected in the predicted segmentation and further processed with task-specific decoder layers. The combination of image and segmentation features allows the model to correct present mistakes in the given input pair. The correction task is trained jointly on the labeled data. On unlabeled data, the exponential moving average of the original network corrects the student’s prediction. The combined outputs of the students’ prediction with the teachers’ correction form the basis for the semi-supervised update. We evaluate our method with the 2017 and 2018 Robotic Scene Segmentation data, the ISIC 2017 and the BraTS 2020 Challenges, a proprietary Endoscopic Submucosal Dissection dataset, Cityscapes, and Pascal VOC 2012. Additionally, we analyze the impact of the individual components and examine the behavior when the amount of labeled data varies, with experiments performed on two distinct segmentation architectures. Our method shows improvements in terms of the mean Intersection over Union over the supervised baseline and competing methods. Code is available at https://github.com/CloneRob/ECMT.</abstract>
    <parentTitle language="eng">Computers in Biology and Medicine</parentTitle>
    <identifier type="doi">10.1016/j.compbiomed.2023.106585</identifier>
    <identifier type="issn">0010-4825</identifier>
    <identifier type="urn">urn:nbn:de:bvb:898-opus4-57790</identifier>
    <note>Corresponding author der OTH Regensburg: Robert Mendel</note>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="Kostentraeger">2027207</enrichment>
    <enrichment key="CorrespondingAuthor">Robert Mendel</enrichment>
    <licence>Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International</licence>
    <author>Robert Mendel</author>
    <author>David Rauber</author>
    <author>Luis Antonio de Souza Jr.</author>
    <author>João Paulo Papa</author>
    <author>Christoph Palm</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Semi-supervised Segmentation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Mean-Teacher</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Pseudo-labels</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Medical Imaging</value>
    </subject>
    <collection role="ddc" number="00">Informatik, Wissen, Systeme</collection>
    <collection role="ddc" number="61">Medizin und Gesundheit</collection>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="institutes" number="RCHST">Regensburg Center of Health Sciences and Technology - RCHST</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="othforschungsschwerpunkt" number="16314">Lebenswissenschaften und Ethik</collection>
    <collection role="oaweg" number="">Hybrid Open Access - OA-Veröffentlichung in einer Subskriptionszeitschrift/-medium</collection>
    <collection role="oaweg" number="">Corresponding author der OTH Regensburg</collection>
    <collection role="funding" number="">Publikationsfonds der OTH Regensburg</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
    <thesisPublisher>Ostbayerische Technische Hochschule Regensburg</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-oth-regensburg/files/5779/1-s2.0-S0010482523000501-main.pdf</file>
  </doc>
  <doc>
    <id>660</id>
    <completedYear/>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>141</pageFirst>
    <pageLast>157</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>Cham</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2020-10-23</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Semi-supervised Segmentation Based on Error-Correcting Supervision</title>
    <abstract language="eng">Pixel-level classification is an essential part of computer vision. For learning from labeled data, many powerful deep learning models have been developed recently. In this work, we augment such supervised segmentation models by allowing them to learn from unlabeled data. Our semi-supervised approach, termed Error-Correcting Supervision, leverages a collaborative strategy. Apart from the supervised training on the labeled data, the segmentation network is judged by an additional network. The secondary correction network learns on the labeled data to optimally spot correct predictions, as well as to amend incorrect ones. As auxiliary regularization term, the corrector directly influences the supervised training of the segmentation network. On unlabeled data, the output of the correction network is essential to create a proxy for the unknown truth. The corrector’s output is combined with the segmentation network’s prediction to form the new target. We propose a loss function that incorporates both the pseudo-labels as well as the predictive certainty of the correction network. Our approach can easily be added to supervised segmentation models. We show consistent improvements over a supervised baseline on experiments on both the Pascal VOC 2012 and the Cityscapes datasets with varying amounts of labeled data.</abstract>
    <parentTitle language="eng">Computer vision - ECCV 2020: 16th European conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXIX</parentTitle>
    <identifier type="isbn">978-3-030-58525-9</identifier>
    <identifier type="doi">10.1007/978-3-030-58526-6_9</identifier>
    <enrichment key="OtherSeries">Lecture Notes in Computer Science; 12374</enrichment>
    <enrichment key="ConferenceStatement">European Conference on Computer Vision, 16th, 2020</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Robert Mendel</author>
    <author>Luis Antonio de Souza Jr.</author>
    <author>David Rauber</author>
    <author>João Paulo Papa</author>
    <author>Christoph Palm</author>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Semi-Supervised Learning</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Machine Learning</value>
    </subject>
    <collection role="ddc" number="0">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="institutes" number="RCHST">Regensburg Center of Health Sciences and Technology - RCHST</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
  <doc>
    <id>1460</id>
    <completedYear/>
    <publishedYear>2021</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>178</pageFirst>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferencepresentation</type>
    <publisherName>Springer Vieweg</publisherName>
    <publisherPlace>Wiesbaden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2021-03-10</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Abstract: Semi-supervised Segmentation Based on Error-correcting Supervision</title>
    <abstract language="eng">Pixel-level classification is an essential part of computer vision. For learning from labeled data, many powerful deep learning models have been developed recently. In this work, we augment such supervised segmentation models by allowing them to learn from unlabeled data. Our semi-supervised approach, termed Error-Correcting Supervision, leverages a collaborative strategy. Apart from the supervised training on the labeled data, the segmentation network is judged by an additional network.</abstract>
    <parentTitle language="eng">Bildverarbeitung für die Medizin 2021. Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021</parentTitle>
    <identifier type="isbn">978-3-658-33197-9</identifier>
    <identifier type="doi">10.1007/978-3-658-33198-6_43</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Robert Mendel</author>
    <author>Luis Antonio de Souza Jr.</author>
    <author>David Rauber</author>
    <author>João Paulo Papa</author>
    <author>Christoph Palm</author>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Deep Learning</value>
    </subject>
    <collection role="ddc" number="0">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="ddc" number="6">Technik, Medizin, angewandte Wissenschaften</collection>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="institutes" number="RCHST">Regensburg Center of Health Sciences and Technology - RCHST</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="othforschungsschwerpunkt" number="16314">Lebenswissenschaften und Ethik</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
  <doc>
    <id>7308</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>3355</pageFirst>
    <pageLast>3372</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume>62</volume>
    <type>article</type>
    <publisherName>Springer Nature</publisherName>
    <publisherPlace>Heidelberg</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2024-06-12</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Layer-selective deep representation to improve esophageal cancer classification</title>
    <abstract language="eng">Even though artiﬁcial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their accountability and transparency level must be improved to transfer this success into clinical practice. The reliability of machine learning decisions must be explained and interpreted, especially for supporting the medical diagnosis.For this task, the deep learning techniques’ black-box nature must somehow be lightened up to clarify its promising results. Hence, we aim to investigate the impact of the ResNet-50 deep convolutional design for Barrett’s esophagus and adenocarcinoma classiﬁcation. For such a task, and aiming at proposing a two-step learning technique, the output of each convolutional layer that composes the ResNet-50 architecture was trained and classiﬁed for further deﬁnition of layers that would provide more impact in the architecture. We showed that local information and high-dimensional features are essential to improve the classiﬁcation for our task. Besides, we observed a signiﬁcant improvement when the most discriminative layers expressed more impact in the training and classiﬁcation of ResNet-50 for Barrett’s esophagus and adenocarcinoma classiﬁcation, demonstrating that both human knowledge and computational processing may inﬂuence the correct learning of such a problem.</abstract>
    <parentTitle language="eng">Medical &amp; Biological Engineering &amp; Computing</parentTitle>
    <identifier type="doi">10.1007/s11517-024-03142-8</identifier>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Luis Antonio de Souza Jr.</author>
    <author>Leandro A. Passos</author>
    <author>Marcos Cleison S. Santana</author>
    <author>Robert Mendel</author>
    <author>David Rauber</author>
    <author>Alanna Ebigbo</author>
    <author>Andreas Probst</author>
    <author>Helmut Messmann</author>
    <author>João Paulo Papa</author>
    <author>Christoph Palm</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Multistep training</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Barrett’s esophagus detection</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Convolutional neural networks</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Deep learning</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="persons" number="palmbarrett">Palm, Christoph (Prof. Dr.) - Projekt Barrett</collection>
    <collection role="othforschungsschwerpunkt" number="16314">Lebenswissenschaften und Ethik</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
</export-example>
