<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>108</id>
    <completedYear/>
    <publishedYear>2017</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>141</pageFirst>
    <pageLast>146</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>Berlin</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Barrett's Esophagus Analysis Using SURF Features</title>
    <abstract language="eng">The development of adenocarcinoma in Barrett’s esophagus is difficult to detect by endoscopic surveillance of patients with signs of dysplasia. Computer assisted diagnosis of endoscopic images (CAD) could therefore be most helpful in the demarcation and classification of neoplastic lesions. In this study we tested the feasibility of a CAD method based on Speeded up Robust Feature Detection (SURF). A given database containing 100 images from 39 patients served as benchmark for feature based classification models. Half of the images had previously been diagnosed by five clinical experts as being ”cancerous”, the other half as ”non-cancerous”. Cancerous image regions had been visibly delineated (masked) by the clinicians. SURF features acquired from full images as well as from masked areas were utilized for the supervised training and testing of an SVM classifier. The predictive accuracy of the developed CAD system is illustrated by sensitivity and specificity values. The results based on full image matching where 0.78 (sensitivity) and 0.82 (specificity) were achieved, while the masked region approach generated results of 0.90 and 0.95, respectively.</abstract>
    <parentTitle language="deu">Bildverarbeitung für die Medizin 2017; Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 12. bis 14. März 2017 in Heidelberg</parentTitle>
    <identifier type="doi">10.1007/978-3-662-54345-0_34</identifier>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <author>Luis Antonio de Souza Jr.</author>
    <author>Christian Hook</author>
    <author>João Paulo Papa</author>
    <author>Christoph Palm</author>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Speiseröhrenkrankheit</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Diagnose</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Maschinelles Sehen</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Automatische Klassifikation</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="RCBE">Regensburg Center of Biomedical Engineering - RCBE</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>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>
  <doc>
    <id>7119</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>10445</pageFirst>
    <pageLast>10459</pageLast>
    <pageNumber>15</pageNumber>
    <edition/>
    <issue/>
    <volume>36</volume>
    <type>article</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>London</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2024-03-14</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">DeepCraftFuse: visual and deeply-learnable features work better together for esophageal cancer detection in patients with Barrett’s esophagus</title>
    <abstract language="eng">Limitations in computer-assisted diagnosis include lack of labeled data and inability to model the relation between what experts see and what computers learn. 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. While deep learning techniques are broad so that unseen information might help learn patterns of interest, human insights to describe objects of interest help in decision-making. This paper proposes a novel approach, DeepCraftFuse, to address the challenge of combining information provided by deep networks with visual-based features to significantly enhance the correct identification of cancerous tissues in patients affected with Barrett’s esophagus (BE). We demonstrate that DeepCraftFuse outperforms state-of-the-art techniques on private and public datasets, reaching results of around 95% when distinguishing patients affected by BE that is either positive or negative to esophageal cancer.</abstract>
    <parentTitle language="eng">Neural Computing and Applications</parentTitle>
    <identifier type="doi">10.1007/s00521-024-09615-z</identifier>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="Kostentraeger">2027700</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>André G.C. Pacheco</author>
    <author>Leandro A. Passos</author>
    <author>Marcos Cleison S. Santana</author>
    <author>Robert Mendel</author>
    <author>Alanna Ebigbo</author>
    <author>Andreas Probst</author>
    <author>Helmut Messmann</author>
    <author>Christoph Palm</author>
    <author>João Paulo Papa</author>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Deep Learning</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Speiseröhrenkrebs</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Adenocarcinom</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Endobrachyösophagus</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Diagnose</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Maschinelles Lernen</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>Object detector</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Barrett’s esophagus</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>
  <doc>
    <id>8164</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>15535</pageFirst>
    <pageLast>15546</pageLast>
    <pageNumber>12</pageNumber>
    <edition/>
    <issue>37</issue>
    <volume/>
    <type>article</type>
    <publisherName>Springer</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2025-05-25</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">TransConv: a lightweight architecture based on transformers and convolutional neural networks for adenocarcinoma and Barrett’s esophagus identification</title>
    <abstract language="eng">Barrett’s esophagus, also known as BE, is commonly associated with repeated exposure to stomach acid. If not treated properly, it may evolve into esophageal adenocarcinoma, aka esophageal cancer. This paper proposes TransConv, a hybrid architecture that benefits from features learned by pre-trained vision transformers (ViTs) and convolutional neural networks (CNNs), followed by a shallow neural network composed of three normalizations, ReLU activations, and fully connected layers, and a SoftMax head to distinguish between BE and esophageal cancer. TransConv is designed to be training-lightweight, and for the ViT and CNN backbone models, weights are kept frozen during training, i.e., the primary goal of TransConv is to learn the weights of the fully connected layer from both backbones only, avoiding the burden of updating their weights but still learning their final descriptions for the lightweight convolutional model. We report promising results with low computational training costs in two datasets, one public and another private. From our achievements, TransConv was able to deliver balanced accuracy results around 85% and 86% for each evaluated dataset, respectively, in a design that required only 50 epochs of model training, a very reduced number compared to state-of-the-art conducted studies in the same domain.</abstract>
    <parentTitle language="eng">Neural Computing and Applications</parentTitle>
    <identifier type="doi">10.1007/s00521-025-11299-y</identifier>
    <enrichment key="opus.import.date">2025-06-03T21:32:12+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Luis A. Souza</author>
    <author>André G.C. Pacheco</author>
    <author>Alberto F. de Souza</author>
    <author>Thiago Oliveira-Santos</author>
    <author>Claudine Badue</author>
    <author>Christoph Palm</author>
    <author>João Paulo Papa</author>
    <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>
    <collection role="DFGFachsystematik" number="1">Ingenieurwissenschaften</collection>
  </doc>
  <doc>
    <id>8978</id>
    <completedYear/>
    <publishedYear>2026</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>11</pageNumber>
    <edition/>
    <issue>1</issue>
    <volume>32</volume>
    <type>article</type>
    <publisherName>Brazilian Computer Society</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2026-03-29</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">LiwTERM-r: a Revised Lightweight Transformer-based Model for Multimodal Skin Lesion Detection Robust to Incomplete Input</title>
    <abstract language="eng">As the most common type of cancer in the world, skin cancer accounts for approximately 30% of all diagnosed tumor-based lesions. Early diagnosis can reduce mortality and prevent disfiguring in different skin regions. With the application of machine learning techniques in recent years, especially deep learning, promising results in this task could be achieved, presenting studies demonstrating that the combination of patients’ clinical anamneses and images of the injured lesion is essential for improving the correct classification of skin lesions. Despite that, meaningful use of anamneses with multiple collected images of the same skin lesion is mandatory, requiring further investigation. Thus, this project aims to contribute to developing multimodal machine learning-based models to solve the skin lesion classification problem by employing a lightweight transformer model that is robust to missing clinical information input. As a main hypothesis, models can be fed by multiple images from different sources as input along with clinical anamneses from the patient’s historical evaluations, leading to a more factual and trustworthy diagnosis. Our model deals with the not-trivial task of combining images and clinical information concerning the skin lesions in a lightweight transformer architecture that does not demand high computation resources or even all the information from the anamneses but still presents competitive classification results.</abstract>
    <parentTitle language="eng">Journal of the Brazilian Computer Society</parentTitle>
    <identifier type="doi">10.5753/jbcs.2026.5871</identifier>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Luis Antonio de Souza Júnior</author>
    <author>André Georghton Cardoso Pacheco</author>
    <author>Thiago Oliveira dos Santos</author>
    <author>Wyctor Fogos da Rocha</author>
    <author>Pedro Henrique Bouzon</author>
    <author>Christoph Palm</author>
    <author>João Paulo Papa</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Deep learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Skin Lesion Detection</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Transformers</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Lightweight Architectures</value>
    </subject>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="oaweg" number="">Diamond Open Access - OA-Veröffentlichung ohne Publikationskosten (Sponsoring)</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>
</export-example>
