<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>7281</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>641</pageFirst>
    <pageLast>649</pageLast>
    <pageNumber>9</pageNumber>
    <edition/>
    <issue/>
    <volume>56</volume>
    <type>article</type>
    <publisherName>Georg Thieme Verlag</publisherName>
    <publisherPlace>Stuttgart</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2024-05-05</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett’s esophagus: a tandem randomized and video trial</title>
    <abstract language="eng">Background &#13;
This study evaluated the effect of an artificial intelligence (AI)-based clinical decision support system on the performance and diagnostic confidence of endoscopists in their assessment of Barrett’s esophagus (BE).&#13;
&#13;
Methods &#13;
96 standardized endoscopy videos were assessed by 22 endoscopists with varying degrees of BE experience from 12 centers. Assessment was randomized into two video sets: group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett’s esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level.&#13;
&#13;
Results &#13;
AI had a stand-alone sensitivity, specificity, and accuracy of 92.2%, 68.9%, and 81.3%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3%, 58.1%, and 71.5%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.8% [95%CI 65.2%–74.2%] to 78.0% [95%CI 74.0%–82.0%]; specificity 67.3% [95%CI 62.5%–72.2%] to 72.7% [95%CI 68.2%–77.3%]). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI.&#13;
&#13;
Conclusion &#13;
BE nonexperts benefitted significantly from additional AI. BE experts and nonexperts remained significantly below the stand-alone performance of AI, suggesting that there may be other factors influencing endoscopists’ decisions to follow or discard AI advice.</abstract>
    <parentTitle language="eng">Endoscopy</parentTitle>
    <identifier type="doi">10.1055/a-2296-5696</identifier>
    <identifier type="urn">urn:nbn:de:bvb:898-opus4-72818</identifier>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International</licence>
    <author>Michael Meinikheim</author>
    <author>Robert Mendel</author>
    <author>Christoph Palm</author>
    <author>Andreas Probst</author>
    <author>Anna Muzalyova</author>
    <author>Markus W. Scheppach</author>
    <author>Sandra Nagl</author>
    <author>Elisabeth Schnoy</author>
    <author>Christoph Römmele</author>
    <author>Dominik Andreas Helmut Otto Schulz</author>
    <author>Jakob Schlottmann</author>
    <author>Friederike Prinz</author>
    <author>David Rauber</author>
    <author>Tobias Rückert</author>
    <author>Tomoaki Matsumura</author>
    <author>Glòria Fernández-Esparrach</author>
    <author>Nasim Parsa</author>
    <author>Michael F. Byrne</author>
    <author>Helmut Messmann</author>
    <author>Alanna Ebigbo</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="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="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/7281/Meinikheim_Mendel_Endoscopy_2024.pdf</file>
  </doc>
  <doc>
    <id>7261</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>79</pageFirst>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>S 02</issue>
    <volume>56</volume>
    <type>conferencepresentation</type>
    <publisherName>Georg Thieme Verlag</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Human-Computer Interaction: Impact of Artificial Intelligence on the diagnostic confidence of endoscopists assessing videos of Barrett’s esophagus</title>
    <abstract language="eng">Aims &#13;
Human-computer interactions (HCI) may have a relevant impact on the performance of Artificial Intelligence (AI). Studies show that although endoscopists assessing Barrett’s esophagus (BE) with AI improve their performance significantly, they do not achieve the level of the stand-alone performance of AI. One aspect of HCI is the impact of AI on the degree of certainty and confidence displayed by the endoscopist. Indirectly, diagnostic confidence when using AI may be linked to trust and acceptance of AI. In a BE video study, we aimed to understand the impact of AI on the diagnostic confidence of endoscopists and the possible correlation with diagnostic performance.&#13;
&#13;
Methods &#13;
22 endoscopists from 12 centers with varying levels of BE experience reviewed ninety-six standardized endoscopy videos. Endoscopists were categorized into experts and non-experts and randomly assigned to assess the videos with and without AI. Participants were randomized in two arms: Arm A assessed videos first without AI and then with AI, while Arm B assessed videos in the opposite order. Evaluators were tasked with identifying BE-related neoplasia and rating their confidence with and without AI on a scale from 0 to 9.&#13;
&#13;
Results &#13;
The utilization of AI in Arm A (without AI first, with AI second) significantly elevated confidence levels for experts and non-experts (7.1 to 8.0 and 6.1 to 6.6, respectively). Only non-experts benefitted from AI with a significant increase in accuracy (68.6% to 75.5%). Interestingly, while the confidence levels of experts without AI were higher than those of non-experts with AI, there was no significant difference in accuracy between these two groups (71.3% vs. 75.5%). In Arm B (with AI first, without AI second), experts and non-experts experienced a significant reduction in confidence (7.6 to 7.1 and 6.4 to 6.2, respectively), while maintaining consistent accuracy levels (71.8% to 71.8% and 67.5% to 67.1%, respectively).&#13;
&#13;
Conclusions &#13;
AI significantly enhanced confidence levels for both expert and non-expert endoscopists. Endoscopists felt significantly more uncertain in their assessments without AI. Furthermore, experts with or without AI consistently displayed higher confidence levels than non-experts with AI, irrespective of comparable outcomes. These findings underscore the possible role of AI in improving diagnostic confidence during endoscopic assessment.</abstract>
    <parentTitle language="eng">Endoscopy</parentTitle>
    <identifier type="issn">1438-8812</identifier>
    <identifier type="doi">10.1055/s-0044-1782859</identifier>
    <enrichment key="ConferenceStatement">ESGE Days 2024, Berlin, 25.–27.04.2024</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>David Roser</author>
    <author>Michael Meinikheim</author>
    <author>Robert Mendel</author>
    <author>Christoph Palm</author>
    <author>Andreas Probst</author>
    <author>Anna Muzalyova</author>
    <author>Markus W. Scheppach</author>
    <author>Sandra Nagl</author>
    <author>Elisabeth Schnoy</author>
    <author>Christoph Römmele</author>
    <author>Dominik Andreas Helmut Otto Schulz</author>
    <author>Jakob Schlottmann</author>
    <author>Friederike Prinz</author>
    <author>David Rauber</author>
    <author>Tobias Rückert</author>
    <author>Tomoaki Matsumura</author>
    <author>G. Fernandez-Esparrach</author>
    <author>Nasim Parsa</author>
    <author>Michael F. Byrne</author>
    <author>Helmut Messmann</author>
    <author>Alanna Ebigbo</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>
  </doc>
  <doc>
    <id>8350</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst>e295</pageFirst>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>5</issue>
    <volume>63</volume>
    <type>conferencepresentation</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace>Stuttgart</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2025-07-10</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Künstliche Intelligenz als Hilfsmittel zur Detektion der Papilla duodeni major und des papillären Ostiums während der ERCP</title>
    <abstract language="deu">Einleitung &#13;
Die Endoskopische Retrograde Cholangiopankreatikographie (ERCP) ist der Goldstandard in der endoskopischen Therapie von Erkrankungen des pankreatobiliären Trakts. Allerdings ist sie technisch anspruchsvoll, schwer zu erlernen und mit einer relativ hohen Komplikationsrate assoziiert. Daher soll in der vorliegenden Machbarkeitsstudie geprüft werden, ob mithilfe eines Deeplearning- Algorithmus die Papille und das Ostium zuverlässig detektiert werden können und dieser für Endoskopiker, insbesondere in der Ausbildungssituation, ein geeignetes Hilfsmittel darstellen könnte. Material und Methodik Insgesamt wurden 1534 ERCP-Bilder von 134 Patienten analysiert, wobei sowohl die Papilla duodeni major als auch das Ostium segmentiert wurden. Anschließend erfolgte das Training eines neuronalen Netzes unter Verwendung eines Deep-Learning-Algorithmus. Für den Test des Algorithmus erfolgte eine fünffache Kreuzvalidierung.&#13;
&#13;
Ergebnisse &#13;
Auf den 1534 gelabelten Bildern wurden für die Klasse Papille ein F1-Wert von 0,7996, eine Sensitivität von 0,8488 und eine Spezifität von 0,9822 erzielt. Für die Klasse Ostium ergaben sich ein F1-Wert von 0,5198, eine Sensitivität von 0,5945 und eine Spezifität von 0,9974. Klassenübergreifend (Klasse Papille und Klasse Ostium) betrug der F1-Wert 0,6593, die Sensitivität 0,7216 und für die Spezifität 0,9898.&#13;
&#13;
Zusammenfassung &#13;
In der vorliegenden Machbarkeitsstudie zeigte das neuronale Netz eine hohe Sensitivität und eine sehr hohe Spezifität bei der Identifikation der Papilla duodeni major. Die Detektion des Ostiums erfolgte hingegen mit einer deutlich geringeren Sensitivität. Zukünftig ist eine Erweiterung des Trainingsdatensatzes um Videos und klinische Daten vorgesehen, um die Leistungsfähigkeit des Netzwerks zu verbessern. Hierdurch könnte langfristig ein geeignetes Assistenzsystem für die ERCP, insbesondere in der Ausbildungssituation etabliert werden.</abstract>
    <parentTitle language="deu">Zeitschrift für Gastroenterologie</parentTitle>
    <identifier type="doi">10.1055/s-0045-1806882</identifier>
    <enrichment key="ConferenceStatement">52. Jahrestagung der Gesellschaft für Gastroenterologie in Bayern e. V.</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Stephan Zellmer</author>
    <author>David Rauber</author>
    <author>Andreas Probst</author>
    <author>Tobias Weber</author>
    <author>Georg Braun</author>
    <author>Sandra Nagl</author>
    <author>Christoph Römmele</author>
    <author>Elisabeth Schnoy</author>
    <author>Lisa Birzle</author>
    <author>Niklas Aehling</author>
    <author>Dominik Andreas Helmut Otto Schulz</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <author>Alanna Ebigbo</author>
    <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="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
  <doc>
    <id>7276</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>S428</pageFirst>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>S 02</issue>
    <volume>56</volume>
    <type>conferencepresentation</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace>Stuttgart</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2024-05-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Early Esophageal Cancer and the Generalizability of Artificial Intelligence</title>
    <abstract language="eng">Aims &#13;
Artificial Intelligence (AI) systems in gastrointestinal endoscopy are narrow because they are trained to solve only one specific task. Unlike Narrow-AI, general AI systems may be able to solve multiple and unrelated tasks. We aimed to understand whether an AI system trained to detect, characterize, and segment early Barrett’s neoplasia (Barrett’s AI) is only capable of detecting this pathology or can also detect and segment other diseases like early squamous cell cancer (SCC).&#13;
&#13;
Methods &#13;
120 white light (WL) and narrow-band endoscopic images (NBI) from 60 patients (1 WL and 1 NBI image per patient) were extracted from the endoscopic database of the University Hospital Augsburg. Images were annotated by three expert endoscopists with extensive experience in the diagnosis and endoscopic resection of early esophageal neoplasias. An AI system based on DeepLabV3+architecture dedicated to early Barrett’s neoplasia was tested on these images. The AI system was neither trained with SCC images nor had it seen the test images prior to evaluation. The overlap between the three expert annotations („expert-agreement“) was the ground truth for evaluating AI performance.&#13;
&#13;
Results &#13;
Barrett’s AI detected early SCC with a mean intersection over reference (IoR) of 92% when at least 1 pixel of the AI prediction overlapped with the expert-agreement. When the threshold was increased to 5%, 10%, and 20% overlap with the expert-agreement, the IoR was 88%, 85% and 82%, respectively. The mean Intersection Over Union (IoU) – a metric according to segmentation quality between the AI prediction and the expert-agreement – was 0.45. The mean expert IoU as a measure of agreement between the three experts was 0.60.&#13;
&#13;
Conclusions &#13;
In the context of this pilot study, the predictions of SCC by a Barrett’s dedicated AI showed some overlap to the expert-agreement. Therefore, features learned from Barrett’s cancer-related training might be helpful also for SCC prediction. Our results allow different possible explanations. On the one hand, some Barrett’s cancer features generalize toward the related task of assessing early SCC. On the other hand, the Barrett’s AI is less specific to Barrett’s cancer than a general predictor of pathological tissue. However, we expect to enhance the detection quality significantly by extending the training to SCC-specific data. The insight of this study opens the way towards a transfer learning approach for more efficient training of AI to solve tasks in other domains.</abstract>
    <parentTitle language="eng">Endoscopy</parentTitle>
    <identifier type="doi">10.1055/s-0044-1783775</identifier>
    <enrichment key="ConferenceStatement">ESGE Days 2024</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Alanna Ebigbo</author>
    <author>David Rauber</author>
    <author>Mousa Ayoub</author>
    <author>Lisa Birzle</author>
    <author>Tomoaki Matsumura</author>
    <author>Andreas Probst</author>
    <author>Ingo Steinbrück</author>
    <author>Sandra Nagl</author>
    <author>Christoph Römmele</author>
    <author>Michael Meinikheim</author>
    <author>Markus W. Scheppach</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <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="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
  <doc>
    <id>7277</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>S93</pageFirst>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>S 02</issue>
    <volume>56</volume>
    <type>conferencepresentation</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace>Stuttgart</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2024-05-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Artificial Intelligence (AI) improves endoscopists’ vessel detection during endoscopic submucosal dissection (ESD)</title>
    <abstract language="eng">Aims &#13;
While AI has been successfully implemented in detecting and characterizing colonic polyps, its role in therapeutic endoscopy remains to be elucidated. Especially third space endoscopy procedures like ESD and peroral endoscopic myotomy (POEM) pose a technical challenge and the risk of operator-dependent complications like intraprocedural bleeding and perforation. Therefore, we aimed at developing an AI-algorithm for intraprocedural real time vessel detection during ESD and POEM.&#13;
&#13;
Methods &#13;
A training dataset consisting of 5470 annotated still images from 59 full-length videos (47 ESD, 12 POEM) and 179681 unlabeled images was used to train a DeepLabV3+neural network with the ECMT semi-supervised learning method. Evaluation for vessel detection rate (VDR) and time (VDT) of 19 endoscopists with and without AI-support was performed using a testing dataset of 101 standardized video clips with 200 predefined blood vessels. Endoscopists were stratified into trainees and experts in third space endoscopy.&#13;
&#13;
Results &#13;
The AI algorithm had a mean VDR of 93.5% and a median VDT of 0.32 seconds. AI support was associated with a statistically significant increase in VDR from 54.9% to 73.0% and from 59.0% to 74.1% for trainees and experts, respectively. VDT significantly decreased from 7.21 sec to 5.09 sec for trainees and from 6.10 sec to 5.38 sec for experts in the AI-support group. False positive (FP) readings occurred in 4.5% of frames. FP structures were detected significantly shorter than true positives (0.71 sec vs. 5.99 sec).&#13;
&#13;
Conclusions &#13;
AI improved VDR and VDT of trainees and experts in third space endoscopy and may reduce performance variability during training. Further research is needed to evaluate the clinical impact of this new technology.</abstract>
    <parentTitle language="eng">Endoscopy</parentTitle>
    <identifier type="doi">10.1055/s-0044-1782891</identifier>
    <enrichment key="ConferenceStatement">ESGE Days 2024</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Markus W. Scheppach</author>
    <author>Robert Mendel</author>
    <author>David Rauber</author>
    <author>Andreas Probst</author>
    <author>Sandra Nagl</author>
    <author>Christoph Römmele</author>
    <author>Michael Meinikheim</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <author>Alanna Ebigbo</author>
    <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="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
  <doc>
    <id>7275</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>S198</pageFirst>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>S 02</issue>
    <volume>56</volume>
    <type>conferencepresentation</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace>Stuttgart</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2024-05-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Artificial intelligence as a tool in the detection of the papillary ostium during ERCP</title>
    <abstract language="eng">Aims &#13;
Endoscopic retrograde cholangiopancreaticography (ERCP) is the gold standard in the diagnosis as well as treatment of diseases of the pancreatobiliary tract. However, it is technically complex and has a relatively high complication rate. In particular, cannulation of the papillary ostium remains challenging. The aim of this study is to examine whether a deep-learning algorithm can be used to detect the major duodenal papilla and in particular the papillary ostium reliably and could therefore be a valuable tool for inexperienced endoscopists, particularly in training situation.&#13;
&#13;
Methods &#13;
We analyzed a total of 654 retrospectively collected images of 85 patients. Both the major duodenal papilla and the ostium were then segmented. Afterwards, a neural network was trained using a deep-learning algorithm. A 5-fold cross-validation was performed. Subsequently, we ran the algorithm on 5 prospectively collected videos of ERCPs.&#13;
&#13;
Results&#13;
5-fold cross-validation on the 654 labeled data resulted in an F1 value of 0.8007, a sensitivity of 0.8409 and a specificity of 0.9757 for the class papilla, and an F1 value of 0.5724, a sensitivity of 0.5456 and a specificity of 0.9966 for the class ostium. Regardless of the class, the average F1 value (class papilla and class ostium) was 0.6866, the sensitivity 0.6933 and the specificity 0.9861. In 100% of cases the AI-detected localization of the papillary ostium in the prospectively collected videos corresponded to the localization of the cannulation performed by the endoscopist.&#13;
&#13;
Conclusions &#13;
In the present study, the neural network was able to identify the major duodenal papilla with a high sensitivity and high specificity. In detecting the papillary ostium, the sensitivity was notably lower. However, when used on videos, the AI was able to identify the location of the subsequent cannulation with 100% accuracy. In the future, the neural network will be trained with more data. Thus, a suitable tool for ERCP could be established, especially in the training situation.</abstract>
    <parentTitle language="eng">Endoscopy</parentTitle>
    <identifier type="doi">10.1055/s-0044-1783138</identifier>
    <enrichment key="ConferenceStatement">ESGE Days 2024</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Stephan Zellmer</author>
    <author>David Rauber</author>
    <author>Andreas Probst</author>
    <author>Tobias Weber</author>
    <author>Georg Braun</author>
    <author>Christoph Römmele</author>
    <author>Sandra Nagl</author>
    <author>Elisabeth Schnoy</author>
    <author>Helmut Messmann</author>
    <author>Alanna Ebigbo</author>
    <author>Christoph Palm</author>
    <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="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
  <doc>
    <id>7278</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>S439</pageFirst>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>S 02</issue>
    <volume>56</volume>
    <type>conferencepresentation</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace>Stuttgart</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2024-05-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Procedural phase recognition in endoscopic submucosal dissection (ESD) using artificial intelligence (AI)</title>
    <abstract language="eng">Aims &#13;
Recent evidence suggests the possibility of intraprocedural phase recognition in surgical operations as well as endoscopic interventions such as peroral endoscopic myotomy and endoscopic submucosal dissection (ESD) by AI-algorithms. The intricate measurement of intraprocedural phase distribution may deepen the understanding of the procedure. Furthermore, real-time quality assessment as well as automation of reporting may become possible. Therefore, we aimed to develop an AI-algorithm for intraprocedural phase recognition during ESD.&#13;
&#13;
Methods &#13;
A training dataset of 364385 single images from 9 full-length ESD videos was compiled. Each frame was classified into one procedural phase. Phases included scope manipulation, marking, injection, application of electrical current and bleeding. Allocation of each frame was only possible to one category. This training dataset was used to train a Video Swin transformer to recognize the phases. Temporal information was included via logarithmic frame sampling. Validation was performed using two separate ESD videos with 29801 single frames.&#13;
&#13;
Results &#13;
The validation yielded sensitivities of 97.81%, 97.83%, 95.53%, 85.01% and 87.55% for scope manipulation, marking, injection, electric application and bleeding, respectively. Specificities of 77.78%, 90.91%, 95.91%, 93.65% and 84.76% were measured for the same parameters.&#13;
&#13;
Conclusions &#13;
The developed algorithm was able to classify full-length ESD videos on a frame-by-frame basis into the predefined classes with high sensitivities and specificities. Future research will aim at the development of quality metrics based on single-operator phase distribution.</abstract>
    <parentTitle language="eng">Endoscopy</parentTitle>
    <identifier type="doi">10.1055/s-0044-1783804</identifier>
    <enrichment key="ConferenceStatement">ESGE Days 2024</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Markus W. Scheppach</author>
    <author>Danilo Weber Nunes</author>
    <author>X. Arizi</author>
    <author>David Rauber</author>
    <author>Andreas Probst</author>
    <author>Sandra Nagl</author>
    <author>Christoph Römmele</author>
    <author>Michael Meinikheim</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <author>Alanna Ebigbo</author>
    <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="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
  <doc>
    <id>8056</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>S511</pageFirst>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>S 02</issue>
    <volume>57</volume>
    <type>conferencepresentation</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace>Stuttgart</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2025-04-28</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Single frame workflow recognition during endoscopic submucosal dissection (ESD) using artificial intelligence (AI)</title>
    <abstract language="eng">Aims &#13;
Precise surgical phase recognition and evaluation may improve our understanding of complex endoscopic procedures. Furthermore, quality control measurements and endoscopy training could benefit from objective descriptions of surgical phase distributions. Therefore, we aimed to develop an artificial intelligence algorithm for frame-by-frame operational phase recognition during endoscopic submucosal dissection (ESD).&#13;
&#13;
Methods &#13;
Full length ESD-videos from 31 patients comprising 6.297.782 single images were collected retrospectively. Videos were annotated on a frame-by-frame basis for the operational macro-phases diagnostics, marking, injection, dissection and bleeding. Further subphases were the application of electrical current, visible injection of fluid into the submucosal space and scope manipulation, leading to 11 phases in total. 4.975.699 frames (21 patients) were used for training of a video swin transformer using uniform frame sampling for temporal information. Hyperparameter tuning was performed with 897.325 further frames (6 patients), while 424.758 frames (4 patients) were used for validation.&#13;
&#13;
Results &#13;
The overall F1 scores on the test dataset for the macro-phases and all 11 phases were 0.96 and 0.90, respectively. The recall values for diagnostics, marking, injection, dissection and bleeding were 1.00, 1.00, 0.95, 0.96 and 0.93, respectively.&#13;
&#13;
Conclusions &#13;
The algorithm classified operational phases during ESD with high accuracy. A precise evaluation of phase distribution may allow for the development of objective quality metrics for quality control and training.</abstract>
    <parentTitle language="eng">Endoscopy</parentTitle>
    <identifier type="doi">10.1055/s-0045-1806324</identifier>
    <enrichment key="ConferenceStatement">ESGE Days 2025</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Markus W. Scheppach</author>
    <author>Danilo Weber Nunes</author>
    <author>X. Arizi</author>
    <author>David Rauber</author>
    <author>Andreas Probst</author>
    <author>Sandra Nagl</author>
    <author>Christoph Römmele</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <author>Alanna Ebigbo</author>
    <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="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
    <collection role="DFGFachsystematik" number="1">Ingenieurwissenschaften</collection>
  </doc>
  <doc>
    <id>8353</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>8</pageNumber>
    <edition/>
    <issue>1</issue>
    <volume>6</volume>
    <type>article</type>
    <publisherName>Wiley</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2025-07-12</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Artificial intelligence-assisted endoscopy and examiner confidence : a study on human–artificial intelligence interaction in Barrett's Esophagus (With Video)</title>
    <abstract language="eng">Objective&#13;
Despite high stand-alone performance, studies demonstrate that artificial intelligence (AI)-supported endoscopic diagnostics often fall short in clinical applications due to human-AI interaction factors. This video-based trial on Barrett's esophagus aimed to investigate how examiner behavior, their levels of confidence, and system usability influence the diagnostic outcomes of AI-assisted endoscopy.&#13;
&#13;
Methods&#13;
The present analysis employed data from a multicenter randomized controlled tandem video trial involving 22 endoscopists with varying degrees of expertise. Participants were tasked with evaluating a set of 96 endoscopic videos of Barrett's esophagus in two distinct rounds, with and without AI assistance. Diagnostic confidence levels were recorded, and decision changes were categorized according to the AI prediction. Additional surveys assessed user experience and system usability ratings.&#13;
&#13;
Results&#13;
AI assistance significantly increased examiner confidence levels (p &lt; 0.001) and accuracy. Withdrawing AI assistance decreased confidence (p &lt; 0.001), but not accuracy. Experts consistently reported higher confidence than non-experts (p &lt; 0.001), regardless of performance. Despite improved confidence, correct AI guidance was disregarded in 16% of all cases, and 9% of initially correct diagnoses were changed to incorrect ones. Overreliance on AI, algorithm aversion, and uncertainty in AI predictions were identified as key factors influencing outcomes. The System Usability Scale questionnaire scores indicated good to excellent usability, with non-experts scoring 73.5 and experts 85.6.&#13;
&#13;
Conclusions&#13;
Our findings highlight the pivotal function of examiner behavior in AI-assisted endoscopy. To fully realize the benefits of AI, implementing explainable AI, improving user interfaces, and providing targeted training are essential. Addressing these factors could enhance diagnostic accuracy and confidence in clinical practice.</abstract>
    <parentTitle language="eng">DEN Open</parentTitle>
    <identifier type="doi">10.1002/deo2.70150</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>David Roser</author>
    <author>Michael Meinikheim</author>
    <author>Anna Muzalyova</author>
    <author>Robert Mendel</author>
    <author>Christoph Palm</author>
    <author>Andreas Probst</author>
    <author>Sandra Nagl</author>
    <author>Markus W. Scheppach</author>
    <author>Christoph Römmele</author>
    <author>Elisabeth Schnoy</author>
    <author>Nasim Parsa</author>
    <author>Michael F. Byrne</author>
    <author>Helmut Messmann</author>
    <author>Alanna Ebigbo</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="oaweg" number="">Gold Open Access- Erstveröffentlichung in einem/als Open-Access-Medium</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>6040</id>
    <completedYear/>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>S169</pageNumber>
    <edition/>
    <issue>S02</issue>
    <volume>55</volume>
    <type>conferencepresentation</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2023-05-04</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">AI-assisted detection and characterization of early Barrett's neoplasia: Results of an Interim analysis</title>
    <abstract language="eng">Aims &#13;
Evaluation of the add-on effect an artificial intelligence (AI) based clinical decision support system has on the performance of endoscopists with different degrees of expertise in the field of Barrett's esophagus (BE) and Barrett's esophagus-related neoplasia (BERN).&#13;
&#13;
Methods &#13;
The support system is based on a multi-task deep learning model trained to solve a segmentation and several classification tasks. The training approach represents an extension of the ECMT semi-supervised learning algorithm. The complete system evaluates a decision tree between estimated motion, classification, segmentation, and temporal constraints, to decide when and how the prediction is highlighted to the observer. In our current study, ninety-six video cases of patients with BE and BERN were prospectively collected and assessed by Barrett's specialists and non-specialists. All video cases were evaluated twice – with and without AI assistance. The order of appearance, either with or without AI support, was assigned randomly. Participants were asked to detect and characterize regions of dysplasia or early neoplasia within the video sequences.&#13;
&#13;
Results &#13;
Standalone sensitivity, specificity, and accuracy of the AI system were 92.16%, 68.89%, and 81.25%, respectively. Mean sensitivity, specificity, and accuracy of expert endoscopists without AI support were 83,33%, 58,20%, and 71,48 %, respectively. Gastroenterologists without Barrett's expertise but with AI support had a comparable performance with a mean sensitivity, specificity, and accuracy of 76,63%, 65,35%, and 71,36%, respectively.&#13;
&#13;
Conclusions &#13;
Non-Barrett's experts with AI support had a similar performance as experts in a video-based study.</abstract>
    <parentTitle language="eng">Endoscopy</parentTitle>
    <identifier type="doi">10.1055/s-0043-1765437</identifier>
    <enrichment key="ConferenceStatement">ESGE Days 2023</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Michael Meinikheim</author>
    <author>Robert Mendel</author>
    <author>Andreas Probst</author>
    <author>Markus W. Scheppach</author>
    <author>Elisabeth Schnoy</author>
    <author>Sandra Nagl</author>
    <author>Christoph Römmele</author>
    <author>Friederike Prinz</author>
    <author>Jakob Schlottmann</author>
    <author>Daniela Golger</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <author>Alanna Ebigbo</author>
    <collection role="ddc" number="61">Medizin und Gesundheit</collection>
    <collection role="ddc" number="000">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="16314">Lebenswissenschaften und Ethik</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
  <doc>
    <id>7948</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>article</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace>Stuttgart</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2025-02-15</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Artificial intelligence improves submucosal vessel detection during third space endoscopy</title>
    <abstract language="eng">Background and study aims: While artificial intelligence (AI) shows high potential in decision support for diagnostic gastrointestinal endoscopy, its role in therapeutic endoscopy remains unclear. Third space endoscopic procedures pose the risk of intraprocedural bleeding. Therefore, we aimed to develop an AI algorithm for intraprocedural blood vessel detection. Patients and Methods: Using a test dataset with 101 standardized video clips containing 200 predefined submucosal blood vessels, 19 endoscopists were evaluated for the vessel detection rate (VDR) and time (VDT) with and without support of an AI algorithm. Test subjects were grouped according to experience in ESD. Results: With AI support, endoscopists VDR increased from 56.4% [CI 54.1–58.6] to 72.4% [CI 70.3–74.4]. Endoscopists‘ VDT dropped from 6.7sec [CI 6.2-7.1] to 5.2sec [CI 4.8-5.7]. False positive (FP) readings appeared in 4.5% of frames and were marked significantly shorter than true positives (6.0sec [CI 5.28-6.70] vs. 0.7sec [CI 0.55-0.87]). Conclusions: AI improved the vessel detection rate and time of endoscopists during third space endoscopy. While these data need to be corroborated by clinical trials, AI may prove to be an invaluable tool for the improvement of endoscopic interventions.</abstract>
    <parentTitle language="eng">Endoscopy</parentTitle>
    <identifier type="doi">10.1055/a-2534-1164</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>Markus W. Scheppach</author>
    <author>Robert Mendel</author>
    <author>Anna Muzalyova</author>
    <author>David Rauber</author>
    <author>Andreas Probst</author>
    <author>Sandra Nagl</author>
    <author>Christoph Römmele</author>
    <author>Hon Chi Yip</author>
    <author>Louis Ho Shing Lau</author>
    <author>Stefan Karl Gölder</author>
    <author>Arthur Schmidt</author>
    <author>Konstantinos Kouladouros</author>
    <author>Mohamed Abdelhafez</author>
    <author>Benjamin M. Walter</author>
    <author>Michael Meinikheim</author>
    <author>Philip Wai Yan Chiu</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <author>Alanna Ebigbo</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Artificial Intelligence</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Third Space Endoscopy</value>
    </subject>
    <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>
    <collection role="DFGFachsystematik" number="1">Ingenieurwissenschaften</collection>
  </doc>
  <doc>
    <id>8499</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst>e612</pageFirst>
    <pageLast>e613</pageLast>
    <pageNumber/>
    <edition/>
    <issue>08</issue>
    <volume>63</volume>
    <type>conferencepresentation</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace>Stuttgart</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2025-09-22</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Künstliche Intelligenz-basierte Erkennung von interventionellen Phasen bei der endoskopischen Submukosadissektion</title>
    <abstract language="deu">Einleitung: Die endoskopische Submukosadissektion (ESD) ist ein komplexes endoskopisches Verfahren, das technische Expertise erfordert. Objektive Methoden zur Analyse von interventionellen Abläufen bei ESD könnten für Qualitätssicherung und Ausbildung, wie auch eine automatische Befunderstellung von Nutzen sein.&#13;
&#13;
Ziele: In dieser Studie wurde ein KI-Algorithmus für die Erkennung und Klassifizierung der interventionellen Phasen der ESD entwickelt, um die technische Basis für eine standardisierte Leistungsbewertung und automatische Befunderstellung zu schaffen.&#13;
&#13;
Methodik: Vollständige ESD-Videoaufnahmen von 49 Patienten wurden retrospektiv zusammengestellt. Der Datensatz umfasste 6.390.151 Einzelbilder, die alle für die folgenden interventionellen Phasen annotiert wurden: Diagnostik, Markierung, Injektion, Dissektion und Hämostase. 3.973.712 Bilder (28 Patienten) wurden für das Training eines Video-Swin-Transformers genutzt. Dabei wurde temporale Information durch standardisierte BIldextraktion in festgelegten zeitlichen Abständen zum analysierten Bild inkorporiert. 2.416.439 separate Bilder (21 Patienten) wurden für eine interne Validierung genutzt.&#13;
&#13;
Ergebnis: Bei der internen Evaluation erreichte das System insgesamt einen F1-Wert von 0,88. Es wurden F1-Werte von 0,99, 0,89, 0,89, 0,91 und 0,52 für Diagnostik, Markierung, Injektion, Dissektion bzw. Blutungsmanagement gemessen. Die Sensitivitäten für dieselben Parameter betrugen 1,00, 0,80, 0,94, 0,89 und 0,67, die Spezifitäten lagen bei 1,00, 1,00, 0,98, 0,88 und 0,93. Positive prädiktive Werte wurden mit 0,98, 1,00, 0,85, 0,94 und 0,43 gemessen.&#13;
&#13;
Schlussfolgerung: In dieser vorläufigen Studie zeigte ein KI-Algorithmus eine hohe Leistungsfähigkeit für die Einzelbild-Erkennung von Verfahrensphasen während der ESD. Die vergleichsweise niedrige Leistung für die Blutungsphase wurde auf das seltene Auftreten von Blutungsepisoden im Trainingsdatensatz zurückgeführt, der zu diesem Zeitpunkt nur Videos in voller Länge umfasste. Die zukünftige Entwicklung des Algorithmus wird sich auf die Reduzierung von Klassenungleichgewichten durch selektive Annotationsprotokolle konzentrieren.</abstract>
    <parentTitle language="deu">Zeitschrift für Gastroenterologie</parentTitle>
    <identifier type="doi">10.1055/s-0045-1811093</identifier>
    <enrichment key="ConferenceStatement">79. Jahrestagung der DGVS mit Sektion Endoskopie Jahrestagung der Deutschen Gesellschaft für Allgemein- und Viszeralchirurgie mit den Arbeitsgemeinschaften der DGAV und Jahrestagung der CACP. - Viszeralmedizin 2025; 15-20. September 2025</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Markus W. Scheppach</author>
    <author>Danilo Weber Nunes</author>
    <author>David Rauber</author>
    <author>X. Arizi</author>
    <author>Andreas Probst</author>
    <author>Sandra Nagl</author>
    <author>Christoph Römmele</author>
    <author>Alanna Ebigbo</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <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="3">Lebenswissenschaften</collection>
    <collection role="othforschungsschwerpunkt" number="">Gesundheit und Soziales</collection>
  </doc>
  <doc>
    <id>8500</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>8</issue>
    <volume>63</volume>
    <type>conferencepresentation</type>
    <publisherName>Thieme</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2025-09-22</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Instrumentenerkennung während der endoskopischen Submukosadissektion mittels künstlicher Intelligenz</title>
    <abstract language="deu">Einleitung: Die endoskopische Submukosadissektion (ESD) ist eine komplexe Technik zur Resektion gastrointestinaler Frühneoplasien. Dabei werden für die verschiedenen Schritte der Intervention spezifische endoskopische Instrumente verwendet. Die präzise und automatische Erkennung und Abgrenzung der verwendeten Instrumente (Injektionsnadeln, elektrochirurgische Messer mit unterschiedlichen Konfigurationen, hämostatische Zangen) könnte wertvolle Informationen über den Fortschritt und die Verfahrensmerkmale der ESD liefern und eine automatische standardisierte Berichterstattung ermöglichen.&#13;
&#13;
Ziele: Ziel dieser Studie war die Entwicklung eines KI-Algorithmus zur Erkennung und Delineation von endoskopischen Instrumenten bei der ESD.&#13;
&#13;
Methodik: 17 ESD-Videos (9×rektal, 5×ösophageal, 3×gastrisch) wurden retrospektiv zusammengestellt. Auf 8530 Einzelbilder dieser Videos wurden durch 2 Studienmitarbeiter die folgenden Klassen eingezeichnet: Hakenmesser – Spitze, Hakenmesser – Katheter, Nadelmesser – Spitze und – Katheter, Injektionsnadel -Spitze und – Katheter sowie hämostatische Zange – Spitze und – Katheter. Der annotierte Datensatz wurde zum Training eines DeepLabV3+-Deep-Learning-Algorithmus mit ConvNeXt-Backbone zur Erkennung und Abgrenzung der genannten Klassen verwendet. Die Evaluation erfolgte durch 5-fache interne Kreuzvalidierung.&#13;
&#13;
Ergebnis: Die Validierung auf Einzelpixelbasis ergab insgesamt einen F1-Score von 0,80, eine Sensitivität von 0,81 und eine Spezifität von 1,00. Es wurden F1-Scores von 1,00, 0,97, 0,80, 0,98, 0,85, 0,97, 0,80, 0,51 bzw. 0,85 für die Klassen Hakenmesser – Katheter und – Spitze, Nadelmesser – Katheter und – Spitze, Injektionsnadel – Katheter und – Spitze, hämostatische Zange – Katheter und – Spitze gemessen.&#13;
&#13;
Schlussfolgerung: In dieser Studie wurden die wichtigsten endoskopischen Instrumente, die während der ESD verwendet werden, mit hoher Genauigkeit erkannt. Die geringere Leistung bei der hämostatische Zange – Katheter kann auf die Unterrepräsentation dieser Klassen in den Trainingsdaten zurückgeführt werden. Zukünftige Studien werden sich auf die Erweiterung der Instrumentenklassen sowie auf die Ausbalancierung der Trainingsdaten konzentrieren.</abstract>
    <parentTitle language="deu">Zeitschrift für Gastroenterologie</parentTitle>
    <identifier type="doi">10.1055/s-0045-1811092</identifier>
    <enrichment key="ConferenceStatement">79. Jahrestagung der DGVS mit Sektion Endoskopie Jahrestagung der Deutschen Gesellschaft für Allgemein- und Viszeralchirurgie mit den Arbeitsgemeinschaften der DGAV und Jahrestagung der CACP. - Viszeralmedizin 2025; 15.-20. September 2025</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Markus W. Scheppach</author>
    <author>David Rauber</author>
    <author>C. Zingler</author>
    <author>Danilo Weber Nunes</author>
    <author>Andreas Probst</author>
    <author>Christoph Römmele</author>
    <author>Sandra Nagl</author>
    <author>Alanna Ebigbo</author>
    <author>Christoph Palm</author>
    <author>Helmut Messmann</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</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="3">Lebenswissenschaften</collection>
    <collection role="othforschungsschwerpunkt" number="">Gesundheit und Soziales</collection>
  </doc>
</export-example>
